Search for: All records

Data driven generative deep learning models have recently emerged as one of the most promising approaches for new materials discovery. While generator models can generate millions of candidates, it is critical to train fast and accurate machine learning models to filter out stable, synthesizable materials with the desired properties. However, such efforts to build supervised regression or classification screening models have been severely hindered by the lack of unstable or unsynthesizable samples, which usually are not collected and deposited in materials databases such as ICSD and Materials Project (MP). At the same time, there is a significant amount of unlabelled data available in these databases. Here we propose a semi-supervised deep neural network (TSDNN) model for high-performance formation energy and synthesizability prediction, which is achieved via its unique teacher-student dual network architecture and its effective exploitation of the large amount of unlabeled data. For formation energy based stability screening, our semi-supervised classifier achieves an absolute 10.3% accuracy improvement compared to the baseline CGCNN regression model. For synthesizability prediction, our model significantly increases the baseline PU learning's true positive rate from 87.9% to 92.9% using 1/49 model parameters. To further prove the effectiveness of our models, we combined our TSDNN-energy and TSDNN-synthesizability models with our CubicGAN generator to discover novel stable cubic structures. Out of the 1000 recommended candidate samples by our models, 512 of them have negative formation energies as validated by our DFT formation energy calculations. Our experimental results show that our semi-supervised deep neural networks can significantly improve the screening accuracy in large-scale generative materials design. Our source code can be accessed at https://git/hub.com/usccolumbia/tsdnn. 

Abstract Pre-trained transformer language models (LMs) 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 the 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 EB 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 LMs can generate chemically valid material compositions with as high as 97.61% to be charge neutral and 91.22% to be electronegativity balanced, which has more than six times higher enrichment compared to the baseline pseudo-random sampling algorithm. Our LMs 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 density functional theory calculations. All our trained materials transformer models and code can be accessed freely at http://www.github.com/usccolumbia/MTransformer . 

Abstract Discovering new materials is a challenging task in materials science crucial to the progress of human society. Conventional approaches based on experiments and simulations are labor-intensive or costly with success heavily depending on experts’ heuristic knowledge. Here, we propose a deep learning based Physics Guided Crystal Generative Model (PGCGM) for efficient crystal material design with high structural diversity and symmetry. Our model increases the generation validity by more than 700% compared to FTCP, one of the latest structure generators and by more than 45% compared to our previous CubicGAN model. Density Functional Theory (DFT) calculations are used to validate the generated structures with 1869 materials out of 2000 are successfully optimized and deposited into the Carolina Materials Databasewww.carolinamatdb.org, of which 39.6% have negative formation energy and 5.3% have energy-above-hull less than 0.25 eV/atom, indicating their thermodynamic stability and potential synthesizability. 

Abstract Semiconductor device technology has greatly developed in complexity since discovering the bipolar transistor. In this work, we developed a computational pipeline to discover stable semiconductors by combining generative adversarial networks (GAN), classifiers, and high-throughput first-principles calculations. We used CubicGAN, a GAN-based algorithm for generating cubic materials and developed a classifier to screen the semiconductors and studied their stability using first principles. We found 12 stable AA$${}^{\prime}$$ ${}^{\prime }$MH₆semiconductors in the F-43m space group including BaNaRhH₆, BaSrZnH₆, BaCsAlH₆, SrTlIrH₆, KNaNiH₆, NaYRuH₆, CsKSiH₆, CaScMnH₆, YZnMnH₆, NaZrMnH₆, AgZrMnH₆, and ScZnMnH₆. Previous research reported that five AA$${}^{\prime}$$ ${}^{\prime }$IrH6 semiconductors with the same space group were synthesized. Our research shows that AA$${}^{\prime}$$ ${}^{\prime }$MnH₆and NaYRuH₆semiconductors have considerably different properties compared to the rest of the AA$${}^{\prime}$$ ${}^{\prime }$MH₆semiconductors. Based on the accurate hybrid functional calculations, AA$${}^{\prime}$$ ${}^{\prime }$MH₆semiconductors are found to be wide-bandgap semiconductors. Moreover, BaSrZnH₆and KNaNiH₆are direct-bandgap semiconductors, whereas others exhibit indirect bandgaps. 

Two-dimensional (2D) materials have emerged as promising functional materials with many applications such as semiconductors and photovoltaics because of their unique optoelectronic properties. Although several thousand 2D materials have been screened in existing materials databases, discovering new 2D materials remains challenging. Herein, we propose a deep learning generative model for composition generation combined with a random forest-based 2D materials classifier to discover new hypothetical 2D materials. Furthermore, a template-based element substitution structure prediction approach is developed to predict the crystal structures of a subset of the newly predicted hypothetical formulas, which allows us to confirm their structure stability using DFT calculations. So far, we have discovered 267 489 new potential 2D materials compositions, where 1485 probability scores are more then 0.95. Among them, we have predicted 101 crystal structures and confirmed 92 2D/layered materials by DFT formation energy calculation. Our results show that generative machine learning models provide an effective way to explore the vast chemical design space for new 2D materials discovery. 

Abstract The availability and easy access of large-scale experimental and computational materials data have enabled the emergence of accelerated development of algorithms and models for materials property prediction, structure prediction, and generative design of materials. However, the lack of user-friendly materials informatics web servers has severely constrained the wide adoption of such tools in the daily practice of materials screening, tinkering, and design space exploration by materials scientists. Herein we first survey current materials informatics web apps and then propose and develop MaterialsAtlas.org, a web-based materials informatics toolbox for materials discovery, which includes a variety of routinely needed tools for exploratory materials discovery, including material’s composition and structure validity check (e.g. charge neutrality, electronegativity balance, dynamic stability, Pauling rules), materials property prediction (e.g. band gap, elastic moduli, hardness, and thermal conductivity), search for hypothetical materials, and utility tools. These user-friendly tools can be freely accessed athttp://www.materialsatlas.org. We argue that such materials informatics apps should be widely developed by the community to speed up materials discovery processes.