More Like this

1. Physics guided deep learning for generative design of crystal materials with symmetry constraints

   https://doi.org/10.1038/s41524-023-00987-9  

   Zhao, Yong; Siriwardane, Edirisuriya M. Dilanga; Wu, Zhenyao; Fu, Nihang; Al-Fahdi, Mohammed; Hu, Ming; Hu, Jianjun (March 2023, npj Computational Materials)

   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. 

   more » « less
2. Topological representations of crystalline compounds for the machine-learning prediction of materials properties

   https://doi.org/10.1038/s41524-021-00493-w  

   Jiang, Yi; Chen, Dong; Chen, Xin; Li, Tangyi; Wei, Guo-Wei; Pan, Feng (December 2021, npj Computational Materials)

   null (Ed.)

   Abstract Accurate theoretical predictions of desired properties of materials play an important role in materials research and development. Machine learning (ML) can accelerate the materials design by building a model from input data. For complex datasets, such as those of crystalline compounds, a vital issue is how to construct low-dimensional representations for input crystal structures with chemical insights. In this work, we introduce an algebraic topology-based method, called atom-specific persistent homology (ASPH), as a unique representation of crystal structures. The ASPH can capture both pairwise and many-body interactions and reveal the topology-property relationship of a group of atoms at various scales. Combined with composition-based attributes, ASPH-based ML model provides a highly accurate prediction of the formation energy calculated by density functional theory (DFT). After training with more than 30,000 different structure types and compositions, our model achieves a mean absolute error of 61 meV/atom in cross-validation, which outperforms previous work such as Voronoi tessellations and Coulomb matrix method using the same ML algorithm and datasets. Our results indicate that the proposed topology-based method provides a powerful computational tool for predicting materials properties compared to previous works. 

   more » « less
3. Directly Predicting Limiting Potentials from Easily Obtainable Physical Properties of Graphene-Supported Single-Atom Electrocatalysts by Machine Learning

   https://doi.org/10.1039/C9TA13404B  

   Lin, Shiru; Xu, Haoxiang; Wang, Yekun; Zeng, Xiao Cheng; Chen, Zhongfang (January 2020, Journal of Materials Chemistry A)

   Oxygen reduction reaction (ORR), oxygen evolution reaction (OER), and hydrogen evolution reaction (HER) are three critical reactions for energy-related applications, such as water electrolyzers and metal-air batteries. Graphene-supported single-atom catalysts (SACs) have been widely explored; however, either experiments or density functional theory (DFT) computations cannot screen catalysts at high speed. Herein, based on DFT computations of 104 graphene-supported SACs (M@C3, M@C4, M@pyridine-N4, and M@pyrrole-N4), we built up machine learning (ML) models to describe the underlying pattern of easily obtainable physical properties and limiting potentials (errors = 0.013/0.005/0.020 V for ORR/OER/HER, respectively), and employed these models to predict the catalysis performance of 260 other graphene-supported SACs containing metal-NxCy active sites (M@NxCy). We recomputed the top catalysts recommended by ML towards ORR/OER/HER by DFT, which confirmed the reliability of our ML model, and identified two OER catalysts (Ir@pyridine-N3C1 and Ir@pyridine-N2C2) outperforming noble metal oxides, RuO2 and IrO2. The ML models quantitatively unveiled the significance of various descriptors and fast narrowed down the potential list of graphene-supported single-atom catalysts. This approach can be easily used to screen and design other SACs, and significantly accelerate the catalyst design for many other important reactions. 

   more » « less
4. Computational Discovery of New 2D Materials Using Deep Learning Generative Models

   https://doi.org/10.1021/acsami.1c01044  

   Song, Yuqi; Siriwardane, Edirisuriya M.; Zhao, Yong; Hu, Jianjun (June 2021, ACS Applied Materials & Interfaces)

   null (Ed.)

   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. 

   more » « less
5. Materials discovery through machine learning formation energy

   https://doi.org/10.1088/2515-7655/abe425  

   Peterson, Gordon G. C.; Brgoch, Jakoah (March 2021, Journal of Physics: Energy)

   Abstract The budding field of materials informatics has coincided with a shift towards artificial intelligence to discover new solid-state compounds. The steady expansion of repositories for crystallographic and computational data has set the stage for developing data-driven models capable of predicting a bevy of physical properties. Machine learning methods, in particular, have already shown the ability to identify materials with near ideal properties for energy-related applications by screening crystal structure databases. However, examples of the data-guided discovery of entirely new, never-before-reported compounds remain limited. The critical step for determining if an unknown compound is synthetically accessible is obtaining the formation energy and constructing the associated convex hull. Fortunately, this information has become widely available through density functional theory (DFT) data repositories to the point that they can be used to develop machine learning models. In this Review, we discuss the specific design choices for developing a machine learning model capable of predicting formation energy, including the thermodynamic quantities governing material stability. We investigate several models presented in the literature that cover various possible architectures and feature sets and find that they have succeeded in uncovering new DFT-stable compounds and directing materials synthesis. To expand access to machine learning models for synthetic solid-state chemists, we additionally presentMatLearn. This web-based application is intended to guide the exploration of a composition diagram towards regions likely to contain thermodynamically accessible inorganic compounds. Finally, we discuss the future of machine-learned formation energy and highlight the opportunities for improved predictive power toward the synthetic realization of new energy-related materials. 

   more » « less