Bulletin of the American Physical Society
APS March Meeting 2020
Volume 65, Number 1
Monday–Friday, March 2–6, 2020; Denver, Colorado
Session M39: Machine Learning for Quantum Matter IIFocus

Hide Abstracts 
Sponsoring Units: DCOMP GDS DMP Chair: Estelle Inack, Perimeter Inst for Theo Phys Room: 703 
Wednesday, March 4, 2020 11:15AM  11:51AM 
M39.00001: Materials discovery through artificial intelligence Invited Speaker: Muratahan Aykol New, suitable materials are almost always at the core of new technologies. This endeavor now is spurred by exciting developments at the intersection of artificial intelligence (AI) and materials science. In this talk, I will present new AI tools developed at TRI for endtoend material discovery systems. Using these tools, codified agents of research can incorporate machinelearning, physics, chemistry, logic or heuristics to make decisions to meet their goals, for example, on which structures to simulate using highfidelity quantum mechanics. New agent designs can also be simulated a priori, projecting their performance in realworld discovery campaigns. Examples of simulations and executions of stable material discovery campaigns will be shown. 
Wednesday, March 4, 2020 11:51AM  12:27PM 
M39.00002: Working without data: overcoming gaps in deep learning and physicsbased extrapolation Invited Speaker: Isaac Tamblyn Despite its many recent successes, several fundamental issues remain with the application of deep learning to experimental data and firstprinciples based simulation. 
Wednesday, March 4, 2020 12:27PM  12:39PM 
M39.00003: Machine learning models of properties of hybrid 2D materials as potential super lubricants Marco Fronzi, Mutaz Abu Ghazaleh, Olexandr Isayev, David Winkler, joe shapter, Michael J Ford The screening of novel materials is an important topic in the field of materials science. Although traditional computational modeling, especially firstprinciples approaches, is a very useful and accurate tool to predict the properties of novel materials, it still demands extensive and expensive stateoftheart computational resources. Additionally, they can be often extremely timeconsuming. We describe a time and resourceefficient machine learning approach to create a large dataset of structural properties of van der Waals layered structures. In particular, we focus on the interlayer energy and the elastic constant of layered materials composed of two different 2dimensional (2D) structures, that are important for novel solid lubricant and superlubricant materials. We show that machine learning models can recapitulate results of computationally expansive approaches (i.e. density functional theory) with high accuracy. 
Wednesday, March 4, 2020 12:39PM  12:51PM 
M39.00004: Charge Density Prediction through 3DCNN for Fast Convergence of SelfConsistent DFT calculation Iori Kurata, Chikashi Shinagawa, Ryohto Sawada The electronic charge density plays an important role in understanding the physical properties of quantum materials. Although the charge density can be obtained by solving the KohnSham equation of density functional theory (DFT), one needs to solve a selfconsistent equation which takes time until convergence. Recent studies have tried to directly predict the charge density using machinelearning methods, but the target materials are limited to slabs or organic molecules because they only considered local electronic features [1,2,3]. 
Wednesday, March 4, 2020 12:51PM  1:03PM 
M39.00005: Datadriven studies of the magnetic anisotropy of twodimensional magnetic materials Yiqi Xie, Trevor David Rhone, Georgios Tritsaris, Oscar Grånäs, Efthimios Kaxiras Twodimensional materials with intrinsic ferromagnetic order are at the forefront of condensed matter research. How many of these materials exist in nature? What is the relationship between thier crystal structure and magnetic properties? Remarkably, atomicallythin magnetic structures can exhibit novel spin properties which do not exist in the corresponding bulk materials. We use firstprinciples calculations, based on density functional theory, and machine learning to study the magnetocrystalline anisotropy of monolayer transition metal trichalcogenides of the form A_{2}B_{2}X_{6}. That is, we created permutations of the chemical composition of the ferromagnetic semiconductor Cr_{2}Ge_{2}Te_{6}. Specifically, we identify trends in their magnetocrystalline anisotropy data. We find that the X site dominates the machine learning prediction of the magnetocrystalline anisotropy of an A_{2}B_{2}X_{6} monolayer. Our datadriven study aims to uncover physical insights into the microscopic origins of magnetism in reduced dimensions and to demonstrate the success of a highthroughput computational approach for the targeted design of quantum materials with potential applications from sensing to data storage. 
Wednesday, March 4, 2020 1:03PM  1:15PM 
M39.00006: Robust cluster expansion of multicomponent systems using machine learning with structured sparsity Zhidong Leong, Teck Leong Tan Identifying a suitable set of descriptors for modeling physical systems often utilizes either deep physical insights or statistical methods. In machine learning, a class of methods known as structured sparsity regularization combines both physics and statisticsbased approaches. We present group lasso as an efficient method for obtaining robust cluster expansions (CE) of multicomponent systems, a popular computational technique for modeling the thermodynamic properties of such systems. Via convex optimization, group lasso selects the most predictive set of atomic clusters as descriptors in accordance with the physical insight that if a cluster is selected, so should its subclusters. These selection rules avoid spuriously large fitting parameters by redistributing them among lower order terms, resulting in more physical, accurate, and robust CEs. We showcase these features of group lasso using the CE of bcc ternary alloy MoVNb. These results are timely given the growing interests in applying CE to increasingly complex systems, which demand a more reliable machine learning method to handle the larger parameter space. 
Wednesday, March 4, 2020 1:15PM  1:27PM 
M39.00007: Generalizing an Energy Predictor based on Wavelet Scattering for 3D Atomic Systems Paul Sinz, Michael Swift, Xavier Brumwell, Kwang Jin Kim, Yue Qi, Matthew J Hirn The dream of machine learning in quantum matter is for a neural network to learn the underlying physics of an atomic system, allowing it to move beyond interpolation of the training set to the prediction of properties that were not present in the original training data. Achieving this ambitious goal will require a method to convert a 3D atomic system into neuralnetworkfriendly features that preserve rotational and translational symmetry, smoothness under small perturbations, and invariance under reordering. The atomic orbital wavelet scattering transform preserves these symmetries by construction, and has achieved great success as a featurization method for machine learning energy prediction. Both in small molecules and in the amorphous Li_{x}Si system, neural networks using wavelet scattering coefficients as features have demonstrated a comparable accuracy to Density Functional Theory at a small fraction of the computational cost. In this work, we test the generalizability of our Li_{x}Si energy predictor to properties that were not included in the training set, such as elastic constants and migration barriers. We also discuss the potential for future improvements in generalizability through automatic trainingset expansion based on active learning. 
Wednesday, March 4, 2020 1:27PM  1:39PM 
M39.00008: Using Machine Learning Models to Predict HigherLevel Quantities from Energy Models Olivier MalenfantThuot, Michel Cote Machine learning methods are now used more and more as a substitute for Density Functional Theory calculations due to their low computational costs. However, in some cases, relevant datasets are not available, and the effort that would be necessary to generate this data suppresses the advantages of using machine learning to speed up the calculations. Furthermore, the process of training a reliable model is not trivial and can also be expensive. For those reasons, we are developing a python package named ML_Calc_Driver^{1}, which goal is to allow to use portable trained models to make predictions easily. Energy datasets are numerous and, through the use of implemented finite difference workflows, can be used to predict higherlevel quantities such as forces, phonon energies, and infrared intensities. As of now, the package is interfaced to use SchNetPack^{2} trained models, and more model types can easily be added as our workflows are independent of the actual calculators. 
Wednesday, March 4, 2020 1:39PM  1:51PM 
M39.00009: AIguided engineering of nanoscale topological materials Srilok Srinivasan, Mathew J Cherukara, David Jason Eckstein, Anthony Avarca, Subramanian Sankaranarayanan, Pierre Darancet Nanoscale organic materials have long been known to host topologically protected excitations. Inspired by recent progress in classifying topological phases in armchair, coveedged and chevron graphene nanoribbons, we develop a highthroughput framework based on the computation of the Zak phase and the Z2 invariants using tightbinding and density functional theory to explore the topology of lowsymmetry 1D and 2D periodic organic compounds. As of today, we have identified 224,071 new topological nanoribbons using our framework. Training deep neural networks on the graphs of these Hamiltonians, we analyze the graphical features conducive to topological excitations in these systems. We show how this workflow can help the atomic assembly of topologically nontrivial artificial lattices. 
Wednesday, March 4, 2020 1:51PM  2:03PM 
M39.00010: Motifbased machine learning for crystalline materials Huta Banjade, Shanshan Zhang, Sandro Hauri, Slobodan Vucetic, Qimin Yan With the development of advanced algorithms and improvements in computational power, machine learning (ML) has been widely successful in predicting various physical and chemical properties of materials. The success of any ML model mainly depends on the good representation of the input data, and there have been surging interests in identifying effective representations for crystalline materials. In this talk, we propose a novel representation of crystalline solidstate materials (such as complex metal oxides) as graphs composed of structure motifs. This motifbased representation serves as input to a graph convolutional network for the learning and prediction of material properties, such as bandgaps and formation energies. Our test results indicate that, when combined with atomic information and related networks, the inclusion of motif information in the network architecture improves the prediction performance, especially for complex oxide materials. 

M39.00011: Machine learning powered kinetic energy functional finding in solid state physics Hongbin Ren, Xi Dai, Lei Wang Kinetic energy functional is crucial to speed up the density functional theory calculation. However, deriving it directly from first principle is challenging, and existing approximations all have significant flaw. In this work, we use machine learning method to build a kinetic energy functional for 1D extended system, our solution combines the dimensionality reduction method with the Gauss process regression, and use a simple scaling trick to generalize the functional to 1D lattice with arbitrary lattice constant. Besides reaching chemical accuracy in kinetic energy calculation, our solution also performs well in functional derivative prediction, and integrating it into the current orbital free density functional theory scheme provide us with expected ground state electron density. 
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