1
|
Chong S, Bigi F, Grasselli F, Loche P, Kellner M, Ceriotti M. Prediction rigidities for data-driven chemistry. Faraday Discuss 2024. [PMID: 39319702 PMCID: PMC11423580 DOI: 10.1039/d4fd00101j] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2024] [Accepted: 08/22/2024] [Indexed: 09/26/2024]
Abstract
The widespread application of machine learning (ML) to the chemical sciences is making it very important to understand how the ML models learn to correlate chemical structures with their properties, and what can be done to improve the training efficiency whilst guaranteeing interpretability and transferability. In this work, we demonstrate the wide utility of prediction rigidities, a family of metrics derived from the loss function, in understanding the robustness of ML model predictions. We show that the prediction rigidities allow the assessment of the model not only at the global level, but also on the local or the component-wise level at which the intermediate (e.g. atomic, body-ordered, or range-separated) predictions are made. We leverage these metrics to understand the learning behavior of different ML models, and to guide efficient dataset construction for model training. We finally implement the formalism for a ML model targeting a coarse-grained system to demonstrate the applicability of the prediction rigidities to an even broader class of atomistic modeling problems.
Collapse
Affiliation(s)
- Sanggyu Chong
- Laboratory of Computational Science and Modeling, Institute of Materials, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.
| | - Filippo Bigi
- Laboratory of Computational Science and Modeling, Institute of Materials, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.
| | - Federico Grasselli
- Laboratory of Computational Science and Modeling, Institute of Materials, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.
| | - Philip Loche
- Laboratory of Computational Science and Modeling, Institute of Materials, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.
| | - Matthias Kellner
- Laboratory of Computational Science and Modeling, Institute of Materials, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.
| | - Michele Ceriotti
- Laboratory of Computational Science and Modeling, Institute of Materials, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.
| |
Collapse
|
2
|
Morrow JD, Ugwumadu C, Drabold DA, Elliott SR, Goodwin AL, Deringer VL. Understanding Defects in Amorphous Silicon with Million-Atom Simulations and Machine Learning. Angew Chem Int Ed Engl 2024; 63:e202403842. [PMID: 38517212 DOI: 10.1002/anie.202403842] [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: 02/23/2024] [Revised: 03/14/2024] [Accepted: 03/18/2024] [Indexed: 03/23/2024]
Abstract
The structure of amorphous silicon (a-Si) is widely thought of as a fourfold-connected random network, and yet it is defective atoms, with fewer or more than four bonds, that make it particularly interesting. Despite many attempts to explain such "dangling-bond" and "floating-bond" defects, respectively, a unified understanding is still missing. Here, we use advanced computational chemistry methods to reveal the complex structural and energetic landscape of defects in a-Si. We study an ultra-large-scale, quantum-accurate structural model containing a million atoms, and thousands of individual defects, allowing reliable defect-related statistics to be obtained. We combine structural descriptors and machine-learned atomic energies to develop a classification of the different types of defects in a-Si. The results suggest a revision of the established floating-bond model by showing that fivefold-bonded atoms in a-Si exhibit a wide range of local environments-analogous to fivefold centers in coordination chemistry. Furthermore, it is shown that fivefold (but not threefold) coordination defects tend to cluster together. Our study provides new insights into one of the most widely studied amorphous solids, and has general implications for understanding defects in disordered materials beyond silicon alone.
Collapse
Affiliation(s)
- Joe D Morrow
- Inorganic Chemistry Laboratory, Department of Chemistry, University of Oxford, Oxford, OX1 3QR, United Kingdom
| | - Chinonso Ugwumadu
- Department of Physics and Astronomy, Nanoscale and Quantum Phenomena Institute (NQPI), Ohio University, Athens, Ohio, 45701, United States
| | - David A Drabold
- Department of Physics and Astronomy, Nanoscale and Quantum Phenomena Institute (NQPI), Ohio University, Athens, Ohio, 45701, United States
| | - Stephen R Elliott
- Physical and Theoretical Chemistry Laboratory, Department of Chemistry, University of, Oxford, OX1 3QZ, United Kingdom
| | - Andrew L Goodwin
- Inorganic Chemistry Laboratory, Department of Chemistry, University of Oxford, Oxford, OX1 3QR, United Kingdom
| | - Volker L Deringer
- Inorganic Chemistry Laboratory, Department of Chemistry, University of Oxford, Oxford, OX1 3QR, United Kingdom
| |
Collapse
|
3
|
Lu B, Xia Y, Ren Y, Xie M, Zhou L, Vinai G, Morton SA, Wee ATS, van der Wiel WG, Zhang W, Wong PKJ. When Machine Learning Meets 2D Materials: A Review. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2024; 11:e2305277. [PMID: 38279508 PMCID: PMC10987159 DOI: 10.1002/advs.202305277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 10/21/2023] [Indexed: 01/28/2024]
Abstract
The availability of an ever-expanding portfolio of 2D materials with rich internal degrees of freedom (spin, excitonic, valley, sublattice, and layer pseudospin) together with the unique ability to tailor heterostructures made layer by layer in a precisely chosen stacking sequence and relative crystallographic alignments, offers an unprecedented platform for realizing materials by design. However, the breadth of multi-dimensional parameter space and massive data sets involved is emblematic of complex, resource-intensive experimentation, which not only challenges the current state of the art but also renders exhaustive sampling untenable. To this end, machine learning, a very powerful data-driven approach and subset of artificial intelligence, is a potential game-changer, enabling a cheaper - yet more efficient - alternative to traditional computational strategies. It is also a new paradigm for autonomous experimentation for accelerated discovery and machine-assisted design of functional 2D materials and heterostructures. Here, the study reviews the recent progress and challenges of such endeavors, and highlight various emerging opportunities in this frontier research area.
Collapse
Affiliation(s)
- Bin Lu
- ARTIST Lab for Artificial Electronic Materials and Technologies, School of MicroelectronicsNorthwestern Polytechnical UniversityXi'an710072P. R. China
- Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang215400P. R. China
| | - Yuze Xia
- ARTIST Lab for Artificial Electronic Materials and Technologies, School of MicroelectronicsNorthwestern Polytechnical UniversityXi'an710072P. R. China
- Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang215400P. R. China
| | - Yuqian Ren
- ARTIST Lab for Artificial Electronic Materials and Technologies, School of MicroelectronicsNorthwestern Polytechnical UniversityXi'an710072P. R. China
- Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang215400P. R. China
| | - Miaomiao Xie
- ARTIST Lab for Artificial Electronic Materials and Technologies, School of MicroelectronicsNorthwestern Polytechnical UniversityXi'an710072P. R. China
- Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang215400P. R. China
| | - Liguo Zhou
- ARTIST Lab for Artificial Electronic Materials and Technologies, School of MicroelectronicsNorthwestern Polytechnical UniversityXi'an710072P. R. China
- Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang215400P. R. China
| | - Giovanni Vinai
- Instituto Officina dei Materiali (IOM)‐CNRLaboratorio TASCTriesteI‐34149Italy
| | - Simon A. Morton
- Advanced Light Source (ALS)Lawrence Berkeley National LaboratoryBerkeleyCA94720USA
| | - Andrew T. S. Wee
- Department of Physics and Centre for Advanced 2D Materials (CA2DM) and Graphene Research Centre (GRC)National University of SingaporeSingapore117542Singapore
| | - Wilfred G. van der Wiel
- NanoElectronics Group, MESA+ Institute for Nanotechnology and BRAINS Center for Brain‐Inspired Nano SystemsUniversity of TwenteEnschede7500AEThe Netherlands
- Institute of PhysicsUniversity of Münster48149MünsterGermany
| | - Wen Zhang
- ARTIST Lab for Artificial Electronic Materials and Technologies, School of MicroelectronicsNorthwestern Polytechnical UniversityXi'an710072P. R. China
- Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang215400P. R. China
- NanoElectronics Group, MESA+ Institute for Nanotechnology and BRAINS Center for Brain‐Inspired Nano SystemsUniversity of TwenteEnschede7500AEThe Netherlands
| | - Ping Kwan Johnny Wong
- ARTIST Lab for Artificial Electronic Materials and Technologies, School of MicroelectronicsNorthwestern Polytechnical UniversityXi'an710072P. R. China
- Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang215400P. R. China
- NPU Chongqing Technology Innovation CenterChongqing400000P. R. China
| |
Collapse
|
4
|
Zhang Z, Fang Z, Wu H, Zhu Y. Temperature-Dependent Paracrystalline Nucleation in Atomically Disordered Diamonds. NANO LETTERS 2024; 24:312-318. [PMID: 38134308 DOI: 10.1021/acs.nanolett.3c04037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/24/2023]
Abstract
Atomically disordered diamonds with medium-range order realized in recent experiments extend our knowledge of atomic disorder in materials. However, the current understanding of amorphous carbons cannot answer why paracrystalline diamond (p-D) can be formed inherently different from other tetrahedral amorphous carbons (ta-Cs), and the emergence of p-D seems to be easily hindered by inappropriate temperatures. Herein, we performed atomistic-based simulations to shed light on temperature-dependent paracrystalline nucleation in atomically disordered diamonds. Using metadynamics and two carefully designed collective variables, reversible phase transitions among different ta-Cs can be presented under different temperatures, evidenced by corresponding local minima on the free energy surface and reaction path along the free energy gradient. We found that p-D is preferred in a narrow range of temperatures, which is comparable to real experimental temperatures under the Arrhenius framework. The insights and related methods should open up a perspective for investigating other amorphous carbons.
Collapse
Affiliation(s)
- ZhongTing Zhang
- CAS Key Laboratory of Mechanical Behavior and Design of Materials, Department of Modern Mechanics, University of Science and Technology of China, Hefei 230027, China
| | - ZhouYu Fang
- CAS Key Laboratory of Mechanical Behavior and Design of Materials, Department of Modern Mechanics, University of Science and Technology of China, Hefei 230027, China
| | - HengAn Wu
- CAS Key Laboratory of Mechanical Behavior and Design of Materials, Department of Modern Mechanics, University of Science and Technology of China, Hefei 230027, China
- State Key Laboratory of Nonlinear Mechanics, Institute of Mechanics, Chinese Academy of Science, 15 Beisihuan West Road, Beijing 100190, China
| | - YinBo Zhu
- CAS Key Laboratory of Mechanical Behavior and Design of Materials, Department of Modern Mechanics, University of Science and Technology of China, Hefei 230027, China
| |
Collapse
|
5
|
Chong S, Grasselli F, Ben Mahmoud C, Morrow JD, Deringer VL, Ceriotti M. Robustness of Local Predictions in Atomistic Machine Learning Models. J Chem Theory Comput 2023; 19:8020-8031. [PMID: 37948446 PMCID: PMC10688186 DOI: 10.1021/acs.jctc.3c00704] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 10/12/2023] [Accepted: 10/12/2023] [Indexed: 11/12/2023]
Abstract
Machine learning (ML) models for molecules and materials commonly rely on a decomposition of the global target quantity into local, atom-centered contributions. This approach is convenient from a computational perspective, enabling large-scale ML-driven simulations with a linear-scaling cost and also allows for the identification and posthoc interpretation of contributions from individual chemical environments and motifs to complicated macroscopic properties. However, even though practical justifications exist for the local decomposition, only the global quantity is rigorously defined. Thus, when the atom-centered contributions are used, their sensitivity to the training strategy or the model architecture should be carefully considered. To this end, we introduce a quantitative metric, which we call the local prediction rigidity (LPR), that allows one to assess how robust the locally decomposed predictions of ML models are. We investigate the dependence of the LPR on the aspects of model training, particularly the composition of training data set, for a range of different problems from simple toy models to real chemical systems. We present strategies to systematically enhance the LPR, which can be used to improve the robustness, interpretability, and transferability of atomistic ML models.
Collapse
Affiliation(s)
- Sanggyu Chong
- Laboratory
of Computational Science and Modeling, Institute
of Materials, École Polytechnique Fédérale de Lausanne, Lausanne 1015, Switzerland
| | - Federico Grasselli
- Laboratory
of Computational Science and Modeling, Institute
of Materials, École Polytechnique Fédérale de Lausanne, Lausanne 1015, Switzerland
| | - Chiheb Ben Mahmoud
- Laboratory
of Computational Science and Modeling, Institute
of Materials, École Polytechnique Fédérale de Lausanne, Lausanne 1015, Switzerland
| | - Joe D. Morrow
- Department
of Chemistry, Inorganic Chemistry Laboratory, University of Oxford, Oxford OX1 3QR, U.K.
| | - Volker L. Deringer
- Department
of Chemistry, Inorganic Chemistry Laboratory, University of Oxford, Oxford OX1 3QR, U.K.
| | - Michele Ceriotti
- Laboratory
of Computational Science and Modeling, Institute
of Materials, École Polytechnique Fédérale de Lausanne, Lausanne 1015, Switzerland
| |
Collapse
|