Bulletin of the American Physical Society
APS March Meeting 2018
Volume 63, Number 1
Monday–Friday, March 5–9, 2018; Los Angeles, California
Session R12: Computational Materials Design  Machine LearningFocus

Hide Abstracts 
Sponsoring Units: DMP DCOMP Chair: Alex Zunger, Univ of Colorado  Boulder Room: LACC 303B 
Thursday, March 8, 2018 8:00AM  8:12AM 
R12.00001: Extensive deep neural networks for 2d materials Iryna Luchak, Kyle Mills, Kevin Ryczko, Adam Domurad, Christopher Beeler, Isaac Tamblyn We present a procedure for training and evaluating a deep neural network which can efficiently infer extensive parameters of arbitrarily large systems, doing so with O(N) complexity. We use a form of domain decomposition for training and inference, where each subdomain (tile) is comprised of a nonoverlapping focus region surrounded by an overlapping context region. The relative sizes of focus and context are physically motivated and depend on the locality length scale of the problem. Extensive deep neural networks (EDNN) are a formulation of convolutional neural networks which provide a flexible and general approach, based on physical constraints, to describe multiscale interactions. They are well suited to massively parallel inference, as no interthread communication is necessary during evaluation. Example uses for graphene, hexagonal boron nitride (hBN), as well as their 2d alloys are demonstrated. 
Thursday, March 8, 2018 8:12AM  8:24AM 
R12.00002: What can one learn about material structure given a single firstprinciples calculation? Sinisa Coh, Nicholas Rajen We extract a variable X from electron orbitals Psi_nk and energies E_nk in the parent highsymmetry structure of a wide range of complex oxides (perovskites, rutiles, pyrochlores, cristobalites). Even though X was calculated in the parent structure we show that its value dictates material's (potentially lowersymmetry) ground state structure. We propose using Wannier functions to extract concealed variables such as X both for material structure prediction and for highthroughput approaches. 
Thursday, March 8, 2018 8:24AM  8:36AM 
R12.00003: Utilizing Convolutional Neural Networks to Predict Properties of Inorganic Compounds Cheol Woo Park, Christopher Wolverton Incorporating structural information in machine learning (ML) models of materials properties has been shown to improve the predictive accuracy of the resulting models. In this study, we demonstrate a novel use of convolution neural networks (CNN) to extract information about the crystal structure of inorganic compounds. The CNNextracted structural properties are then combined with compositiondependent elemental properties to form the material representation for our ML model. We illustrate this method using datasets consisting of highthroughput density functional theory (DFT) data of formation energies of compounds. We critically examine the accuracy of different representations of the compound crystal structure as input for the CNN. We train ML models on ~200,000 entries taken from the Open Quantum Materials Database and evaluate the predictive accuracy on a test set of 20,000 compounds. We compare the predictive accuracy of our CNN model for formation energies with other recentlyproposed structural representations, e.g., those based on Voronoi tessellation. 
Thursday, March 8, 2018 8:36AM  9:12AM 
R12.00004: Machine Learning and Materials Discovery Invited Speaker: Gus Hart The relative accuracy and speed of density functional calculations have transformed computational materials science and enabled the creation of large databases of computed materials properties. But true "materials by design" or insilico materials discovery has not yet been realized, though there are isolated success stories. It seems likely that into make computional discovery of new materials possible, or to discover materials engineering routes to improve alreadydeployed materials, a brute force approach will not be practicalsome other paradigm will be required. Machine learning, so successful in some other application areas, is an intriguing and promising idea, but there are hurdles to overcome. There are two important differences between the standard machine learning problems of image recognition, voice recognition, etc., and materials prediction. In the first instance, we cannot afford the typical accuracy tradeoffmaterials predictions are not useful without meeting a high accuracy target; the energy difference of competing phases is often very small, requiring high fidelity in the models. The second difference is the amount of training datawe don't have "big data''. How do we move forward? In this talk I will review the state of the art in this emerging discipline and show some results from BYU's Materials Simulation Group efforts in this area. 
Thursday, March 8, 2018 9:12AM  9:24AM 
R12.00005: Accelerated Discovery of Quaternary Heusler with HighThroughput Density Functional Theory and Machine Learning Kyoungdoc Kim, Logan Ward, Jiangang He, Amar Krishna, Ankit Agrawal, Peter Voorhees, Christopher Wolverton Discovering manycomponent crystalline materials is a complex task owing to the large composition space. Here, we employ machine learning to find 55 previously unknown, thermodynamically stable quaternary Heusler (QH) compounds in a search space of over 2M compounds after performing only 303 Density Functional Theory (DFT) calculations. Our ML model predicts the stability of a material based on attributes derived from the Voronoi tessellation of its crystal structure, and we trained the model using 450k entries from the OQMD. We find that including data from many types of crystal structures when training ML models leads to better accuracy than when using a carefully curated dataset containing only a single family of material (i.e., only Heuslers). This means that large datasets, such as OQMD, are particularly valuable for materials discovery. We also find that the models trained using our method perform 10x better at identifying new stable QHs than existing heuristics and about 30% better than other machine learning methods. Given the fact that our method does not require a speciallydeveloped training set and its excellent performance, we propose it can be used to discover materials with many other types of crystal structures. 
Thursday, March 8, 2018 9:24AM  9:36AM 
R12.00006: Statistical Learning of Kinetic Monte Carlo Models of Complex Chemistry from Molecular Dynamics Qian Yang, Enze Chen, Muralikrishna Raju, Evan Reed Complex chemical processes, such as the decomposition of energetic materials or the adsorption of water on titania nanoparticles, are typically studied using largescale molecular dynamics (MD) simulations. These computations may involve thousands of atoms forming hundreds of molecular species and undergoing thousands of reactions. It is natural to wonder whether this wealth of data can be utilized to build more efficient, interpretable, and predictive models. In this talk, we will use techniques from statistical learning to develop a framework for constructing kinetic Monte Carlo (KMC) models from MD data. We will show that our KMC models can not only extrapolate the behavior of the chemical system by as much as an order of magnitude in time, but can also be used to study the dynamics of entirely different chemical trajectories with a high degree of fidelity. Importantly, our KMC models require only minutes to simulate systems and timescales that typically require weeks using MD. The ability of our trained KMC models to quickly extrapolate to different chemistries suggests a path forward for accelerating the simulation of novel materials. 
Thursday, March 8, 2018 9:36AM  9:48AM 
R12.00007: In Situ Multiobjective GeneticAlgorithm Workflow for Training and Uncertainty Quantification of Reactive MolecularDynamics Force Fields Ankit Mishra, Sungwook Hong, Pankaj Rajak, Chunyang Sheng, Kenichi Nomura, Rajiv Kalia, Aiichiro Nakano, Priya Vashishta The conventional approach of training a ReaxFF reactive force field parameters by fitting to a quantummechanical database is tedious and time consuming, and requires a considerable degree of prior experience. For fast and automated development of ReaxFF force fields, we propose a dynamic approach of directly fitting ReaxFF based reactive molecular dynamics (RMD) trajectories against a quantum molecular dynamics (QMD) trajectory on the fly. Here, we present a scalable in situ MOGA (iMOGA) workflow that eliminates the file I/O bottleneck involving file base communication between RMD, QMD and genetic algorithm computations, using interprocess communications but with minimal modification of the original parallel RMD code. The iMOGA workflow has been used to tune ReaxFF parameters for the sulfidation of MoO_{3} by H_{2}S, while providing uncertainty quantification (UQ) of the force field. 
Thursday, March 8, 2018 9:48AM  10:00AM 
R12.00008: 3D Scattering Transform Representation of Materials: From Molecules to Crystals Andrew Nguyen, Chandramouli Nyshadham, Conrad Rosenbrock, Gus Hart Computational materials scientists have generated huge databases of quantum accurate calculations for materials and their properties. These large databases have been mined to find correlations between structure and macroscopic properties in order to find new interesting materials. Machine learning potentials are gradually replacing more expensive firstprinciples calculations as surrogate models to obtain information on stability and properties of a material based on the microscopic arrangement of its atoms. In order for these machine learning potentials to be effective, the representations must be invariant to permutation, isometric transformations, and stable to deformation. In this talk, we present a 3D scattering transform representation that satisfies these properties. We apply this representation to molecules and crystal systems to show the robustness of this representation. 
Thursday, March 8, 2018 10:00AM  10:12AM 
R12.00009: Determining Nanoscale Structures from Pair Distribution Function and Density Functional Theory via MultiObjective Optimization Spencer Hills, Fatih Sen, Alper Kinaci, Maria Chan The structures of nanoparticles are challenging to determine. Various techniques have been proposed, each with its own limitations. Computational predictions require approximations and extensive sampling to find lowenergy structures, and lowestenergy structures are not guaranteed. Experimental characterization, such as pair distribution function (PDF), provides information on the specific structure, but the inversion of such data is nontrivial. 
Thursday, March 8, 2018 10:12AM  10:24AM 
R12.00010: GAtor: A First Principles Genetic Algorithm for Molecular Crystal Structure Prediction Farren Curtis, Xiayue Li, Timothy Rose, Alvaro VazquezMayagoitia, Saswata Bhattacharya, Luca Ghiringhelli, Noa Marom We present the implementation of GAtor, a massively parallel, first principles genetic algorithm (GA) for molecular crystal structure prediction. GAtor is written in Python and performs local optimizations and energy evaluations using dispersioninclusive density functional theory (DFT). GAtor offers a variety of fitness evaluation, selection, crossover, and mutation schemes. Breeding operators designed specifically for molecular crystals provide a balance between exploration and exploitation. Evolutionary niching is implemented by using machine learning to perform clustering on the fly and then employing a clusterbased fitness function. The best structures generated by GAtor are rerelaxed and reranked using a hierarchy of increasingly accurate DFT functionals and dispersion methods. GAtor is applied to a chemically diverse set of four past blind test targets, characterized by different types of intermolecular interactions. The experimentally observed structures and other lowenergy structures are found for all four targets. In particular, for Target II, 5cyano3hydroxythiophene, the top ranked putative crystal structure is a Z’=2 structure with P1bar symmetry and a scaffold packing motif, which has not been reported previously. 
Thursday, March 8, 2018 10:24AM  10:36AM 
R12.00011: Bayesian optimization of layered transition metal dichalcogenide heterostructures Pankaj Rajak, Lindsay Bassman, Aiichiro Nakano, Rajiv Kalia, Priya Vashishta, Fei Sha, David Singh Vertical heterostructures made from stacked monolayers of transition metal dichalcogenides (TMDC) are promising candidates for the next generation optoelectronic and thermoelectric devices. Identification of optimal layered materials for specific applications requires estimation of several physical properties, including electronic band structure and thermal transport coefficients. However, exhaustive screening of the material structure space using ab initio calculations is currently outside the bounds of existing computational resources. Furthermore, the functional form of how each physical property relates to the structures is often unknown, making gradientbased optimization unsuitable. Here, we present a model based on the Bayesian optimization to expedite the discovery of optimal Nlayered heterostructures. As specific exmaples, we consider the electronic band gap and thermoelectric figure of merit. With high probability, the Bayesian optimization discovered the optimal heterostructure after evaluation of only ~15% of all possible 3 or 4layered structures. 
Thursday, March 8, 2018 10:36AM  10:48AM 
R12.00012: Genetic Algorithms and DFT in the Search for Novel Stable and Metastable Crystal Structures of the Uranium Oxides Ashley Shields, Andrew Miskowiec, Brian Anderson The existence of nonstoichiometric uranium oxides is well known. However, many of these possible structures are not wellcharacterized experimentally because traditional analysis tools fail to easily characterize the structure of systems with low or no translational symmetry. Even stoichiometric uranium oxides such as U_{3}O_{8}, U_{4}O_{9}, and UO_{3} exhibit complex crystal phases when varying temperature and pressure. Using a combination of genetic algorithms and DFT calculations, we have searched the uranium–oxygen system for novel stable and metastable UO_{x} states. Several structure prediction codes already exist that implement genetic algorithms for this purpose, such as the Genetic Algorithm for Structure Prediction and the Universal Structure Predictor: Evolutionary Xtallography (USPEX) codes. USPEX can do additional searches for metastable states from a wellconverged starting structure using an evolutionary metadynamics algorithm. By further calculating experimental observables such as the vibrational spectra of lowenergy predicted structures, direct comparisons to experimentally obtained data of unknown compounds can be made, and unknown experimental samples can potentially be assigned to a predicted crystal structure. 
Thursday, March 8, 2018 10:48AM  11:00AM 
R12.00013: Prediction of novel metallic carbon and silicon allotropes using an inverse material design method HaJun Sung, Sunghyun Kim, Woo Hyun Han, InHo Lee, Kee Joo Chang Carbon has a rich variety of structural allotropes due to its ability of forming sp, sp^{2}, and sp^{3} hybridized bonds. Graphene, a single layer of graphite, consists of allsp^{2} bonds and exhibits a semimetallic band structure with Dirac points. The cubic diamond phase of Si is semiconducting and this material is widely used as the key element in the semiconductor technology. Although many metastable forms of Si have been observed, no metallic phase at ambient conditions has been reported to date. In this work, we report novel metallic carbon and silicon allotropes using an inverse material design method based on evolutionary global optimization and firstprinciples DFT calculations. The new carbon allotrope, termed mC_{8}, consists of fivemembered rings with sp^{3} bonding interconnected by sp^{2}bonded graphitic carbon networks. Analyzing the electronic band structure, we identify that mC_{8} belongs to the class of topological nodal line semimetals. The new Si allotrope, termed P6/mSi_{6}, contains open channels embedded in a simple hexagonal lattice. We find that the P6/mSi_{6} clathrate is superconducting with the critical temperature of about 12 K at zero pressure. 
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. 
© 2021 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