Bulletin of the American Physical Society
APS March Meeting 2022
Volume 67, Number 3
Monday–Friday, March 14–18, 2022; Chicago
Session Y32: Material Science and Machine Learning IIFocus Recordings Available

Hide Abstracts 
Sponsoring Units: GDS Chair: William Ratcliff, GDS Room: McCormick Place W192B 
Friday, March 18, 2022 8:00AM  8:12AM 
Y32.00001: Datadriven estimation of transfer integrals in undoped cuprates Denys Y Kononenko, Ulrich K Rößler, Jeroen van den Brink, Oleg Janson For magnetic insulators such as undoped cuprates, bandstructure calculations 
Friday, March 18, 2022 8:12AM  8:24AM 
Y32.00002: HighThroughput Screening of Semiconductors for Artificial Photosynthesis with DataMining and First Principles Calculations Sean M Stafford, Jose L MendozaCortes, Alexander Aduenko, Jose L MendozaCortes We propose an algorithm for efficient design of semiconductor structures with a selected set of physical properties. We deploy our algorithm to produce semiconductor candidates for artificial photosynthesis, i.e. photocatalytic water splitting. Our candidate structures are composed of earthabundant elements, capable of trapping sunlight, suitable for H_{2} and/or O_{2} production, and stable to reduction and oxidation in aqueous media. First, we predict thousands of undiscovered semiconductors compositions using an ionic translation model trained on a large experimental database. Then, we screen the predicted semiconductors compositions for redox stability under HER or OER conditions. Finally, we generate thermodynamically stable crystal structures and calculate accurate band gap values for these compounds. Ultimately we produce dozens of promising semiconductor candidates with ideal properties for artificial photosynthesis. 
Friday, March 18, 2022 8:24AM  8:36AM 
Y32.00003: Accelerated materials discovery of complex multicomponent alloys and ceramics with deep reinforcement learning Artem Pimachev In recent years the study of multicomponent alloys and ceramics including disordered rock salt cathodes for Liion batteries, metal halide perovskite solar absorbers, alloys for thermoelectrics, ultrahightemperature ceramics for aerospace applications has seen rapid growth due to their superior mechanical, thermal, and magnetic properties. The immense configurational space offers unique opportunities for discovery of new materials with unprecedented qualities. However, discovery of materials with targeted properties is challenging due to the huge number of distinct atomic configurations available . We employ multidimensional scaling (MDS) strategies to reduce the size of the configurational manifold. We use the distribution of local environments of elements in a given configuration as descriptors of the configuration. The atomic environments are described using features such as bond length and order parameter. The dimensionality reduction is beneficial for the reinforcement learning (RL) approach, which scales poorly for large numbers of space states. We compare the number of exploration steps needed to reach the target configuration before training (random walk) and after training the deep RL model. We demonstrate the approach to discover configurations for ternary compounds such as (Al_{x}Ga_{y}In_{z})_{2N}O_{3N} and highentropy ceramics. Deep RL is implemented on the reduced 3D and 2D manifold in order to achieve target physical property. 
Friday, March 18, 2022 8:36AM  8:48AM 
Y32.00004: A neural network potential for high throughput screening of the energetics and thermodynamical stabilities of nonstoichiometric Chromium Sulfides Akram Ibrahim, Daniel Wines, Can Ataca Machine learning potentials (MLPs) have recently become a powerful tool in computational materials science due to their ability to bridge the quantummechanical accuracy of ab initio methods to large systems with a linear scaling. We present a neural network potential (NNP) trained on data generated using density functional theory (DFT) to predict the energies and stabilities for a wide range of stoichiometries of CrS structures with Cr vacancies. A preliminary investigation of the stable phases is performed using the cluster expansion method (CE). Crystal structures are exhaustively enumerated for a more finegrained stoichiometry range. The NNP shows an excellent transferability to unseen stoichiometries, which is utilized in identifying the crystal structures of the stable and metastable phases for the full stoichiometric space. The phonon bandstructures are then predicted with an excellent agreement with DFT over the full stoichiometry space. Furthermore, the dynamical stabilities of some phases are evaluated using classical molecular dynamics (MD) driven by the NNP. The employed methodology acts as a systematic approach using (MLPs) to search the structure space and investigate the phonon and dynamical stabilities for a wide range of stoichiometries of a given material. 
Friday, March 18, 2022 8:48AM  9:00AM 
Y32.00005: Predicting oxygen vacancy formation energy in metal oxides Bianca Baldassarri, Christopher M Wolverton

Friday, March 18, 2022 9:00AM  9:12AM 
Y32.00006: Superconductor and Critical Temperature Predictions Using Machine Learning Benjamin W Roter, Sasa V Dordevic, Nemanja Ninkovic We used superconductors from the SuperCon database to perform 
Friday, March 18, 2022 9:12AM  9:24AM 
Y32.00007: Crystal Diffusion Variational Autoencoder for Periodic Material Generation Tian Xie, Xiang Fu, Octavian Ganea, Regina Barzilay, Tommi S Jaakkola Generating the periodic structure of stable materials is a longstanding challenge for the inverse design of solidstate materials. This task is difficult because stable materials only exist in a lowdimensional subspace of all possible periodic arrangements of atoms: 1) the coordinates must lie in the local energy minimum defined by quantum mechanics, and 2) global stability also requires the structure to follow the complex, yet specific bonding preferences between different atom types. Existing methods fail to incorporate these factors and often lack proper invariances. We propose a Crystal Diffusion Variational Autoencoder (CDVAE) that captures the physical inductive bias of material stability. By learning from the data distribution of stable materials, the decoder generates materials in a diffusion process that moves atomic coordinates towards a lower energy state and updates atom types to satisfy bonding preferences between neighbors. Our model also explicitly encodes interactions across periodic boundaries and respects permutation, translation, rotation, and periodic invariances. We significantly outperform past methods in three tasks: 1) reconstructing the input structure, 2) generating valid, diverse, and realistic materials, and 3) generating materials that optimize a specific property. Our approach opens exciting new opportunities for the propertyguided inverse design of solidstate materials for various important applications. 
Friday, March 18, 2022 9:24AM  9:36AM 
Y32.00008: Predicting elastic properties of crystal structures using rotationally equivariant graph neural networks Teerachote Pakornchote, Annop Ektarawong, Thiparat Chotibut The advent of machine learning (ML) enables datadriven approaches for computational materials science. With sufficient data from first principles, e.g. density functional theory, welldeveloped ML models can predict properties of unseen materials with high accuracy. Despite its empirical success, standard black box ML models lack explainability, and often are uninformed of material physics. In this work, we apply the recently developed ML model that is aware of symmetry groups possessed by crystal structures, to predict the elastic property of crystalline solids. Specifically, we train graph neural networks designed to learn rotational equivariance of threedimensional objects to predict the strain energy tensors computed from the elastic tensors of crystalline solids. Although the strain energy tensor has 6 x 6 components, the number of independent components crucially depend on the symmetries of the crystals. Our physicsinformed ML model can predict the strain energy tensor of unseen crystal structures rather accurately, and symmetryinduced tensor components are considerably differentiated. Our work is a stepping stone towards the datadriven discovery of materials with desirable properties. 
Friday, March 18, 2022 9:36AM  9:48AM 
Y32.00009: Machine learning to establish zero point energy as a screening parameter for identifying vibrationally stable perovskites Krishnaraj Kundavu, Amrita Bhattacharya, Suman Mondal, Souvik Hui, Rushikesh Rathod The present calculations show that scanning the potential energy surface of any compositional space (i.e. perovskites, in this context) using formation energy calculations i.e. with E_{hull} analysis is not sufficient to comment on vibrational stability of compounds. Machine learning is used to classify the vibrationally stable perovskites from the unstable ones, which shows the zero point energy (ZPE), i.e. thermal energy content of the system at 0 K, has a strong implication on thermal stability of compounds. Below a threshold value of ZPE (∼ 40 kJmol^{−1}), 90 % of compounds are found to be vibrationally stable. This is very advantageous, since ZPE can be absolutely quantitatively calculated for each structure individually. However, it suffers lengthy vibration calculation, which can not be performed for large scale high throughput screening. Thus, one of the compress sensing techniques (SISSO) is used to provide a highly accurate regression model for the ZPE using only elemental and simple compound descriptors. This model, while providing computationally inexpensive means to predict the vibrational stability of compounds, also establishes ZPE as a reference free screening parameter for predicting the vibrational stability of the compounds, which can be extended to different compound classes and even to elevated temperatures. 
Follow Us 
Engage
Become an APS Member 
My APS
Renew Membership 
Information for 
About APSThe American Physical Society (APS) is a nonprofit membership organization working to advance the knowledge of physics. 
© 2023 American Physical Society
 All rights reserved  Terms of Use
 Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 207403844
(301) 2093200
Editorial Office
1 Research Road, Ridge, NY 119612701
(631) 5914000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 200452001
(202) 6628700