1
|
Li Q, Dong R, Fu N, Omee SS, Wei L, Hu J. Global Mapping of Structures and Properties of Crystal Materials. J Chem Inf Model 2023. [PMID: 37310214 DOI: 10.1021/acs.jcim.3c00224] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Understanding materials' composition-structure-function relationships is of critical importance for the design and discovery of novel functional materials. While most such studies focus on individual materials, we conducted a global mapping study of all known materials deposited in the Materials Project database to investigate their distributions in the space of a set of seven compositional, structural, physical, and neural latent descriptors. These two-dimensional materials maps along with their density maps allow us to illustrate the distribution of the patterns and clusters of different shapes, which indicates the propensity of these materials and the tinkering history of existing materials. We then overlap the material properties such as composition prototypes and piezoelectric properties over the background material maps to study the relationships of how material compositions and structures affect their physical properties. We also use these maps to study the spatial distributions of properties of known inorganic materials, in particular those of local vicinities in structural space such as structural density and functional diversity. These maps provide a uniquely comprehensive overview of materials and space and thus reveal previously undescribed fundamental properties. Our methodology can be easily extended by other researchers to generate their own global material maps with different background maps and overlap properties for both distribution understanding and cluster-based new material discovery. The source code for feature generation and generated maps is available at https://github.com/usccolumbia/matglobalmapping.
Collapse
Affiliation(s)
- Qinyang Li
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Rongzhi Dong
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Nihang Fu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Sadman Sadeed Omee
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Lai Wei
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Jianjun Hu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| |
Collapse
|
2
|
Fu N, Wei L, Song Y, Li Q, Xin R, Omee SS, Dong R, Siriwardane EMD, Hu J. MATERIAL TRANSFORMERS: DEEP LEARNING LANGUAGE MODELS FOR GENERATIVE MATERIALS DESIGN. Mach Learn : Sci Technol 2022. [DOI: 10.1088/2632-2153/acadcd] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022] Open
Abstract
Abstract
Pre-trained transformer language models on large unlabeled corpus have produced state-of-the-art results in natural language processing, organic molecule design, and protein sequence generation. However, no such models have been applied to learn the composition patterns for generative design of material compositions. Here we train a series of seven modern transformer models (GPT, GPT-2, GPT-Neo, GPT-J, BLMM, BART, and RoBERTa) for materials design using the expanded formulas of the ICSD, OQMD, and Materials Projects databases. Six different datasets with/out non-charge-neutral or balanced electronegativity samples are used to benchmark the generative design performances and uncover the biases of modern transformer models for the generative design of materials compositions. Our experiments show that the materials transformers based on causal language models can generate chemically valid materials compositions with as high as 97.54\% to be charge neutral and 91.40\% to be electronegativity balanced, which has more than six times higher enrichment compared to the baseline pseudo-random sampling algorithm. Our language models also demonstrate high generation novelty and their potential in new materials discovery is proved by their capability to recover the leave-out materials. We also find that the properties of the generated compositions can be tailored by training the models with selected training sets such as high-bandgap samples. Our experiments also show that different models each have their own preference in terms of the properties of the generated samples and their running time complexity varies a lot. We have applied our materials transformers to discover a set of new materials as validated using DFT calculations. All our trained materials transformer models and code can be accessed freely at \url{http://www.github.com/usccolumbia/MTransformer}.
Collapse
|
3
|
Dong R, Zhao Y, Song Y, Fu N, Omee SS, Dey S, Li Q, Wei L, Hu J. DeepXRD, a Deep Learning Model for Predicting XRD spectrum from Material Composition. ACS Appl Mater Interfaces 2022; 14:40102-40115. [PMID: 36018289 DOI: 10.1021/acsami.2c05812] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
One of the long-standing problems in materials science is how to predict a material's structure and then its properties given only its composition. Experimental characterization of crystal structures has been widely used for structure determination, which is, however, too expensive for high-throughput screening. At the same time, directly predicting crystal structures from compositions remains a challenging unsolved problem. Herein we propose a deep learning algorithm for predicting the XRD spectrum given only the composition of a material, which can then be used to infer key structural features for downstream structural analysis such as crystal system or space group classification or crystal lattice parameter determination or materials property prediction. Benchmark studies on two data sets show that our DeepXRD algorithm can achieve good performance for XRD prediction as evaluated over our test sets. It can thus be used in high-throughput screening in the huge materials composition space for materials discovery.
Collapse
Affiliation(s)
- Rongzhi Dong
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Yong Zhao
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Yuqi Song
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Nihang Fu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Sadman Sadeed Omee
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Sourin Dey
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Qinyang Li
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Lai Wei
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Jianjun Hu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| |
Collapse
|
4
|
Louis SY, Siriwardane EMD, Joshi RP, Omee SS, Kumar N, Hu J. Accurate Prediction of Voltage of Battery Electrode Materials Using Attention-Based Graph Neural Networks. ACS Appl Mater Interfaces 2022; 14:26587-26594. [PMID: 35666275 DOI: 10.1021/acsami.2c00029] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Performing first-principles calculations to discover electrodes' properties in the large chemical space is a challenging task. While machine learning (ML) has been applied to effectively accelerate those discoveries, most of the applied methods ignore the materials' spatial information and only use predefined features: based only on chemical compositions. We propose two attention-based graph convolutional neural network techniques to learn the average voltage of electrodes. Our proposed methods, which combine both atomic composition and atomic coordinates in 3D-space, improve the accuracy in voltage prediction significantly when compared to composition-based ML models. The first model directly learns the chemical reaction of electrodes and metal ions to predict their average voltage, whereas the second model combines electrodes' ML predicted formation energy (Eform) to compute their average voltage. Our Eform-based model demonstrates improved accuracy in transferability from our subset of learned Li ions to Na ions. Moreover, we predicted the theoretical voltage of 10 NaxMPO4F (M = Ti, Cr, Fe, Cu, Mn, Co, and Ni) fluorophosphate battery frameworks, which are unavailable in the Material Project database. It could be shown that we can expect average voltages higher than 3.1 V from those Na battery frameworks except from the NaTiPO4F and TiPO4F pair of electrodes, which offer an average voltage of 1.32 V.
Collapse
Affiliation(s)
- Steph-Yves Louis
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Edirisuriya M Dilanga Siriwardane
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
- Department of Physics, University of Colombo, PO Box 1490, Colombo 0300, Sri Lanka
| | - Rajendra P Joshi
- Pacific Northwest National Laboratory, Richland, Washington 99352, United States
- TQuT Inc., 10205 Edgerton Avenue NE, Rockford, Michigan 49341, United States
| | - Sadman Sadeed Omee
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Neeraj Kumar
- Pacific Northwest National Laboratory, Richland, Washington 99352, United States
| | - Jianjun Hu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| |
Collapse
|
5
|
Wei L, Fu N, Siriwardane EMD, Yang W, Omee SS, Dong R, Xin R, Hu J. TCSP: a Template-Based Crystal Structure Prediction Algorithm for Materials Discovery. Inorg Chem 2022; 61:8431-8439. [PMID: 35420427 DOI: 10.1021/acs.inorgchem.1c03879] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
Fast and accurate crystal structure prediction (CSP) algorithms and web servers are highly desirable for the exploration and discovery of new materials out of the infinite chemical design space. However, currently, the computationally expensive first-principles calculation-based CSP algorithms are applicable to relatively small systems and are out of reach of most materials researchers. Several teams have used an element substitution approach for generating or predicting new structures, but usually in an ad hoc way. Here we develop a template-based crystal structure prediction (TCSP) algorithm and its companion web server, which makes this tool accessible to all materials researchers. Our algorithm uses elemental/chemical similarity and oxidation states to guide the selection of template structures and then rank them based on the substitution compatibility and can return multiple predictions with ranking scores in a few minutes. A benchmark study on the 98290 formulas of the Materials Project database using leave-one-out evaluation shows that our algorithm can achieve high accuracy (for 13145 target structures, TCSP predicted their structures with root-mean-square deviation < 0.1) for a large portion of the formulas. We have also used TCSP to discover new materials of the Ga-B-N system, showing its potential for high-throughput materials discovery. Our user-friendly web app TCSP can be accessed freely at www.materialsatlas.org/crystalstructure on our MaterialsAtlas.org web app platform.
Collapse
Affiliation(s)
- Lai Wei
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Nihang Fu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Edirisuriya M D Siriwardane
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Wenhui Yang
- School of Mechanical Engineering, Guizhou University, Guiyang 550055, China
| | - Sadman Sadeed Omee
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Rongzhi Dong
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Rui Xin
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Jianjun Hu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| |
Collapse
|