1
|
Wang K, Gupta V, Lee CS, Mao Y, Kilic MNT, Li Y, Huang Z, Liao WK, Choudhary A, Agrawal A. XElemNet: towards explainable AI for deep neural networks in materials science. Sci Rep 2024; 14:25178. [PMID: 39448747 PMCID: PMC11502843 DOI: 10.1038/s41598-024-76535-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2024] [Accepted: 10/15/2024] [Indexed: 10/26/2024] Open
Abstract
Recent progress in deep learning has significantly impacted materials science, leading to accelerated material discovery and innovation. ElemNet, a deep neural network model that predicts formation energy from elemental compositions, exemplifies the application of deep learning techniques in this field. However, the "black-box" nature of deep learning models often raises concerns about their interpretability and reliability. In this study, we propose XElemNet to explore the interpretability of ElemNet by applying a series of explainable artificial intelligence (XAI) techniques, focusing on post-hoc analysis and model transparency. The experiments with artificial binary datasets reveal ElemNet's effectiveness in predicting convex hulls of element-pair systems across periodic table groups, indicating its capability to effectively discern elemental interactions in most cases. Additionally, feature importance analysis within ElemNet highlights alignment with chemical properties of elements such as reactivity and electronegativity. XElemNet provides insights into the strengths and limitations of ElemNet and offers a potential pathway for explaining other deep learning models in materials science.
Collapse
Affiliation(s)
- Kewei Wang
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | - Vishu Gupta
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | - Claire Songhyun Lee
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | - Yuwei Mao
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | | | - Youjia Li
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | - Zanhua Huang
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | - Wei-Keng Liao
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | - Alok Choudhary
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA
| | - Ankit Agrawal
- Electrical and Computer Engineering, Northwestern University, Evanston, 60201, USA.
| |
Collapse
|
2
|
Speckhard D, Bechtel T, Ghiringhelli LM, Kuban M, Rigamonti S, Draxl C. How big is big data? Faraday Discuss 2024. [PMID: 39315406 DOI: 10.1039/d4fd00102h] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/25/2024]
Abstract
Big data has ushered in a new wave of predictive power using machine-learning models. In this work, we assess what big means in the context of typical materials-science machine-learning problems. This concerns not only data volume, but also data quality and veracity as much as infrastructure issues. With selected examples, we ask (i) how models generalize to similar datasets, (ii) how high-quality datasets can be gathered from heterogenous sources, (iii) how the feature set and complexity of a model can affect expressivity, and (iv) what infrastructure requirements are needed to create larger datasets and train models on them. In sum, we find that big data present unique challenges along very different aspects that should serve to motivate further work.
Collapse
Affiliation(s)
- Daniel Speckhard
- Physics Department and CSMB, Humboldt-Universität zu Berlin, Zum Großen Windkanal 2, 12489 Berlin, Germany.
- Max Planck Institute for Solid State Research, Heisenbergstraaae 1, 70569 Stuttgart, Germany
| | - Tim Bechtel
- Physics Department and CSMB, Humboldt-Universität zu Berlin, Zum Großen Windkanal 2, 12489 Berlin, Germany.
- Max Planck Institute for Solid State Research, Heisenbergstraaae 1, 70569 Stuttgart, Germany
| | - Luca M Ghiringhelli
- Department of Materials Science and Engineering, Friedrich-Alexander Universität Erlangen-Nürnberg, Dr.-Mack-Str. 77, 90762 Fürth, Germany
| | - Martin Kuban
- Physics Department and CSMB, Humboldt-Universität zu Berlin, Zum Großen Windkanal 2, 12489 Berlin, Germany.
| | - Santiago Rigamonti
- Physics Department and CSMB, Humboldt-Universität zu Berlin, Zum Großen Windkanal 2, 12489 Berlin, Germany.
| | - Claudia Draxl
- Physics Department and CSMB, Humboldt-Universität zu Berlin, Zum Großen Windkanal 2, 12489 Berlin, Germany.
- Max Planck Institute for Solid State Research, Heisenbergstraaae 1, 70569 Stuttgart, Germany
| |
Collapse
|
3
|
Xue SD, Hong QJ. Materials Properties Prediction (MAPP): Empowering the Prediction of Material Properties Solely Based on Chemical Formulas. MATERIALS (BASEL, SWITZERLAND) 2024; 17:4176. [PMID: 39274568 PMCID: PMC11396529 DOI: 10.3390/ma17174176] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/08/2024] [Revised: 08/17/2024] [Accepted: 08/21/2024] [Indexed: 09/16/2024]
Abstract
Predicting material properties has always been a challenging task in materials science. With the emergence of machine learning methodologies, new avenues have opened up. In this study, we build upon our recently developed graph neural network (GNN) approach to construct models that predict four distinct material properties. Our graph model represents materials as element graphs, with chemical formulas serving as the only input. This approach ensures permutation invariance, offering a robust solution to prior limitations. By employing bootstrap methods to train this individual GNN, we further enhance the reliability and accuracy of our predictions. With multi-task learning, we harness the power of extensive datasets to boost the performance of smaller ones. We introduce the inaugural version of the Materials Properties Prediction (MAPP) framework, empowering the prediction of material properties solely based on chemical formulas.
Collapse
Affiliation(s)
- Si-Da Xue
- School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ 85287, USA
| | - Qi-Jun Hong
- School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ 85287, USA
| |
Collapse
|
4
|
Akinpelu A, Bhullar M, Yao Y. Discovery of novel materials through machine learning. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2024; 36:453001. [PMID: 39106893 DOI: 10.1088/1361-648x/ad6bdb] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Accepted: 08/06/2024] [Indexed: 08/09/2024]
Abstract
Experimental exploration of new materials relies heavily on a laborious trial-and-error approach. In addition to substantial time and resource requirements, traditional experiments and computational modelling are typically limited in finding target materials within the enormous chemical space. Therefore, creating innovative techniques to expedite material discovery becomes essential. Recently, machine learning (ML) has emerged as a valuable tool for material discovery, garnering significant attention due to its remarkable advancements in prediction accuracy and time efficiency. This rapidly developing computational technique accelerates the search and optimization process and enables the prediction of material properties at a minimal computational cost, thereby facilitating the discovery of novel materials. We provide a comprehensive overview of recent studies on discovering new materials by predicting materials and their properties using ML techniques. Beginning with an introduction of the fundamental principles of ML methods, we subsequently examine the current research landscape on the applications of ML in predicting material properties that lead to the discovery of novel materials. Finally, we discuss challenges in employing ML within materials science, propose potential solutions, and outline future research directions.
Collapse
Affiliation(s)
- Akinwumi Akinpelu
- Department of Physics and Engineering Physics, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada
| | - Mangladeep Bhullar
- Department of Physics and Engineering Physics, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada
| | - Yansun Yao
- Department of Physics and Engineering Physics, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada
| |
Collapse
|
5
|
Zhu D, Xin Z, Zheng S, Wang Y, Yang X. Addressing the Accuracy-Cost Trade-off in Material Property Prediction Using a Teacher-Student Strategy. J Chem Theory Comput 2024; 20:5743-5750. [PMID: 38875176 DOI: 10.1021/acs.jctc.4c00625] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/16/2024]
Abstract
Deep learning has catalyzed a transformative shift in material discovery, offering a key advantage over traditional experimental and theoretical methods by significantly reducing associated costs. Models adept at predicting properties from chemical compositions alone do not require structural information. However, this cost-efficient approach compromises model precision, particularly in Chemical Composition-based Property Prediction Models (CPMs), which are notably less accurate than Structure-based Property Prediction Models (SPMs). Addressing this challenge, our study introduces a novel Teacher-Student (TS) strategy, where a pretrained SPM serves as an instructive 'teacher' to enhance the CPM's precision. This TS strategy successfully harmonizes low-cost exploration with high accuracy, achieving a significant 47.1% reduction in relative error in scenarios involving 100 data entries. We also evaluate the effectiveness of the proposed strategy by employing perovskites as a case study. This method represents a significant advancement in the exploration and identification of valuable materials, leveraging CPM's potential while overcoming its precision limitations.
Collapse
Affiliation(s)
- Dong Zhu
- Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Zhikuang Xin
- Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Siming Zheng
- Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Yangang Wang
- Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Xiaoyu Yang
- Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| |
Collapse
|
6
|
Yuan S, Dordevic SV. Diffusion models for conditional generation of hypothetical new families of superconductors. Sci Rep 2024; 14:10275. [PMID: 38704484 PMCID: PMC11069549 DOI: 10.1038/s41598-024-61040-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2024] [Accepted: 04/30/2024] [Indexed: 05/06/2024] Open
Abstract
Effective computational search holds great potential for aiding the discovery of high-temperature superconductors (HTSs), especially given the lack of systematic methods for their discovery. Recent progress has been made in this area with machine learning, especially with deep generative models, which have been able to outperform traditional manual searches at predicting new superconductors within existing superconductor families but have yet to be able to generate completely new families of superconductors. We address this limitation by implementing conditioning-a method to control the generation process-for our generative model and develop SuperDiff, a denoising diffusion probabilistic model with iterative latent variable refinement conditioning for HTS discovery-the first deep generative model for superconductor discovery with conditioning on reference compounds. With SuperDiff, by being able to control the generation process, we were able to computationally generate completely new families of hypothetical superconductors for the very first time. Given that SuperDiff also has relatively fast training and inference times, it has the potential to be a very powerful tool for accelerating the discovery of new superconductors and enhancing our understanding of them.
Collapse
Affiliation(s)
- Samuel Yuan
- Homestead High School, Cupertino, CA, 95014, USA.
| | - S V Dordevic
- Department of Physics, The University of Akron, Akron, OH, 44325, USA
| |
Collapse
|
7
|
Han J, Li T, He Y, Yang Z. Predicting the effect of chemicals on fruit using graph neural networks. Sci Rep 2024; 14:8203. [PMID: 38589529 PMCID: PMC11002035 DOI: 10.1038/s41598-024-58991-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Accepted: 04/05/2024] [Indexed: 04/10/2024] Open
Abstract
The neural network method is a type of machine learning that has made significant advances over the past few years in a variety of fields, particularly text, speech, images, videos, etc. In areas where data is unstructured, traditional machine learning has not been able to surpass the 'glass ceiling'; therefore, researchers have turned to neural networks as auxiliary tools to achieve significant breakthroughs or develop new research methods. An array of computational chemistry challenges can be addressed using neural networks, including virtual screening, quantitative structure-activity relationships, protein structure prediction, materials design, quantum chemistry, and property prediction, among others. This paper proposes a strategy for predicting the chemical properties of fruits by using graph neural networks, and it aims to provide some guidance to researchers and streamline the identification process.
Collapse
Affiliation(s)
- Junming Han
- College of Food Science and Technology, Yunnan Agricultural University, Kunming, 650201, China
| | - Tong Li
- Yunnan Agricultural University, Kunming, 650201, China.
| | - Yun He
- College of Big Data, Yunnan Agricultural University, Kunming, 650201, China
| | - Ziyi Yang
- College of Agronomy and Biotechnology, Yunnan Agricultural University, Kunming, 650201, China
| |
Collapse
|
8
|
Rossignol H, Minotakis M, Cobelli M, Sanvito S. Machine-Learning-Assisted Construction of Ternary Convex Hull Diagrams. J Chem Inf Model 2024; 64:1828-1840. [PMID: 38271693 PMCID: PMC10966649 DOI: 10.1021/acs.jcim.3c01391] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 01/04/2024] [Accepted: 01/04/2024] [Indexed: 01/27/2024]
Abstract
In the search for novel intermetallic ternary alloys, much of the effort goes into performing a large number of ab initio calculations covering a wide range of compositions and structures. These are essential to building a reliable convex hull diagram. While density functional theory (DFT) provides accurate predictions for many systems, its computational overheads set a throughput limit on the number of hypothetical phases that can be probed. Here, we demonstrate how an ensemble of machine-learning (ML) spectral neighbor-analysis potentials (SNAPs) can be integrated into a workflow for the construction of accurate ternary convex hull diagrams, highlighting regions that are fertile for materials discovery. Our workflow relies on using available binary-alloy data both to train the SNAP models and to create prototypes for ternary phases. From the prototype structures, all unique ternary decorations are created and used to form a pool of candidate compounds. The SNAPs ensemble is then used to prerelax the structures and screen the most favorable prototypes before using DFT to build the final phase diagram. As constructed, the proposed workflow relies on no extra first-principles data to train the ML surrogate model and yields a DFT-level accurate convex hull. We demonstrate its efficacy by investigating the Cu-Ag-Au and Mo-Ta-W ternary systems.
Collapse
Affiliation(s)
- Hugo Rossignol
- School of Physics and CRANN
Institute, Trinity College Dublin, College Green, Dublin 2, Ireland
| | - Michail Minotakis
- School of Physics and CRANN
Institute, Trinity College Dublin, College Green, Dublin 2, Ireland
| | - Matteo Cobelli
- School of Physics and CRANN
Institute, Trinity College Dublin, College Green, Dublin 2, Ireland
| | - Stefano Sanvito
- School of Physics and CRANN
Institute, Trinity College Dublin, College Green, Dublin 2, Ireland
| |
Collapse
|
9
|
Korolev V, Mitrofanov A. Coarse-Grained Crystal Graph Neural Networks for Reticular Materials Design. J Chem Inf Model 2024; 64:1919-1931. [PMID: 38456446 DOI: 10.1021/acs.jcim.3c02083] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/09/2024]
Abstract
Reticular materials, including metal-organic frameworks and covalent organic frameworks, combine the relative ease of synthesis and an impressive range of applications in various fields from gas storage to biomedicine. Diverse properties arise from the variation of building units─metal centers and organic linkers─in almost infinite chemical space. Such variation substantially complicates the experimental design and promotes the use of computational methods. In particular, the most successful artificial intelligence algorithms for predicting the properties of reticular materials are atomic-level graph neural networks, which optionally incorporate domain knowledge. Nonetheless, the data-driven inverse design involving these models suffers from the incorporation of irrelevant and redundant features such as a full atomistic graph and network topology. In this study, we propose a new way of representing materials, aiming to overcome the limitations of existing methods; the message passing is performed on a coarse-grained crystal graph that comprises molecular building units. To highlight the merits of our approach, we assessed the predictive performance and energy efficiency of neural networks built on different materials representations, including composition-based and crystal-structure-aware models. Coarse-grained crystal graph neural networks showed decent accuracy at low computational costs, making them a valuable alternative to omnipresent atomic-level algorithms. Moreover, the presented models can be successfully integrated into an inverse materials design pipeline as estimators of the objective function. Overall, the coarse-grained crystal graph framework is aimed at challenging the prevailing atom-centric perspective on reticular materials design.
Collapse
Affiliation(s)
- Vadim Korolev
- Department of Chemistry, Lomonosov Moscow State University, Moscow 119991, Russia
- MSU Institute for Artificial Intelligence, Lomonosov Moscow State University, Moscow 119192, Russia
| | - Artem Mitrofanov
- Department of Chemistry, Lomonosov Moscow State University, Moscow 119991, Russia
- MSU Institute for Artificial Intelligence, Lomonosov Moscow State University, Moscow 119192, Russia
| |
Collapse
|
10
|
Jung SG, Jung G, Cole JM. Automatic Prediction of Peak Optical Absorption Wavelengths in Molecules Using Convolutional Neural Networks. J Chem Inf Model 2024; 64:1486-1501. [PMID: 38422386 PMCID: PMC10934802 DOI: 10.1021/acs.jcim.3c01792] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Revised: 02/15/2024] [Accepted: 02/16/2024] [Indexed: 03/02/2024]
Abstract
Molecular design depends heavily on optical properties for applications such as solar cells and polymer-based batteries. Accurate prediction of these properties is essential, and multiple predictive methods exist, from ab initio to data-driven techniques. Although theoretical methods, such as time-dependent density functional theory (TD-DFT) calculations, have well-established physical relevance and are among the most popular methods in computational physics and chemistry, they exhibit errors that are inherent in their approximate nature. These high-throughput electronic structure calculations also incur a substantial computational cost. With the emergence of big-data initiatives, cost-effective, data-driven methods have gained traction, although their usability is highly contingent on the degree of data quality and sparsity. In this study, we present a workflow that employs deep residual convolutional neural networks (DR-CNN) and gradient boosting feature selection to predict peak optical absorption wavelengths (λmax) exclusively from SMILES representations of dye molecules and solvents; one would normally measure λmax using UV-vis absorption spectroscopy. We use a multifidelity modeling approach, integrating 34,893 DFT calculations and 26,395 experimentally derived λmax data, to deliver more accurate predictions via a Bayesian-optimized gradient boosting machine. Our approach is benchmarked against the state of the art that is reported in the scientific literature; results demonstrate that learnt representations via a DR-CNN workflow that is integrated with other machine learning methods can accelerate the design of molecules for specific optical characteristics.
Collapse
Affiliation(s)
- Son Gyo Jung
- Cavendish
Laboratory, Department of Physics, University
of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K.
- ISIS
Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K.
- Research
Complex at Harwell, Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K.
| | - Guwon Jung
- Cavendish
Laboratory, Department of Physics, University
of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K.
- Research
Complex at Harwell, Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K.
- Scientific
Computing Department, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K.
| | - Jacqueline M. Cole
- Cavendish
Laboratory, Department of Physics, University
of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K.
- ISIS
Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K.
- Research
Complex at Harwell, Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K.
| |
Collapse
|
11
|
Han G, Vasylenko A, Daniels LM, Collins CM, Corti L, Chen R, Niu H, Manning TD, Antypov D, Dyer MS, Lim J, Zanella M, Sonni M, Bahri M, Jo H, Dang Y, Robertson CM, Blanc F, Hardwick LJ, Browning ND, Claridge JB, Rosseinsky MJ. Superionic lithium transport via multiple coordination environments defined by two-anion packing. Science 2024; 383:739-745. [PMID: 38359130 DOI: 10.1126/science.adh5115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2023] [Accepted: 01/17/2024] [Indexed: 02/17/2024]
Abstract
Fast cation transport in solids underpins energy storage. Materials design has focused on structures that can define transport pathways with minimal cation coordination change, restricting attention to a small part of chemical space. Motivated by the greater structural diversity of binary intermetallics than that of the metallic elements, we used two anions to build a pathway for three-dimensional superionic lithium ion conductivity that exploits multiple cation coordination environments. Li7Si2S7I is a pure lithium ion conductor created by an ordering of sulphide and iodide that combines elements of hexagonal and cubic close-packing analogously to the structure of NiZr. The resulting diverse network of lithium positions with distinct geometries and anion coordination chemistries affords low barriers to transport, opening a large structural space for high cation conductivity.
Collapse
Affiliation(s)
- Guopeng Han
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Andrij Vasylenko
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Luke M Daniels
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Chris M Collins
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Lucia Corti
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
| | - Ruiyong Chen
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Hongjun Niu
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Troy D Manning
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Dmytro Antypov
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
| | - Matthew S Dyer
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
| | - Jungwoo Lim
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Stephenson Institute for Renewable Energy, University of Liverpool, Liverpool L69 7ZF, UK
| | - Marco Zanella
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Manel Sonni
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Mounib Bahri
- Albert Crewe Centre, University of Liverpool, Research Technology Building, Elisabeth Street, Pembroke Place, Liverpool L69 3GE, UK
| | - Hongil Jo
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
| | - Yun Dang
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Craig M Robertson
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
| | - Frédéric Blanc
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
- Stephenson Institute for Renewable Energy, University of Liverpool, Liverpool L69 7ZF, UK
| | - Laurence J Hardwick
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
- Stephenson Institute for Renewable Energy, University of Liverpool, Liverpool L69 7ZF, UK
| | - Nigel D Browning
- Albert Crewe Centre, University of Liverpool, Research Technology Building, Elisabeth Street, Pembroke Place, Liverpool L69 3GE, UK
- School of Engineering, Department of Mechanical, Materials and Aerospace Engineering, University of Liverpool, Liverpool L69 3GH, UK
| | - John B Claridge
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
| | - Matthew J Rosseinsky
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, UK
- Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, 51 Oxford Street, University of Liverpool, Liverpool L7 3NY, UK
| |
Collapse
|
12
|
Wang Z, Chen A, Tao K, Han Y, Li J. MatGPT: A Vane of Materials Informatics from Past, Present, to Future. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2024; 36:e2306733. [PMID: 37813548 DOI: 10.1002/adma.202306733] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Revised: 09/05/2023] [Indexed: 10/17/2023]
Abstract
Combining materials science, artificial intelligence (AI), physical chemistry, and other disciplines, materials informatics is continuously accelerating the vigorous development of new materials. The emergence of "GPT (Generative Pre-trained Transformer) AI" shows that the scientific research field has entered the era of intelligent civilization with "data" as the basic factor and "algorithm + computing power" as the core productivity. The continuous innovation of AI will impact the cognitive laws and scientific methods, and reconstruct the knowledge and wisdom system. This leads to think more about materials informatics. Here, a comprehensive discussion of AI models and materials infrastructures is provided, and the advances in the discovery and design of new materials are reviewed. With the rise of new research paradigms triggered by "AI for Science", the vane of materials informatics: "MatGPT", is proposed and the technical path planning from the aspects of data, descriptors, generative models, pretraining models, directed design models, collaborative training, experimental robots, as well as the efforts and preparations needed to develop a new generation of materials informatics, is carried out. Finally, the challenges and constraints faced by materials informatics are discussed, in order to achieve a more digital, intelligent, and automated construction of materials informatics with the joint efforts of more interdisciplinary scientists.
Collapse
Affiliation(s)
- Zhilong Wang
- National Key Laboratory of Science and Technology on Micro/Nano Fabrication, Shanghai Jiao Tong University, Shanghai, 200240, China
- Key Laboratory of Thin Film and Microfabrication of Ministry of Education, Department of Micro/Nano Electronics, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - An Chen
- National Key Laboratory of Science and Technology on Micro/Nano Fabrication, Shanghai Jiao Tong University, Shanghai, 200240, China
- Key Laboratory of Thin Film and Microfabrication of Ministry of Education, Department of Micro/Nano Electronics, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Kehao Tao
- National Key Laboratory of Science and Technology on Micro/Nano Fabrication, Shanghai Jiao Tong University, Shanghai, 200240, China
- Key Laboratory of Thin Film and Microfabrication of Ministry of Education, Department of Micro/Nano Electronics, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Yanqiang Han
- National Key Laboratory of Science and Technology on Micro/Nano Fabrication, Shanghai Jiao Tong University, Shanghai, 200240, China
- Key Laboratory of Thin Film and Microfabrication of Ministry of Education, Department of Micro/Nano Electronics, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Jinjin Li
- National Key Laboratory of Science and Technology on Micro/Nano Fabrication, Shanghai Jiao Tong University, Shanghai, 200240, China
- Key Laboratory of Thin Film and Microfabrication of Ministry of Education, Department of Micro/Nano Electronics, Shanghai Jiao Tong University, Shanghai, 200240, China
| |
Collapse
|
13
|
Kim S, Noh J, Gu GH, Chen S, Jung Y. Predicting synthesis recipes of inorganic crystal materials using elementwise template formulation. Chem Sci 2024; 15:1039-1045. [PMID: 38239693 PMCID: PMC10793203 DOI: 10.1039/d3sc03538g] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Accepted: 12/05/2023] [Indexed: 01/22/2024] Open
Abstract
While advances in computational techniques have accelerated virtual materials design, the actual synthesis of predicted candidate materials is still an expensive and slow process. While a few initial studies attempted to predict the synthesis routes for inorganic crystals, the existing models do not yield the priority of predictions and could produce thermodynamically unrealistic precursor chemicals. Here, we propose an element-wise graph neural network to predict inorganic synthesis recipes. The trained model outperforms the popularity-based statistical baseline model for the top-k exact match accuracy test, showing the validity of our approach for inorganic solid-state synthesis. We further validate our model by the publication-year-split test, where the model trained based on the materials data until the year 2016 is shown to successfully predict synthetic precursors for the materials synthesized after 2016. The high correlation between the probability score and prediction accuracy suggests that the probability score can be interpreted as a measure of confidence levels, which can offer the priority of the predictions.
Collapse
Affiliation(s)
- Seongmin Kim
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST) 291, Daehak-ro, Yuseong-gu Daejeon 34141 South Korea
| | - Juhwan Noh
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST) 291, Daehak-ro, Yuseong-gu Daejeon 34141 South Korea
| | - Geun Ho Gu
- School of Energy Technology, Korea Institute of Energy Technology 200 Hyuksin-ro Naju 58330 South Korea
| | - Shuan Chen
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST) 291, Daehak-ro, Yuseong-gu Daejeon 34141 South Korea
| | - Yousung Jung
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST) 291, Daehak-ro, Yuseong-gu Daejeon 34141 South Korea
- School of Chemical and Biological Engineering, Institute of Chemical Processes, Seoul National University 1, Gwanak-ro, Gwanak-gu Seoul 08826 South Korea
| |
Collapse
|
14
|
Zhang T, Chai Y, Wang S, Yu J, Jiang S, Zhu W, Fang Z, Li B. Recent Study Advances in Flexible Sensors Based on Polyimides. SENSORS (BASEL, SWITZERLAND) 2023; 23:9743. [PMID: 38139589 PMCID: PMC10747040 DOI: 10.3390/s23249743] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Revised: 12/05/2023] [Accepted: 12/07/2023] [Indexed: 12/24/2023]
Abstract
With the demand for healthy life and the great advancement of flexible electronics, flexible sensors are playing an irreplaceably important role in healthcare monitoring, wearable devices, clinic treatment, and so on. In particular, the design and application of polyimide (PI)-based sensors are emerging swiftly. However, the tremendous potential of PI in sensors is not deeply understood. This review focuses on recent studies in advanced applications of PI in flexible sensors, including PI nanofibers prepared by electrospinning as flexible substrates, PI aerogels as friction layers in triboelectric nanogenerator (TENG), PI films as sensitive layers based on fiber Bragg grating (FBG) in relative humidity (RH) sensors, photosensitive PI (PSPI) as sacrificial layers, and more. The simple laser-induced graphene (LIG) technique is also introduced in the application of PI graphitization to graphene. Finally, the prospect of PIs in the field of electronics is proposed in the review.
Collapse
Affiliation(s)
- Tianyong Zhang
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin), Tianjin 300072, China
- Tianjin Engineering Research Center of Functional Fine Chemicals, Tianjin 300354, China
| | - Yamei Chai
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
| | - Suisui Wang
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
| | - Jianing Yu
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
| | - Shuang Jiang
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
| | - Wenxuan Zhu
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
| | - Zihao Fang
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
| | - Bin Li
- Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China; (T.Z.); (Y.C.); (S.W.); (J.Y.); (S.J.); (W.Z.); (Z.F.)
- Tianjin Engineering Research Center of Functional Fine Chemicals, Tianjin 300354, China
| |
Collapse
|
15
|
Igou T, Zhong S, Reid E, Chen Y. Real-Time Sensor Data Profile-Based Deep Learning Method Applied to Open Raceway Pond Microalgal Productivity Prediction. ENVIRONMENTAL SCIENCE & TECHNOLOGY 2023; 57:17981-17989. [PMID: 37234045 PMCID: PMC10666538 DOI: 10.1021/acs.est.2c07578] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/14/2022] [Revised: 05/10/2023] [Accepted: 05/11/2023] [Indexed: 05/27/2023]
Abstract
Microalgal biotechnology holds the potential for renewable biofuels, bioproducts, and carbon capture applications due to unparalleled photosynthetic efficiency and diversity. Outdoor open raceway pond (ORP) cultivation enables utilization of sunlight and atmospheric carbon dioxide to drive microalgal biomass synthesis for production of bioproducts including biofuels; however, environmental conditions are highly dynamic and fluctuate both diurnally and seasonally, making ORP productivity prediction challenging without time-intensive physical measurements and location-specific calibrations. Here, for the first time, we present an image-based deep learning method for the prediction of ORP productivity. Our method is based on parameter profile plot images of sensor parameters, including pH, dissolved oxygen, temperature, photosynthetically active radiation, and total dissolved solids. These parameters can be remotely monitored without physical interaction with ORPs. We apply the model to data we generated during the Unified Field Studies of the Algae Testbed Public-Private-Partnership (ATP3 UFS), the largest publicly available ORP data set to date, which includes millions of sensor records and 598 productivities from 32 ORPs operated in 5 states in the United States. We demonstrate that this approach significantly outperforms an average value based traditional machine learning method (R2 = 0.77 ≫ R2 = 0.39) without considering bioprocess parameters (e.g., biomass density, hydraulic retention time, and nutrient concentrations). We then evaluate the sensitivity of image and monitoring data resolutions and input parameter variations. Our results demonstrate ORP productivity can be effectively predicted from remote monitoring data, providing an inexpensive tool for microalgal production and operational forecasting.
Collapse
Affiliation(s)
- Thomas Igou
- School
of Civil & Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
| | - Shifa Zhong
- Department
of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai 200241, PR China
| | - Elliot Reid
- School
of Civil & Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
| | - Yongsheng Chen
- School
of Civil & Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
| |
Collapse
|
16
|
Griesemer SD, Xia Y, Wolverton C. Accelerating the prediction of stable materials with machine learning. NATURE COMPUTATIONAL SCIENCE 2023; 3:934-945. [PMID: 38177590 DOI: 10.1038/s43588-023-00536-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Accepted: 09/14/2023] [Indexed: 01/06/2024]
Abstract
Despite the rise in computing power, the large space of possible combinations of elements and crystal structure types makes large-scale high-throughput surveys of stable materials prohibitively expensive, especially for complex materials and materials subject to environmental conditions such as finite temperature. When physics-based computational methods and labor-intensive experiments are not feasible, machine learning (ML) methods can be a rapid and powerful alternative. Owing to a wealth of experimental and first-principles data as well as improved ML frameworks designed for materials modeling, ML is shown to be effective in predicting stability parameters and accelerating the discovery of new stable materials. In this Review, we summarize the most recent advancements in applying ML methodologies in predicting materials stability, focusing particularly on predictions of zero- and finite-temperature stability. We also highlight the need for more ML development in predictions of other thermodynamic knobs, such as pressure and surface/interfacial energy, which practically impact materials stability.
Collapse
Affiliation(s)
- Sean D Griesemer
- Department of Materials Science and Engineering, Northwestern University, Evanston, IL, USA
| | - Yi Xia
- Department of Materials Science and Engineering, Northwestern University, Evanston, IL, USA
- Department of Mechanical and Materials Engineering, Portland State University, Portland, OR, USA
| | - Chris Wolverton
- Department of Materials Science and Engineering, Northwestern University, Evanston, IL, USA.
| |
Collapse
|
17
|
Kim E, Dordevic SV. ScGAN: a generative adversarial network to predict hypothetical superconductors. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2023; 36:025702. [PMID: 37757835 DOI: 10.1088/1361-648x/acfdeb] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/25/2023] [Accepted: 09/27/2023] [Indexed: 09/29/2023]
Abstract
Despite having been discovered more than three decades ago, high temperature superconductors (HTSs) lack both an explanation for their mechanisms and a systematic way to search for them. To aid this search, this project proposes ScGAN, a generative adversarial network (GAN) to efficiently predict new superconductors. ScGAN was trained on compounds in Open Quantum Materials Database and then transfer learned onto the SuperCon database or a subset of it. Once trained, the GAN was used to predict superconducting candidates, and approximately 70% of them were determined to be superconducting by a classification model-a 23-fold increase in discovery rate compared to manual search methods. Furthermore, more than 99% of predictions were novel materials, demonstrating that ScGAN was able to potentially predict completely new superconductors, including several promising HTS candidates. This project presents a novel, efficient way to search for new superconductors, which may be used in technological applications or provide insight into the unsolved problem of high temperature superconductivity.
Collapse
Affiliation(s)
- Evan Kim
- Tesla STEM High School, Redmond, WA 98053, United States of America
| | - S V Dordevic
- Department of Physics, The University of Akron, Akron, OH 44325, United States of America
| |
Collapse
|
18
|
Su Y, Wang J, Zou Y. Machine Learning-Aided High-Throughput First-Principles Calculations to Predict the Formation Energy of μ Phase. ACS OMEGA 2023; 8:37317-37328. [PMID: 37841158 PMCID: PMC10568586 DOI: 10.1021/acsomega.3c05146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Accepted: 09/21/2023] [Indexed: 10/17/2023]
Abstract
The μ phase is a type of hard and brittle constituent that exists in high-temperature alloys. The formation energy is a crucial thermochemical datum, and the accurate calculation of the formation energy of the μ phase contributes to the material design of high-temperature alloys. Traditional first-principles calculations demand significant computational time and resources. In this study, an innovative machine learning (ML)-based approach to accurately predict the formation energy of the μ phase is proposed. This approach involves the utilization of six algorithms and two model evaluation methods to construct the ML models. Leveraging a comprehensive data set containing 1036 binary configurations of the μ phase, the model trained using a 10-fold cross-validation technique, and the multilayer perceptron (MLP) algorithm achieves a mean absolute error (MAE) of 23.906 meV/atom. To validate its generalization performance, the trained model is further validated on 900 ternary configurations, resulting in an MAE of 32.754 meV/atom. Compared with solely using traditional first-principles calculations, our approach significantly reduces the computational time by at least 52%. Moreover, the ML model exhibits exceptional accuracy in predicting the lattice parameters of the μ phase. The MAE values for the a and c parameters are 0.024 and 0.214 Å, respectively, corresponding to low error rates of only 0.479 and 0.578%. Additionally, the ML model was utilized to accurately predict the formation energy of all of the possible ternary configurations. To enhance accessibility to the formation energy data of the μ phase, a user-friendly graphical user interface (GUI) was developed, ensuring convenient usability for researchers and practitioners.
Collapse
Affiliation(s)
- Yue Su
- State
Key Laboratory of Powder Metallurgy, Central
South University, Changsha 410083, China
| | - Jiong Wang
- State
Key Laboratory of Powder Metallurgy, Central
South University, Changsha 410083, China
| | - You Zou
- Information
and Network Center, Central South University, Changsha 410083, China
| |
Collapse
|
19
|
Cuomo A, Ibarraran S, Sreekumar S, Li H, Eun J, Menzel JP, Zhang P, Buono F, Song JJ, Crabtree RH, Batista VS, Newhouse TR. Feed-Forward Neural Network for Predicting Enantioselectivity of the Asymmetric Negishi Reaction. ACS CENTRAL SCIENCE 2023; 9:1768-1774. [PMID: 37780365 PMCID: PMC10540279 DOI: 10.1021/acscentsci.3c00512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/24/2023] [Indexed: 10/03/2023]
Abstract
Density functional theory (DFT) is a powerful tool to model transition state (TS) energies to predict selectivity in chemical synthesis. However, a successful multistep synthesis campaign must navigate energetically narrow differences in pathways that create some limits to rapid and unambiguous application of DFT to these problems. While powerful data science techniques may provide a complementary approach to overcome this problem, doing so with the relatively small data sets that are widespread in organic synthesis presents a significant challenge. Herein, we show that a small data set can be labeled with features from DFT TS calculations to train a feed-forward neural network for predicting enantioselectivity of a Negishi cross-coupling reaction with P-chiral hindered phosphines. This approach to modeling enantioselectivity is compared with conventional approaches, including exclusive use of DFT energies and data science approaches, using features from ligands or ground states with neural network architectures.
Collapse
Affiliation(s)
- Abbigayle
E. Cuomo
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Sebastian Ibarraran
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Sanil Sreekumar
- Chemical
Development, Boehringer Ingelheim Pharmaceuticals
Inc, 900 Ridgebury Road, Ridgefield, Connecticut 06877, United States
| | - Haote Li
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Jungmin Eun
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Jan Paul Menzel
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Pengpeng Zhang
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Frederic Buono
- Chemical
Development, Boehringer Ingelheim Pharmaceuticals
Inc, 900 Ridgebury Road, Ridgefield, Connecticut 06877, United States
| | - Jinhua J. Song
- Chemical
Development, Boehringer Ingelheim Pharmaceuticals
Inc, 900 Ridgebury Road, Ridgefield, Connecticut 06877, United States
| | - Robert H. Crabtree
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Victor S. Batista
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| | - Timothy R. Newhouse
- Department
of Chemistry, Yale University, New Haven, Connecticut 06511, United States
| |
Collapse
|
20
|
Gómez-Peralta JI, Bokhimi X, Quintana P. Convolutional Neural Networks to Assist the Assessment of Lattice Parameters from X-ray Powder Diffraction. J Phys Chem A 2023; 127:7655-7664. [PMID: 37647548 DOI: 10.1021/acs.jpca.3c03860] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/01/2023]
Abstract
This article presents the development of convolutional neural networks (CNNs) for the estimation of lattice parameters in organic compounds across various crystal systems. A comprehensive collection of 92,085 organic compounds was utilized to train the CNNs, encompassing crystals with unit cells containing up to 512 atoms and a maximum unit cell volume of 8000 Å3. Simulated diffraction patterns were generated for each compound, comprising four diffraction patterns with different crystal sizes. These diffraction patterns were generated within a 2θ window of 3-60°, employing a step size of 0.02051°. Two distinct CNN architectures were developed with differing input data. The first CNN, referred to as XRD-CNN, was trained solely on diffraction patterns. In the test set, XRD-CNN demonstrated a mean absolute percentage error (MAPE) of 11.04% for unit cell vectors, 7.40% for angles, and 26.83% for unit cell volume. The second CNN, XRDElem-CNN, incorporated a binary representation of atoms within the unit cell as an additional input. XRDElem-CNN achieved improved performance, yielding MAPE values of 4.73% for unit vectors, 6.49% for angles, and 6.05% for the unit cell volume. To validate the performance of XRDElem-CNN, real diffraction patterns obtained from a conventional laboratory diffractometer (Cu Kα wavelength) were employed. Various representations of atoms within the unit cell were proposed, which were computationally efficient for evaluation with the CNNs. The assessed lattice parameters by XRDElem-CNN were validated using the Lp-search method, showing agreement with the reported values.
Collapse
Affiliation(s)
- Juan Iván Gómez-Peralta
- Laboratorio Nacional de Nano y Biomateriales, CINVESTAV-IPN, Antigua Carretera a Progreso km 6, A. P. 37, 97310 Mérida, Yucatán, Mexico
| | - Xim Bokhimi
- Instituto de Física, Universidad Nacional Autónoma de México, A. P. 20-364, 01000 Ciudad de México, DF, Mexico
| | - Patricia Quintana
- Laboratorio Nacional de Nano y Biomateriales, CINVESTAV-IPN, Antigua Carretera a Progreso km 6, A. P. 37, 97310 Mérida, Yucatán, Mexico
| |
Collapse
|
21
|
Wang B, Zhang Z, Dong Y, Qiu Y, Ren J, Bi K, Ji X, Liu C, Zhou L, Dai Y. Machine-Learning-Enabled Ligand Screening for Cs/Sr Crystallizing Separation. Inorg Chem 2023; 62:13293-13303. [PMID: 37557894 DOI: 10.1021/acs.inorgchem.3c01564] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/11/2023]
Abstract
The reprocessing of spent nuclear fuel is critical for the sustainability of the nuclear energy industry. However, several key separation processes present challenges in this regard, calling for continuous research into next-generation separation materials. Herein, we propose a high-throughput screening framework to improve efficiency in identifying potential ligands that selectively coordinate metal cations of interest in liquid wastes that considers multiple key chemical characteristics, including aqueous solubility, pKa, and coordination bond length. Machine-learning models were designed for the fast and accurate prediction of these characteristics by using graph convolution and transfer-learning techniques. Suitable ligands for Cs/Sr crystallizing separation were identified through the "computational funnel", and several top-ranking, nontoxic, low-cost ligands were selected for experimental verification.
Collapse
Affiliation(s)
- Bingbing Wang
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Zhiyuan Zhang
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Yue Dong
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Yuqing Qiu
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Junyu Ren
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Kexin Bi
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Xu Ji
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Chong Liu
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Li Zhou
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| | - Yiyang Dai
- School of Chemical Engineering, Sichuan University, Chengdu 610065, China
| |
Collapse
|
22
|
Wang Y, Su T, Cui Y, Ma X, Zhou X, Wang Y, Hu S, Ren W. Cuprate superconducting materials above liquid nitrogen temperature from machine learning. RSC Adv 2023; 13:19836-19845. [PMID: 37404317 PMCID: PMC10315706 DOI: 10.1039/d3ra02848h] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2023] [Accepted: 06/08/2023] [Indexed: 07/06/2023] Open
Abstract
The superconductivity of cuprates remains a challenging topic in condensed matter physics, and the search for materials that superconduct electricity above liquid nitrogen temperature and even at room temperature is of great significance for future applications. Nowadays, with the advent of artificial intelligence, research approaches based on data science have achieved excellent results in material exploration. We investigated machine learning (ML) models by employing separately the element symbolic descriptor atomic feature set 1 (AFS-1) and a prior physics knowledge descriptor atomic feature set 2 (AFS-2). An analysis of the manifold in the hidden layer of the deep neural network (DNN) showed that cuprates still offer the greatest potential as superconducting candidates. By calculating the SHapley Additive exPlanations (SHAP) value, it is evident that the covalent bond length and hole doping concentration emerge as the crucial factors influencing the superconducting critical temperature (Tc). These findings align with our current understanding of the subject, emphasizing the significance of these specific physical quantities. In order to improve the robustness and practicability of our model, two types of descriptors were used to train the DNN. We also proposed the idea of cost-sensitive learning, predicted the sample in another dataset, and designed a virtual high-throughput search workflow.
Collapse
Affiliation(s)
- Yuxue Wang
- Department of Physics, Material Genome Institute, Institute for the Conservation of Cultural Heritage, Shanghai University Shanghai 200444 China
- Shanghai Key Laboratory of High Temperature Superconductors, International Center for Quantum and Molecular Structures, Shanghai University Shanghai 200444 China
- Zhejiang Lab Hangzhou 311100 China
| | - Tianhao Su
- Department of Physics, Material Genome Institute, Institute for the Conservation of Cultural Heritage, Shanghai University Shanghai 200444 China
- Shanghai Key Laboratory of High Temperature Superconductors, International Center for Quantum and Molecular Structures, Shanghai University Shanghai 200444 China
- Zhejiang Lab Hangzhou 311100 China
| | - Yaning Cui
- Department of Physics, Material Genome Institute, Institute for the Conservation of Cultural Heritage, Shanghai University Shanghai 200444 China
- Shanghai Key Laboratory of High Temperature Superconductors, International Center for Quantum and Molecular Structures, Shanghai University Shanghai 200444 China
- Zhejiang Lab Hangzhou 311100 China
| | - Xianzhe Ma
- Department of Physics, Material Genome Institute, Institute for the Conservation of Cultural Heritage, Shanghai University Shanghai 200444 China
- Shanghai Key Laboratory of High Temperature Superconductors, International Center for Quantum and Molecular Structures, Shanghai University Shanghai 200444 China
- Zhejiang Lab Hangzhou 311100 China
| | - Xue Zhou
- Center for Spintronics and Quantum Systems, State Key Laboratory for Mechanical Behavior of Materials, Xi'an Jiaotong University Xi'an Shaanxi 710049 China
| | - Yin Wang
- Department of Physics, Material Genome Institute, Institute for the Conservation of Cultural Heritage, Shanghai University Shanghai 200444 China
- Shanghai Key Laboratory of High Temperature Superconductors, International Center for Quantum and Molecular Structures, Shanghai University Shanghai 200444 China
- Zhejiang Lab Hangzhou 311100 China
| | - Shunbo Hu
- Department of Physics, Material Genome Institute, Institute for the Conservation of Cultural Heritage, Shanghai University Shanghai 200444 China
- Shanghai Key Laboratory of High Temperature Superconductors, International Center for Quantum and Molecular Structures, Shanghai University Shanghai 200444 China
- Zhejiang Lab Hangzhou 311100 China
| | - Wei Ren
- Department of Physics, Material Genome Institute, Institute for the Conservation of Cultural Heritage, Shanghai University Shanghai 200444 China
- Shanghai Key Laboratory of High Temperature Superconductors, International Center for Quantum and Molecular Structures, Shanghai University Shanghai 200444 China
- Zhejiang Lab Hangzhou 311100 China
| |
Collapse
|
23
|
Gupta V, Peltekian A, Liao WK, Choudhary A, Agrawal A. Improving deep learning model performance under parametric constraints for materials informatics applications. Sci Rep 2023; 13:9128. [PMID: 37277456 DOI: 10.1038/s41598-023-36336-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2023] [Accepted: 06/01/2023] [Indexed: 06/07/2023] Open
Abstract
Modern machine learning (ML) and deep learning (DL) techniques using high-dimensional data representations have helped accelerate the materials discovery process by efficiently detecting hidden patterns in existing datasets and linking input representations to output properties for a better understanding of the scientific phenomenon. While a deep neural network comprised of fully connected layers has been widely used for materials property prediction, simply creating a deeper model with a large number of layers often faces with vanishing gradient problem, causing a degradation in the performance, thereby limiting usage. In this paper, we study and propose architectural principles to address the question of improving the performance of model training and inference under fixed parametric constraints. Here, we present a general deep-learning framework based on branched residual learning (BRNet) with fully connected layers that can work with any numerical vector-based representation as input to build accurate models to predict materials properties. We perform model training for materials properties using numerical vectors representing different composition-based attributes of the respective materials and compare the performance of the proposed models against traditional ML and existing DL architectures. We find that the proposed models are significantly more accurate than the ML/DL models for all data sizes by using different composition-based attributes as input. Further, branched learning requires fewer parameters and results in faster model training due to better convergence during the training phase than existing neural networks, thereby efficiently building accurate models for predicting materials properties.
Collapse
Affiliation(s)
- Vishu Gupta
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA
| | - Alec Peltekian
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA
| | - Wei-Keng Liao
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA
| | - Alok Choudhary
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA
| | - Ankit Agrawal
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA.
| |
Collapse
|
24
|
Schmidt J, Hoffmann N, Wang HC, Borlido P, Carriço PJMA, Cerqueira TFT, Botti S, Marques MAL. Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2023; 35:e2210788. [PMID: 36949007 DOI: 10.1002/adma.202210788] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/20/2022] [Revised: 02/28/2023] [Indexed: 06/02/2023]
Abstract
Crystal-graph attention neural networks have emerged recently as remarkable tools for the prediction of thermodynamic stability. The efficacy of their learning capabilities and their reliability is however subject to the quantity and quality of the data they are fed. Previous networks exhibit strong biases due to the inhomogeneity of the training data. Here a high-quality dataset is engineered to provide a better balance across chemical and crystal-symmetry space. Crystal-graph neural networks trained with this dataset show unprecedented generalization accuracy. Such networks are applied to perform machine-learning-assisted high-throughput searches of stable materials, spanning 1 billion candidates. In this way, the number of vertices of the global T = 0 K phase diagram is increased by 30% and find more than ≈150 000 compounds with a distance to the convex hull of stability of less than 50 meV atom-1 . The discovered materials are then accessed for applications, identifying compounds with extreme values of a few properties, such as superconductivity, superhardness, and giant gap-deformation potentials.
Collapse
Affiliation(s)
- Jonathan Schmidt
- Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, D-06099, Halle, Germany
| | - Noah Hoffmann
- Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, D-06099, Halle, Germany
| | - Hai-Chen Wang
- Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, D-06099, Halle, Germany
| | - Pedro Borlido
- CFisUC, Department of Physics, University of Coimbra, Rua Larga, 3004-516, Coimbra, Portugal
| | - Pedro J M A Carriço
- CFisUC, Department of Physics, University of Coimbra, Rua Larga, 3004-516, Coimbra, Portugal
| | - Tiago F T Cerqueira
- CFisUC, Department of Physics, University of Coimbra, Rua Larga, 3004-516, Coimbra, Portugal
| | - Silvana Botti
- Institut für Festkörpertheorie und -optik, Friedrich-Schiller-Universität Jena, Max-Wien-Platz 1, 07743, Jena, Germany
| | - Miguel A L Marques
- Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, D-06099, Halle, Germany
| |
Collapse
|
25
|
Gupta V, Choudhary K, Mao Y, Wang K, Tavazza F, Campbell C, Liao WK, Choudhary A, Agrawal A. MPpredictor: An Artificial Intelligence-Driven Web Tool for Composition-Based Material Property Prediction. J Chem Inf Model 2023; 63:1865-1871. [PMID: 36972592 PMCID: PMC10091406 DOI: 10.1021/acs.jcim.3c00307] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/29/2023]
Abstract
The applications of artificial intelligence, machine learning, and deep learning techniques in the field of materials science are becoming increasingly common due to their promising abilities to extract and utilize data-driven information from available data and accelerate materials discovery and design for future applications. In an attempt to assist with this process, we deploy predictive models for multiple material properties, given the composition of the material. The deep learning models described here are built using a cross-property deep transfer learning technique, which leverages source models trained on large data sets to build target models on small data sets with different properties. We deploy these models in an online software tool that takes a number of material compositions as input, performs preprocessing to generate composition-based attributes for each material, and feeds them into the predictive models to obtain up to 41 different material property values. The material property predictor is available online at http://ai.eecs.northwestern.edu/MPpredictor.
Collapse
Affiliation(s)
- Vishu Gupta
- ECE Department, Northwestern University, Evanston, Illinois 60208, United States
| | - Kamal Choudhary
- Materials Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, Maryland 20899, United States
- Theiss Research, La Jolla, California 92037, United States
- DeepMaterials LLC, Silver Spring, Maryland 20906, United States
| | - Yuwei Mao
- ECE Department, Northwestern University, Evanston, Illinois 60208, United States
| | - Kewei Wang
- ECE Department, Northwestern University, Evanston, Illinois 60208, United States
| | - Francesca Tavazza
- Materials Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, Maryland 20899, United States
| | - Carelyn Campbell
- Materials Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, Maryland 20899, United States
| | - Wei-Keng Liao
- ECE Department, Northwestern University, Evanston, Illinois 60208, United States
| | - Alok Choudhary
- ECE Department, Northwestern University, Evanston, Illinois 60208, United States
| | - Ankit Agrawal
- ECE Department, Northwestern University, Evanston, Illinois 60208, United States
| |
Collapse
|
26
|
Zhu R, Tian SIP, Ren Z, Li J, Buonassisi T, Hippalgaonkar K. Predicting Synthesizability using Machine Learning on Databases of Existing Inorganic Materials. ACS OMEGA 2023; 8:8210-8218. [PMID: 36910925 PMCID: PMC9996807 DOI: 10.1021/acsomega.2c04856] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 12/07/2022] [Indexed: 06/02/2023]
Abstract
Defining the metric for synthesizability and predicting new compounds that can be experimentally realized in the realm of data-driven research is a pressing problem in contemporary materials science. The increasing computational power and advancements in machine learning (ML) algorithms provide a new avenue to solve the synthesizability challenge. In this work, using the Inorganic Crystal Structure Database (ICSD) and the Materials Project (MP) database, we represent crystal structures in Fourier-transformed crystal properties (FTCP) representation and use a deep learning model to predict synthesizability in the form of a synthesizability score (SC). Such an SC model, as a synthesizability filter for new materials, enables an efficient and accurate classification to identify promising material candidates. The SC prediction model achieved 82.6/80.6% (precision/recall) overall accuracy in predicting ternary crystal materials. We also trained the SC model by only considering compounds uploaded on the MP before 2015 as the training set and testing on multiple sets of materials uploaded after 2015. In the post-2019 test set, we obtain a high 88.60% true positive rate accuracy, coupled with 9.81% precision, indicating that newly added materials remain unexplored and have high synthesis potential. Further, we provide a list of 100 materials predicted to be synthesizable from this post-2019 dataset (highest SC) for future studies, and our SC model, as a validation filter, is beneficial for future material screening and discovery.
Collapse
Affiliation(s)
- Ruiming Zhu
- Institute
of Materials Research and Engineering, Agency
for Science, Technology and Research (A*STAR), Singapore 138634, Singapore
- Department
of Materials Science and Engineering, Nanyang
Technological University, Singapore 117575, Singapore
| | - Siyu Isaac Parker Tian
- Low
Energy Electronic Systems (LEES), Singapore-MIT
Alliance for Research and Technology (SMART), Singapore 138602, Singapore
| | - Zekun Ren
- Low
Energy Electronic Systems (LEES), Singapore-MIT
Alliance for Research and Technology (SMART), Singapore 138602, Singapore
- Xinterra
Pte Ltd., 77 Robinson
Road, Singapore 068896, Singapore
| | - Jiali Li
- Department
of Chemical and Biomolecular Engineering, National University of Singapore, Singapore 117585, Singapore
| | - Tonio Buonassisi
- Low
Energy Electronic Systems (LEES), Singapore-MIT
Alliance for Research and Technology (SMART), Singapore 138602, Singapore
- Department
of Mechanical Engineering, Massachusetts
Institute of Technology, Cambridge, Massachusetts 02139-4307, United States
| | - Kedar Hippalgaonkar
- Institute
of Materials Research and Engineering, Agency
for Science, Technology and Research (A*STAR), Singapore 138634, Singapore
- Department
of Materials Science and Engineering, Nanyang
Technological University, Singapore 117575, Singapore
| |
Collapse
|
27
|
Chew PY, Reinhardt A. Phase diagrams-Why they matter and how to predict them. J Chem Phys 2023; 158:030902. [PMID: 36681642 DOI: 10.1063/5.0131028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022] Open
Abstract
Understanding the thermodynamic stability and metastability of materials can help us to, for example, gauge whether crystalline polymorphs in pharmaceutical formulations are likely to be durable. It can also help us to design experimental routes to novel phases with potentially interesting properties. In this Perspective, we provide an overview of how thermodynamic phase behavior can be quantified both in computer simulations and machine-learning approaches to determine phase diagrams, as well as combinations of the two. We review the basic workflow of free-energy computations for condensed phases, including some practical implementation advice, ranging from the Frenkel-Ladd approach to thermodynamic integration and to direct-coexistence simulations. We illustrate the applications of such methods on a range of systems from materials chemistry to biological phase separation. Finally, we outline some challenges, questions, and practical applications of phase-diagram determination which we believe are likely to be possible to address in the near future using such state-of-the-art free-energy calculations, which may provide fundamental insight into separation processes using multicomponent solvents.
Collapse
Affiliation(s)
- Pin Yu Chew
- Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom
| | - Aleks Reinhardt
- Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom
| |
Collapse
|
28
|
Zhang L, Zhuang Z, Fang Q, Wang X. Study on the Automatic Identification of ABX3 Perovskite Crystal Structure Based on the Bond-Valence Vector Sum. MATERIALS (BASEL, SWITZERLAND) 2022; 16:ma16010334. [PMID: 36614673 PMCID: PMC9821887 DOI: 10.3390/ma16010334] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/12/2022] [Revised: 12/26/2022] [Accepted: 12/28/2022] [Indexed: 05/14/2023]
Abstract
Perovskite materials have a variety of crystal structures, and the properties of crystalline materials are greatly influenced by geometric information such as the space group, crystal system, and lattice constant. It used to be mostly obtained using calculations based on density functional theory (DFT) and experimental data from X-ray diffraction (XRD) curve fitting. These two techniques cannot be utilized to identify materials on a wide scale in businesses since they require expensive equipment and take a lot of time. Machine learning (ML), which is based on big data statistics and nonlinear modeling, has advanced significantly in recent years and is now capable of swiftly and reliably predicting the structures of materials with known chemical ratios based on a few key material-specific factors. A dataset encompassing 1647 perovskite compounds in seven crystal systems was obtained from the Materials Project database for this study, which used the ABX3 perovskite system as its research object. A descriptor called the bond-valence vector sum (BVVS) is presented to describe the intricate geometry of perovskites in addition to information on the usual chemical composition of the elements. Additionally, a model for the automatic identification of perovskite structures was built through a comparison of various ML techniques. It is possible to identify the space group and crystal system using just a small dataset of 10 feature descriptors. The highest accuracy is 0.955 and 0.974, and the highest correlation coefficient (R2) value of the lattice constant can reach 0.887, making this a quick and efficient method for determining the crystal structure.
Collapse
Affiliation(s)
- Laisheng Zhang
- Institute of Material Science and Information Technology, Anhui University, Hefei 230601, China
- Institute of Solid State Physics, Hefei Institute of Materials Science, Chinese Academy of Sciences, Hefei 230031, China
| | - Zhong Zhuang
- Institute of Solid State Physics, Hefei Institute of Materials Science, Chinese Academy of Sciences, Hefei 230031, China
- Correspondence: ; Tel.: +86-138-5513-7903
| | - Qianfeng Fang
- Institute of Solid State Physics, Hefei Institute of Materials Science, Chinese Academy of Sciences, Hefei 230031, China
| | - Xianping Wang
- Institute of Solid State Physics, Hefei Institute of Materials Science, Chinese Academy of Sciences, Hefei 230031, China
| |
Collapse
|
29
|
Kuntz D, Wilson AK. Machine learning, artificial intelligence, and chemistry: how smart algorithms are reshaping simulation and the laboratory. PURE APPL CHEM 2022. [DOI: 10.1515/pac-2022-0202] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Abstract
Machine learning and artificial intelligence are increasingly gaining in prominence through image analysis, language processing, and automation, to name a few applications. Machine learning is also making profound changes in chemistry. From revisiting decades-old analytical techniques for the purpose of creating better calibration curves, to assisting and accelerating traditional in silico simulations, to automating entire scientific workflows, to being used as an approach to deduce underlying physics of unexplained chemical phenomena, machine learning and artificial intelligence are reshaping chemistry, accelerating scientific discovery, and yielding new insights. This review provides an overview of machine learning and artificial intelligence from a chemist’s perspective and focuses on a number of examples of the use of these approaches in computational chemistry and in the laboratory.
Collapse
Affiliation(s)
- David Kuntz
- Department of Chemistry , University of North Texas , Denton , TX 76201 , USA
| | - Angela K. Wilson
- Department of Chemistry , Michigan State University , East Lansing , MI 48824 , USA
| |
Collapse
|
30
|
Gong S, Wang S, Xie T, Chae WH, Liu R, Shao-Horn Y, Grossman JC. Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning. JACS AU 2022; 2:1964-1977. [PMID: 36186569 PMCID: PMC9516701 DOI: 10.1021/jacsau.2c00235] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
The application of machine learning to predict materials properties measured by experiments are valuable yet difficult due to the limited amount of experimental data. In this work, we use a multifidelity random forest model to learn the experimental formation enthalpy of materials with prediction accuracy higher than the Perdew-Burke-Ernzerhof (PBE) functional with linear correction, PBEsol, and meta-generalized gradient approximation (meta-GGA) functionals (SCAN and r2SCAN), and it outperforms the hotly studied deep neural network-based representation learning and transfer learning. We then use the model to calibrate the DFT formation enthalpy in the Materials Project database and discover materials with underestimated stability. The multifidelity model is also used as a data-mining approach to find how DFT deviates from experiments by explaining the model output.
Collapse
Affiliation(s)
- Sheng Gong
- Department
of Materials Science and Engineering, Massachusetts
Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Shuo Wang
- Department
of Materials Science and Engineering, University
of Maryland, College
Park, Maryland 20742, United States
| | - Tian Xie
- Computer
Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Woo Hyun Chae
- Department
of Materials Science and Engineering, Massachusetts
Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Runze Liu
- Department
of Materials Science and Engineering, Massachusetts
Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Yang Shao-Horn
- Department
of Materials Science and Engineering, Massachusetts
Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Jeffrey C. Grossman
- Department
of Materials Science and Engineering, Massachusetts
Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
31
|
Melting temperature prediction using a graph neural network model: From ancient minerals to new materials. Proc Natl Acad Sci U S A 2022; 119:e2209630119. [PMID: 36044552 PMCID: PMC9457469 DOI: 10.1073/pnas.2209630119] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
Abstract
The melting point is a fundamental property that is time-consuming to measure or compute, thus hindering high-throughput analyses of melting relations and phase diagrams over large sets of candidate compounds. To address this, we build a machine learning model, trained on a database of ∼10,000 compounds, that can predict the melting temperature in a fraction of a second. The model, made publicly available online, features graph neural network and residual neural network architectures. We demonstrate the model's usefulness in diverse applications. For the purpose of materials design and discovery, we show that it can quickly discover novel multicomponent materials with high melting points. These predictions are confirmed by density functional theory calculations and experimentally validated. In an application to planetary science and geology, we employ the model to analyze the melting temperatures of ∼4,800 minerals to uncover correlations relevant to the study of mineral evolution.
Collapse
|
32
|
Korolev V, Nevolin I, Protsenko P. A universal similarity based approach for predictive uncertainty quantification in materials science. Sci Rep 2022; 12:14931. [PMID: 36056050 PMCID: PMC9440040 DOI: 10.1038/s41598-022-19205-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Accepted: 08/25/2022] [Indexed: 11/08/2022] Open
Abstract
Immense effort has been exerted in the materials informatics community towards enhancing the accuracy of machine learning (ML) models; however, the uncertainty quantification (UQ) of state-of-the-art algorithms also demands further development. Most prominent UQ methods are model-specific or are related to the ensembles of models; therefore, there is a need to develop a universal technique that can be readily applied to a single model from a diverse set of ML algorithms. In this study, we suggest a new UQ measure known as the Δ-metric to address this issue. The presented quantitative criterion was inspired by the k-nearest neighbor approach adopted for applicability domain estimation in chemoinformatics. It surpasses several UQ methods in accurately ranking the predictive errors and could be considered a low-cost option for a more advanced deep ensemble strategy. We also evaluated the performance of the presented UQ measure on various classes of materials, ML algorithms, and types of input features, thus demonstrating its universality.
Collapse
Affiliation(s)
- Vadim Korolev
- Department of Chemistry, Lomonosov Moscow State University, Moscow, 119991, Russia.
| | - Iurii Nevolin
- Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, Moscow, 119071, Russia
| | - Pavel Protsenko
- Department of Chemistry, Lomonosov Moscow State University, Moscow, 119991, Russia
| |
Collapse
|
33
|
Song JK, Zhang Y, Fei XY, Chen YR, Luo Y, Jiang JS, Ru Y, Xiang YW, Li B, Luo Y, Kuai L. Classification and biomarker gene selection of pyroptosis-related gene expression in psoriasis using a random forest algorithm. Front Genet 2022; 13:850108. [PMID: 36110207 PMCID: PMC9468882 DOI: 10.3389/fgene.2022.850108] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2022] [Accepted: 07/04/2022] [Indexed: 11/13/2022] Open
Abstract
Background: Psoriasis is a chronic and immune-mediated skin disorder that currently has no cure. Pyroptosis has been proved to be involved in the pathogenesis and progression of psoriasis. However, the role pyroptosis plays in psoriasis remains elusive. Methods: RNA-sequencing data of psoriasis patients were obtained from the Gene Expression Omnibus (GEO) database, and differentially expressed pyroptosis-related genes (PRGs) between psoriasis patients and normal individuals were obtained. A principal component analysis (PCA) was conducted to determine whether PRGs could be used to distinguish the samples. PRG and immune cell correlation was also investigated. Subsequently, a novel diagnostic model comprising PRGs for psoriasis was constructed using a random forest algorithm (ntree = 400). A receiver operating characteristic (ROC) analysis was used to evaluate the classification performance through both internal and external validation. Consensus clustering analysis was used to investigate whether there was a difference in biological functions within PRG-based subtypes. Finally, the expression of the kernel PRGs were validated in vivo by qRT-PCR. Results: We identified a total of 39 PRGs, which could distinguish psoriasis samples from normal samples. The process of T cell CD4 memory activated and mast cells resting were correlated with PRGs. Ten PRGs, IL-1β, AIM2, CASP5, DHX9, CASP4, CYCS, CASP1, GZMB, CHMP2B, and CASP8, were subsequently screened using a random forest diagnostic model. ROC analysis revealed that our model has good diagnostic performance in both internal validation (area under the curve [AUC] = 0.930 [95% CI 0.877–0.984]) and external validation (mean AUC = 0.852). PRG subtypes indicated differences in metabolic processes and the MAPK signaling pathway. Finally, the qRT-PCR results demonstrated the apparent dysregulation of PRGs in psoriasis, especially AIM2 and GZMB. Conclusion: Pyroptosis may play a crucial role in psoriasis and could provide new insights into the diagnosis and underlying mechanisms of psoriasis.
Collapse
Affiliation(s)
- Jian-Kun Song
- Shanghai Skin Disease Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Ying Zhang
- Department of Dermatology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- Institute of Dermatology, Shanghai Academy of Traditional Chinese Medicine, Shanghai, China
| | - Xiao-Ya Fei
- Shanghai Skin Disease Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Yi-Ran Chen
- Department of Dermatology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- Institute of Dermatology, Shanghai Academy of Traditional Chinese Medicine, Shanghai, China
| | - Ying Luo
- Department of Dermatology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- Institute of Dermatology, Shanghai Academy of Traditional Chinese Medicine, Shanghai, China
| | - Jing-Si Jiang
- Department of Dermatology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- Institute of Dermatology, Shanghai Academy of Traditional Chinese Medicine, Shanghai, China
| | - Yi Ru
- Department of Dermatology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- Institute of Dermatology, Shanghai Academy of Traditional Chinese Medicine, Shanghai, China
| | - Yan-Wei Xiang
- Department of Dermatology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- School of Rehabilitation Science, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Bin Li
- Shanghai Skin Disease Hospital, School of Medicine, Tongji University, Shanghai, China
- Institute of Dermatology, Shanghai Academy of Traditional Chinese Medicine, Shanghai, China
| | - Yue Luo
- Shanghai Skin Disease Hospital, School of Medicine, Tongji University, Shanghai, China
- *Correspondence: Yue Luo, ; Le Kuai,
| | - Le Kuai
- Department of Dermatology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- Institute of Dermatology, Shanghai Academy of Traditional Chinese Medicine, Shanghai, China
- *Correspondence: Yue Luo, ; Le Kuai,
| |
Collapse
|
34
|
Pressure Induced Disorder-Order Phase Transitions in the Al4Cr Phases. CRYSTALS 2022. [DOI: 10.3390/cryst12071008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Abstract
An ordered ω-Al4Cr phase synthesized recently by a high-pressure sintering (HPS) approach was calculated to be stable by density function theory (DFT), implying that high pressure can accelerate the disorder-order phase transitions. The structural building units of the ω-Al4Cr phase as well as the non-stoichiometric disordered ε-Al4Cr and μ-Al4Cr phases have been analyzed by the topological “nanocluster” method in order to explore the structural relations among these phases. Both the ε-and μ-Al4Cr phases contain the typical Macky or pseudo-Macky cluster, and their centered positions were all occupied by Cr atoms, which all occupy the high-symmetry Wyckoff positions. The mechanism of the pressure-induced disorder-order phase transitions from the ε-/μ-Al4Cr to the ω-Al4Cr phase has been analyzed. and the related peritectic and eutectoid reactions have been re-evaluated. All results suggest that the stable ω-Al4Cr phase are transformed from the μ-Al4Cr phase by the eutectoid reaction that is accelerated by high-pressure conditions, whereas the ε-Al4Cr phase should form by the peritectic reaction.
Collapse
|
35
|
Loh C, Christensen T, Dangovski R, Kim S, Soljačić M. Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science. Nat Commun 2022; 13:4223. [PMID: 35864122 PMCID: PMC9304370 DOI: 10.1038/s41467-022-31915-y] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2021] [Accepted: 07/07/2022] [Indexed: 11/18/2022] Open
Abstract
Deep learning techniques have been increasingly applied to the natural sciences, e.g., for property prediction and optimization or material discovery. A fundamental ingredient of such approaches is the vast quantity of labeled data needed to train the model. This poses severe challenges in data-scarce settings where obtaining labels requires substantial computational or labor resources. Noting that problems in natural sciences often benefit from easily obtainable auxiliary information sources, we introduce surrogate- and invariance-boosted contrastive learning (SIB-CL), a deep learning framework which incorporates three inexpensive and easily obtainable auxiliary information sources to overcome data scarcity. Specifically, these are: abundant unlabeled data, prior knowledge of symmetries or invariances, and surrogate data obtained at near-zero cost. We demonstrate SIB-CL's effectiveness and generality on various scientific problems, e.g., predicting the density-of-states of 2D photonic crystals and solving the 3D time-independent Schrödinger equation. SIB-CL consistently results in orders of magnitude reduction in the number of labels needed to achieve the same network accuracies.
Collapse
Affiliation(s)
- Charlotte Loh
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA.
| | - Thomas Christensen
- Department of Physics, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Rumen Dangovski
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Samuel Kim
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Marin Soljačić
- Department of Physics, Massachusetts Institute of Technology, Cambridge, MA, USA
| |
Collapse
|
36
|
Mai H, Le TC, Chen D, Winkler DA, Caruso RA. Machine Learning for Electrocatalyst and Photocatalyst Design and Discovery. Chem Rev 2022; 122:13478-13515. [PMID: 35862246 DOI: 10.1021/acs.chemrev.2c00061] [Citation(s) in RCA: 71] [Impact Index Per Article: 35.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
Electrocatalysts and photocatalysts are key to a sustainable future, generating clean fuels, reducing the impact of global warming, and providing solutions to environmental pollution. Improved processes for catalyst design and a better understanding of electro/photocatalytic processes are essential for improving catalyst effectiveness. Recent advances in data science and artificial intelligence have great potential to accelerate electrocatalysis and photocatalysis research, particularly the rapid exploration of large materials chemistry spaces through machine learning. Here a comprehensive introduction to, and critical review of, machine learning techniques used in electrocatalysis and photocatalysis research are provided. Sources of electro/photocatalyst data and current approaches to representing these materials by mathematical features are described, the most commonly used machine learning methods summarized, and the quality and utility of electro/photocatalyst models evaluated. Illustrations of how machine learning models are applied to novel electro/photocatalyst discovery and used to elucidate electrocatalytic or photocatalytic reaction mechanisms are provided. The review offers a guide for materials scientists on the selection of machine learning methods for electrocatalysis and photocatalysis research. The application of machine learning to catalysis science represents a paradigm shift in the way advanced, next-generation catalysts will be designed and synthesized.
Collapse
Affiliation(s)
- Haoxin Mai
- Applied Chemistry and Environmental Science, School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, Victoria 3001, Australia
| | - Tu C Le
- School of Engineering, STEM College, RMIT University, GPO Box 2476, Melbourne, Victoria 3001, Australia
| | - Dehong Chen
- Applied Chemistry and Environmental Science, School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, Victoria 3001, Australia
| | - David A Winkler
- Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, Victoria 3052, Australia.,Biochemistry and Chemistry, La Trobe University, Kingsbury Drive, Bundoora, Victoria 3042, Australia.,School of Pharmacy, University of Nottingham, Nottingham NG7 2RD, United Kingdom
| | - Rachel A Caruso
- Applied Chemistry and Environmental Science, School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, Victoria 3001, Australia
| |
Collapse
|
37
|
Jha D, Gupta V, Liao WK, Choudhary A, Agrawal A. Moving closer to experimental level materials property prediction using AI. Sci Rep 2022; 12:11953. [PMID: 35831344 PMCID: PMC9279333 DOI: 10.1038/s41598-022-15816-0] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2022] [Accepted: 06/29/2022] [Indexed: 11/25/2022] Open
Abstract
While experiments and DFT-computations have been the primary means for understanding the chemical and physical properties of crystalline materials, experiments are expensive and DFT-computations are time-consuming and have significant discrepancies against experiments. Currently, predictive modeling based on DFT-computations have provided a rapid screening method for materials candidates for further DFT-computations and experiments; however, such models inherit the large discrepancies from the DFT-based training data. Here, we demonstrate how AI can be leveraged together with DFT to compute materials properties more accurately than DFT itself by focusing on the critical materials science task of predicting “formation energy of a material given its structure and composition”. On an experimental hold-out test set containing 137 entries, AI can predict formation energy from materials structure and composition with a mean absolute error (MAE) of 0.064 eV/atom; comparing this against DFT-computations, we find that AI can significantly outperform DFT computations for the same task (discrepancies of \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$>0.076$$\end{document}>0.076 eV/atom) for the first time.
Collapse
Affiliation(s)
- Dipendra Jha
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, 60208, USA
| | - Vishu Gupta
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, 60208, USA
| | - Wei-Keng Liao
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, 60208, USA
| | - Alok Choudhary
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, 60208, USA
| | - Ankit Agrawal
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, 60208, USA.
| |
Collapse
|
38
|
Zhang Z, Cheng M, Xiao X, Bi K, Song T, Hu KQ, Dai Y, Zhou L, Liu C, Ji X, Shi WQ. Machine-Learning-Guided Identification of Coordination Polymer Ligands for Crystallizing Separation of Cs/Sr. ACS APPLIED MATERIALS & INTERFACES 2022; 14:33076-33084. [PMID: 35801670 DOI: 10.1021/acsami.2c05272] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Separation of Cs/Sr is one of many coordination-chemistry-centered processes in the grand scheme of spent nuclear fuel reprocessing, a critical link for a sustainable nuclear energy industry. To deploy a crystallizing Cs/Sr separation technology, we planned to systematically screen and identify candidate ligands that can efficiently and selectively bind to Sr2+ and form coordination polymers. Therefore, we mined the Cambridge Structural Database for characteristic structural information and developed a machine-learning-guided methodology for ligand evaluation. The optimized machine-learning model, correlating the molecular structures of the ligands with the predicted coordinative properties, generated a ranking list of potential compounds for Cs/Sr selective crystallization. The Sr2+ sequestration capability and selectivity over Cs+ of the promising ligands identified (squaric acid and chloranilic acid) were subsequently confirmed experimentally, with commendable performances, corroborating the artificial-intelligence-guided strategy.
Collapse
Affiliation(s)
- Zhiyuan Zhang
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Min Cheng
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Xinyi Xiao
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Kexin Bi
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Ting Song
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Kong-Qiu Hu
- Laboratory of Nuclear Energy Chemistry, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Yiyang Dai
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Li Zhou
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Chong Liu
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Xu Ji
- School of Chemical Engineering, Sichuan University, Chengdu 610065, People's Republic of China
| | - Wei-Qun Shi
- Laboratory of Nuclear Energy Chemistry, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| |
Collapse
|
39
|
Ihalage A, Hao Y. Formula Graph Self-Attention Network for Representation-Domain Independent Materials Discovery. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2022; 9:e2200164. [PMID: 35475548 PMCID: PMC9218748 DOI: 10.1002/advs.202200164] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/09/2022] [Revised: 03/05/2022] [Indexed: 06/14/2023]
Abstract
The success of machine learning (ML) in materials property prediction depends heavily on how the materials are represented for learning. Two dominant families of material descriptors exist, one that encodes crystal structure in the representation and the other that only uses stoichiometric information with the hope of discovering new materials. Graph neural networks (GNNs) in particular have excelled in predicting material properties within chemical accuracy. However, current GNNs are limited to only one of the above two avenues owing to the little overlap between respective material representations. Here, a new concept of formula graph which unifies stoichiometry-only and structure-based material descriptors is introduced. A self-attention integrated GNN that assimilates a formula graph is further developed and it is found that the proposed architecture produces material embeddings transferable between the two domains. The proposed model can outperform some previously reported structure-agnostic models and their structure-based counterparts while exhibiting better sample efficiency and faster convergence. Finally, the model is applied in a challenging exemplar to predict the complex dielectric function of materials and nominate new substances that potentially exhibit epsilon-near-zero phenomena.
Collapse
Affiliation(s)
- Achintha Ihalage
- School of Electronic Engineering and Computer ScienceQueen Mary University of LondonMile End RdLondonE1 4NSUnited Kingdom
| | - Yang Hao
- School of Electronic Engineering and Computer ScienceQueen Mary University of LondonMile End RdLondonE1 4NSUnited Kingdom
| |
Collapse
|
40
|
Allen AEA, Tkatchenko A. Machine learning of material properties: Predictive and interpretable multilinear models. SCIENCE ADVANCES 2022; 8:eabm7185. [PMID: 35522750 PMCID: PMC9075804 DOI: 10.1126/sciadv.abm7185] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/11/2021] [Accepted: 03/21/2022] [Indexed: 06/14/2023]
Abstract
Machine learning models can provide fast and accurate predictions of material properties but often lack transparency. Interpretability techniques can be used with black box solutions, or alternatively, models can be created that are directly interpretable. We revisit material datasets used in several works and demonstrate that simple linear combinations of nonlinear basis functions can be created, which have comparable accuracy to the kernel and neural network approaches originally used. Linear solutions can accurately predict the bandgap and formation energy of transparent conducting oxides, the spin states for transition metal complexes, and the formation energy for elpasolite structures. We demonstrate how linear solutions can provide interpretable predictive models and highlight the new insights that can be found when a model can be directly understood from its coefficients and functional form. Furthermore, we discuss how to recognize when intrinsically interpretable solutions may be the best route to interpretability.
Collapse
|
41
|
Sheshanarayana R, Govind Rajan A. Tailoring Nanoporous Graphene via Machine Learning: Predicting Probabilities and Formation Times of Arbitrary Nanopore Shapes. J Chem Phys 2022; 156:204703. [DOI: 10.1063/5.0089469] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Abstract
Nanopores in graphene, a 2D material, are currently being explored for various applications, such as gas separation, water desalination, and DNA sequencing. The shapes and sizes of nanopores play a major role in determining the performance of devices made out of graphene. However, given an arbitrary nanopore shape, anticipating its creation probability and formation time are challenging inverse problems, solving which could help develop theoretical models for nanoporous graphene and guide experiments in tailoring pore sizes/shapes. In this work, we develop a machine learning (ML) framework to predict these target variables, based on data generated using kinetic Monte Carlo simulations and chemical graph theory. Thereby, we enable the rapid quantification of the ease of formation of a given nanopore shape in graphene via silicon-catalyzed electron-beam etching and provide an experimental handle to realize it in practice. We use structural features such as the number of carbon atoms removed, the number of edge atoms, the diameter of the nanopore, and its shape factor, which can be readily extracted from the nanopore shape. We show that the trained models can accurately predict nanopore probabilities and formation times with R2 values on the test set of 0.97 and 0.95, respectively. Not only that, we obtain physical insight into the working of the model and discuss the role played by the various structural features in modulating nanopore formation. Overall, our work provides a solid foundation for experimental studies to manipulate nanopore sizes/shapes and for theoretical studies to consider realistic structures of nanopores in graphene.
Collapse
|
42
|
Joung JF, Han M, Jeong M, Park S. Beyond Woodward-Fieser Rules: Design Principles of Property-Oriented Chromophores Based on Explainable Deep Learning Optical Spectroscopy. J Chem Inf Model 2022; 62:2933-2942. [PMID: 35476584 DOI: 10.1021/acs.jcim.2c00173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
An adequate understanding of molecular structure-property relationships is important for developing new molecules with desired properties. Although deep learning optical spectroscopy (DLOS) has been successfully applied to predict the optical and photophysical properties of organic chromophores, how specific functional groups and solvents affect the optical properties is not clearly understood. Here, we employed an explainable DLOS method by applying the integrated gradients method to DLOS. The integrated gradients method allows us to obtain attributions, indicating how much the functional group contributes to the optical properties including the absorption wavelength and bandwidth, extinction coefficients, emission wavelength and bandwidth, photoluminescence quantum yield, and lifetime. The attributions of 54 functional groups and 9 solvent molecules to seven optical properties are quantified and can be used to estimate the optical properties of chromophores as in the Woodward-Fieser rule. Unlike the Woodward-Fieser rule for only the absorption wavelength, the attributions obtained in this work can be applied to estimate all seven optical properties, which makes a significant extension of the Woodward-Fieser rules. In addition, we demonstrated a strategy for utilizing the attributions in the design of molecules and in tuning the optical properties of the molecules. The design of molecular structures using attributions can revolutionize the development of optimal molecules.
Collapse
Affiliation(s)
- Joonyoung F Joung
- Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea
| | - Minhi Han
- Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea
| | - Minseok Jeong
- Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea
| | - Sungnam Park
- Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea
| |
Collapse
|
43
|
Maihom T, Sittiwong J, Probst M, Limtrakul J. Understanding the interactions between lithium polysulfides and anchoring materials in advanced lithium-sulfur batteries using density functional theory. Phys Chem Chem Phys 2022; 24:8604-8623. [PMID: 35363239 DOI: 10.1039/d1cp05715d] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
Lithium-sulfur batteries (LSBs) are promising energy storage devices because of their high theoretical capacity and energy density. However, the "shuttle" effect in lithium polysulfides (LiPSs) is an unresolved issue that can hinder their practical commercial application. Research on LSBs has focused on finding appropriate materials that suppress this effect by efficiently anchoring the LiPSs intermediates. Quantum chemical computations are a useful tool for understanding the mechanistic details of chemical interaction involving LiPSs, and they can also offer strategies for the rational design of LiPSs anchoring materials. In this perspective, we highlight computational and theoretical work performed on this topic. This includes elucidating and characterizing the adsorption mechanisms, and the dominant types of interactions, and summarizing the binding energies of LiPSs on anchoring materials. We also give examples and discuss the potential of descriptors and machine learning approaches to predict the adsorption strength and reactivity of materials. We believe that both approaches will become indispensable in modelling future LSBs.
Collapse
Affiliation(s)
- Thana Maihom
- Department of Chemistry, Faculty of Liberal Arts and Science, Kasetsart University, Kamphaeng Saen Campus, Nakhon Pathom 73140, Thailand. .,Department of Materials Science and Engineering, Vidyasirimedhi Institute of Science and Technology, Rayong 21210, Thailand
| | - Jarinya Sittiwong
- Department of Chemistry, Faculty of Liberal Arts and Science, Kasetsart University, Kamphaeng Saen Campus, Nakhon Pathom 73140, Thailand.
| | - Michael Probst
- Institute of Ion Physics and Applied Physics, University of Innsbruck, 6020 Innsbruck, Austria.,School of Molecular Science and Engineering, Vidyasirimedhi Institute of Science and Technology, Rayong 21210, Thailand
| | - Jumras Limtrakul
- Department of Materials Science and Engineering, Vidyasirimedhi Institute of Science and Technology, Rayong 21210, Thailand
| |
Collapse
|
44
|
Buchnev O, Grant-Jacob JA, Eason RW, Zheludev NI, Mills B, MacDonald KF. Deep-Learning-Assisted Focused Ion Beam Nanofabrication. NANO LETTERS 2022; 22:2734-2739. [PMID: 35324209 PMCID: PMC9097578 DOI: 10.1021/acs.nanolett.1c04604] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/30/2021] [Revised: 03/17/2022] [Indexed: 06/01/2023]
Abstract
Focused ion beam (FIB) milling is an important rapid prototyping tool for micro- and nanofabrication and device and materials characterization. It allows for the manufacturing of arbitrary structures in a wide variety of materials, but establishing the process parameters for a given task is a multidimensional optimization challenge, usually addressed through time-consuming, iterative trial-and-error. Here, we show that deep learning from prior experience of manufacturing can predict the postfabrication appearance of structures manufactured by focused ion beam (FIB) milling with >96% accuracy over a range of ion beam parameters, taking account of instrument- and target-specific artifacts. With predictions taking only a few milliseconds, the methodology may be deployed in near real time to expedite optimization and improve reproducibility in FIB processing.
Collapse
Affiliation(s)
- Oleksandr Buchnev
- Optoelectronics
Research Centre, University of Southampton, Highfield, Southampton SO17 1BJ, United Kingdom
| | - James A. Grant-Jacob
- Optoelectronics
Research Centre, University of Southampton, Highfield, Southampton SO17 1BJ, United Kingdom
| | - Robert W. Eason
- Optoelectronics
Research Centre, University of Southampton, Highfield, Southampton SO17 1BJ, United Kingdom
| | - Nikolay I. Zheludev
- Optoelectronics
Research Centre, University of Southampton, Highfield, Southampton SO17 1BJ, United Kingdom
- Centre
for Disruptive Photonic Technologies & The Photonics Institute,
SPMS, Nanyang Technological University, Singapore 637371, Singapore
| | - Ben Mills
- Optoelectronics
Research Centre, University of Southampton, Highfield, Southampton SO17 1BJ, United Kingdom
| | - Kevin F. MacDonald
- Optoelectronics
Research Centre, University of Southampton, Highfield, Southampton SO17 1BJ, United Kingdom
| |
Collapse
|
45
|
Sahinovic A, Geisler B. Quantifying transfer learning synergies in infinite-layer and perovskite nitrides, oxides, and fluorides. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2022; 34:214003. [PMID: 35234671 DOI: 10.1088/1361-648x/ac5995] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/31/2021] [Accepted: 03/01/2022] [Indexed: 06/14/2023]
Abstract
We combine density functional theory simulations and active learning (AL) of element-embedding neural networks (NNs) to explore the sample efficiency for the prediction of vacancy layer formation energies and lattice parameters inABXninfinite-layer (n= 2) versus perovskite (n= 3) nitrides, oxides, and fluorides in the spirit of transfer learning. Following a comprehensive data analysis from different thermodynamic, structural, and statistical perspectives, we show that NNs model these observables with high precision, using merely∼30%of the data for training and exclusively theA-,B-, andX-site element names as minimal input devoid of any physicala prioriinformation. Element embedding autonomously arranges the chemical elements with a characteristic recurrent topology, such that their relations are consistent with human knowledge. We compare two different embedding strategies and show that these techniques render additional input such as atomic properties negligible. Simultaneously, we demonstrate that AL is largely independent of the initial training set, and exemplify its superiority over randomly composed training sets. Despite their highly distinct chemistry, the present approach successfully identifies fundamental quantum-mechanical universalities between nitrides, oxides, and fluorides that enhance the combined prediction accuracy by up to 16% with respect to three specialized NNs at equivalent numerical effort. This quantification of synergistic effects provides an impression of the transfer learning improvements one may expect for similarly complex materials. Finally, by embedding the tensor product of theBandXsites and subsequent quantitative cluster analysis, we establish from an unbiased artificial-intelligence perspective that oxides and nitrides exhibit significant parallels, whereas fluorides constitute a rather distinct materials class.
Collapse
Affiliation(s)
- Armin Sahinovic
- Department of Physics, Universität Duisburg-Essen, Lotharstr. 1, 47057 Duisburg, Germany
| | - Benjamin Geisler
- Department of Physics, Universität Duisburg-Essen, Lotharstr. 1, 47057 Duisburg, Germany
| |
Collapse
|
46
|
Farizhandi AAK, Betancourt O, Mamivand M. Deep learning approach for chemistry and processing history prediction from materials microstructure. Sci Rep 2022; 12:4552. [PMID: 35296736 PMCID: PMC8927426 DOI: 10.1038/s41598-022-08484-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2021] [Accepted: 03/04/2022] [Indexed: 11/18/2022] Open
Abstract
Finding the chemical composition and processing history from a microstructure morphology for heterogeneous materials is desired in many applications. While the simulation methods based on physical concepts such as the phase-field method can predict the spatio-temporal evolution of the materials' microstructure, they are not efficient techniques for predicting processing and chemistry if a specific morphology is desired. In this study, we propose a framework based on a deep learning approach that enables us to predict the chemistry and processing history just by reading the morphological distribution of one element. As a case study, we used a dataset from spinodal decomposition simulation of Fe-Cr-Co alloy created by the phase-field method. The mixed dataset, which includes both images, i.e., the morphology of Fe distribution, and continuous data, i.e., the Fe minimum and maximum concentration in the microstructures, are used as input data, and the spinodal temperature and initial chemical composition are utilized as the output data to train the proposed deep neural network. The proposed convolutional layers were compared with pretrained EfficientNet convolutional layers as transfer learning in microstructure feature extraction. The results show that the trained shallow network is effective for chemistry prediction. However, accurate prediction of processing temperature requires more complex feature extraction from the morphology of the microstructure. We benchmarked the model predictive accuracy for real alloy systems with a Fe-Cr-Co transmission electron microscopy micrograph. The predicted chemistry and heat treatment temperature were in good agreement with the ground truth.
Collapse
Affiliation(s)
| | - Omar Betancourt
- Department of Mechanical Engineering, University of California-Berkeley, Berkeley, CA, 94720, USA
| | - Mahmood Mamivand
- Department of Mechanical and Biomedical Engineering, Boise State University, Boise, ID, 83706, USA.
| |
Collapse
|
47
|
Wang B, Fan Q, Yue Y. Study of crystal properties based on attention mechanism and crystal graph convolutional neural network. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2022; 34:195901. [PMID: 35189607 DOI: 10.1088/1361-648x/ac5705] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/01/2021] [Accepted: 02/21/2022] [Indexed: 06/14/2023]
Abstract
The prediction of crystal properties has always been limited by huge computational costs. In recent years, the rise of machine learning methods has gradually made it possible to study crystal properties on a large scale. We propose an attention mechanism-based crystal graph convolutional neural network, which builds a machine learning model by inputting crystallographic information files and target properties. In our research, the attention mechanism is introduced in the crystal graph convolutional neural network (CGCNN) to learn the local chemical environment, and node normalization is added to reduce the risk of overfitting. We collect structural information and calculation data of about 36 000 crystals and examine the prediction performance of the models for the formation energy, total energy, bandgap, and Fermi energy of crystals in our research. Compared with the CGCNN, it is found that the accuracy (ACCU) of the predicted properties can be further improved to varying degrees by the introduction of the attention mechanism. Moreover, the total magnetization and bandgap can be classified under the same neural network framework. The classification ACCU of wide bandgap semiconductor crystals with a bandgap threshold of 2.3 eV reaches 93.2%, and the classification ACCU of crystals with a total magnetization threshold of 0.5 μBreaches 88.8%. The work is helpful to realize large-scale prediction and classification of crystal properties, accelerating the discovery of new functional crystal materials.
Collapse
Affiliation(s)
- Buwei Wang
- College of Information Engineering, Yangzhou University, Yangzhou, People's Republic of China
| | - Qian Fan
- College of Information Engineering, Yangzhou University, Yangzhou, People's Republic of China
| | - Yunliang Yue
- College of Information Engineering, Yangzhou University, Yangzhou, People's Republic of China
| |
Collapse
|
48
|
Lu Q, Wu J, Liu S, Zhang S, Cai X, Li W, Jiang J, Jin X. Revealing geometrically necessary dislocation density from electron backscatter patterns via multi-modal deep learning. Ultramicroscopy 2022; 237:113519. [DOI: 10.1016/j.ultramic.2022.113519] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2021] [Revised: 03/08/2022] [Accepted: 03/27/2022] [Indexed: 11/28/2022]
|
49
|
A Survey of Datasets, Preprocessing, Modeling Mechanisms, and Simulation Tools Based on AI for Material Analysis and Discovery. MATERIALS 2022; 15:ma15041428. [PMID: 35207968 PMCID: PMC8875409 DOI: 10.3390/ma15041428] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/18/2021] [Revised: 01/17/2022] [Accepted: 01/26/2022] [Indexed: 02/01/2023]
Abstract
Research has become increasingly more interdisciplinary over the past few years. Artificial intelligence and its sub-fields have proven valuable for interdisciplinary research applications, especially physical sciences. Recently, machine learning-based mechanisms have been adapted for material science applications, meeting traditional experiments' challenges in a time and cost-efficient manner. The scientific community focuses on harnessing varying mechanisms to process big data sets extracted from material databases to derive hidden knowledge that can successfully be employed in technical frameworks of material screening, selection, and recommendation. However, a plethora of underlying aspects of the existing material discovery methods needs to be critically assessed to have a precise and collective analysis that can serve as a baseline for various forthcoming material discovery problems. This study presents a comprehensive survey of state-of-the-art benchmark data sets, detailed pre-processing and analysis, appropriate learning model mechanisms, and simulation techniques for material discovery. We believe that such an in-depth analysis of the mentioned aspects provides promising directions to the young interdisciplinary researchers from computing and material science fields. This study will help devise useful modeling in the materials discovery to positively contribute to the material industry, reducing the manual effort involved in the traditional material discovery. Moreover, we also present a detailed analysis of experimental and computation-based artificial intelligence mechanisms suggested by the existing literature.
Collapse
|
50
|
Hu J, Song Y. Piezoelectric modulus prediction using machine learning and graph neural networks. Chem Phys Lett 2022. [DOI: 10.1016/j.cplett.2022.139359] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/11/2022]
|