Bulletin of the American Physical Society
APS March Meeting 2017
Volume 62, Number 4
Monday–Friday, March 13–17, 2017; New Orleans, Louisiana
Session B1: Computational Discovery and Design of Novel Materials IIFocus

Hide Abstracts 
Sponsoring Units: DMP DCOMP Chair: Noa Marom, Carnegie Mellon University Room: 260 
Monday, March 13, 2017 11:15AM  11:51AM 
B1.00001: Quantum Machine Learning Invited Speaker: Anatole von Lilienfeld Many of the most relevant properties of matter depend explicitly on atomistic detail, rendering a first principles approach mandatory. Due to the combinatorial scaling of possible compositions and structures this precludes systematic highthroughput screening in search of new compounds for all but the simplest system classes and properties. Therefore it is desirable to exploit implicit redundancies, present in repeatedly performed quantum calculations. I will discuss our latest machine learning models of quantum mechanical observables, trained and applied throughout chemical compound space. [Preview Abstract] 
Monday, March 13, 2017 11:51AM  12:03PM 
B1.00002: QuantumChemical Insights from Deep Tensor Neural Networks Kristof T. Sch\"utt, Farhad Arbabzadah, Stefan Chmiela, KlausRobert M\"uller, Alexandre Tkatchenko Discovery of novel materials can be guided by searching databases of known structures and properties. Indeed, electronic structure calculations and machine learning have recently been combined aiming towards the goal of accelerated discovery of chemicals with desired properties. However, the design of an appropriate descriptor is critical to the success of these approaches. Here we address this issue with deep neural tensor networks (DTNN): a deep learning approach that is able to learn efficient representations of molecules and materials [1]. The mathematical construction of the DTNN model provides statistically rigorous partitioning of extensive molecular properties into atomic contributions  a longstanding challenge for quantummechanical calculations of molecules. Beyond achieving accurate energy predictions (1 kcal mol$^{1}$) throughout compositional and configurational space, DTNN provide spatially and chemically resolved insights into quantummechanical properties of molecular systems beyond those trivially contained in the training data. Thus, we propose DTNN as a versatile framework for understanding complex quantummechanical systems based on highthroughput electronic structure calculations. [1] K. T. Sch\"utt et al., Nat. Comm. (2016). [Preview Abstract] 
Monday, March 13, 2017 12:03PM  12:15PM 
B1.00003: Multifidelity Learning Models for Accurate Bandgap Predictions of Solids Turab Lookman, Ghanshyam Pilania, James E. Gubernatis We present a multidelity cokriging statistical learning framework that combines variablefidelity quantum mechanical calculations of bandgaps to generate a machinelearned model that enables lowcost accurate predictions of the bandgaps at the highest fidelity level. In addition, the adopted Gaussian process regression formulation allows us to predict the underlying uncertainties as a measure of our confidence in the predictions. Using a set of 600 Elpasolite compounds as an example dataset and using semilocal and hybrid exchange correlation functionals within density functional theory as two levels of modelities, we demonstrate the excellent learning performance of the method against actual high fidelity quantum mechanical calculations of the bandgaps. The presented statistical learning method is not restricted to bandgaps or electronic structure methods and extends the utility of high throughput property predictions in a significant way. [Preview Abstract] 
Monday, March 13, 2017 12:15PM  12:27PM 
B1.00004: Finding descriptors for material properties from billions of candidates via compressed sensing: accurate prediction of crystal structures and band gaps from only chemical composition Runhai Ouyang, Emre Ahmetcik, Luca M. Ghiringhelli, Matthias Scheffler Identifying the key physical parameters (termed descriptor) determining the target material properties is a critical step toward material discovery and rational design. Thus far, systematic methods for the descriptor identification are not well established. In particular, it has been suggested that good descriptors should both yield an accurate prediction and be physically interpretable [L. M. Ghiringhelli,\emph{et al.}, PRL \textbf{114}, 105503 (2015)]. In this talk, we present a systematic scheme for descriptor identification based on sure independent screening [J. Fan and J. Lv, J. R. Statist. Soc. B {\bf 70}, 849 (2008)] and compressed sensing [E. Candès and M. B. Wakin, IEEE Signal Proc. Mag. {\bf 25}, 21 (2008)]. The scheme starts with automatic building of the ``feature spaces'', i.e. all offered candidate descriptors, and the feature space may contain billions of options. The employed combination of sure independent screening and compressed sensing provides an efficient scheme for identifying the best lowdimensional descriptor. The approach is demonstrated for the important problems of crystalstructure and bandgap prediction. [Preview Abstract] 
Monday, March 13, 2017 12:27PM  12:39PM 
B1.00005: A machine learning approach for the classification of metallic glasses Eric Gossett, Eric Perim, Cormac Toher, Dongwoo Lee, Haitao Zhang, Jingbei Liu, Shaofan Zhao, Jan Schroers, Joost Vlassak, Stefano Curtarolo Metallic glasses possess an extensive set of mechanical properties along with plasticlike processability [1]. As a result, they are a promising material in many industrial applications [2]. However, the successful synthesis of novel metallic glasses requires trial and error, costing both time and resources. Therefore, we propose a highthroughput approach that combines an extensive set of experimental measurements with advanced machine learning techniques. This allows us to classify metallic glasses and predict the full phase diagrams for a given alloy system. Thus this method provides a means to identify potential glassformers and opens up the possibility for accelerating and reducing the cost of the design of new metallic glasses. [1] J. Schroers, N. Paton, Amorphous metal alloys form like plastics. Adv. Mater. Processes 164(1), 6163 (2006) [2] W. L. Johnson, Bulk glassforming metallic alloys: science and technology. MRS Bull. 24, 42–56 (1999) [Preview Abstract] 
Monday, March 13, 2017 12:39PM  12:51PM 
B1.00006: Machine Learning of ABO$_3$ Crystalline Compounds J. E. Gubernatis, P. V. Balachandran, T. Lookman We apply two advanced machine learning methods to a database of experimentally known AB$O_3$ materials to predict the existence of possible new perovskite materials and possible new cubic perovskites. Constructing a list of 625 possible new materials from charge conserving combinations of A and B atoms in known stable ABO$_3$ materials, we predict about 440 new perovskites. These new perovskites are predicted most likely to occur when the A and B atoms are a lanthanide or actinide, when the A atom is a alkali, alkali earth, or late transition metal, and a when the B atom is a $p$block atom. These results are in basic agreement with the recent materials discovery by substitution analysis of Hautier et al. [Inorg. Chem. 50, 656 (2011)] who datamined the entire ICSD data base to develop the probability that in any crystal structure atom X could be substituted for by atom Y. The results of our analysis has several points of disagreement with a recent high throughput DFT study of ABO$_3$ crystalline compounds by Emery et al. [Chem. Mat. 28, 5621 (2016)] who predict few, if any, new perovskites whose A and B atoms are both a lanthanide. They also predict far more new cubic perovskites than we do: We predict few, if any, with a high degree of probability. [Preview Abstract] 
Monday, March 13, 2017 12:51PM  1:03PM 
B1.00007: Machine learning energies of 2M elpasolite (ABC$_2$D$_6$) crystals Felix A. Faber, Alexander Lindmaa, O. Anatole von Lilienfeld, Rickard Armiento Elpasolite is one of the most predominant quaternary crystal structures (AlNaK$_2$F$_6$ prototype) reported in the Inorganic Crystal Structure Database. We present a machine learning model to calculate density functional theory quality formation energies for all 2M possible ABC$_2$D$_6$ elpasolite crystals one can make up from all maingroup elements up to Bi. The model's accuracy can be improved systematically, reaching a meanabsolute out of sample error of 0.1 eV/atom after training on 10k crystals. Out of the 2M crystals, we have identified 128 new structures which we predict to be on the convex hullamong which NFAl$_2$Ca$_6$, a metallic elpasolite with unusual stoichiometry and negative atomic oxidation state of Al. [Preview Abstract] 
Monday, March 13, 2017 1:03PM  1:15PM 
B1.00008: Understanding magnetism in transitionmetal multilayer thinfilms on MgO(001) by using machinelearning technique K. Nakamura, K. Nozaki, K. Hukushima, H. Kino, T. Akiyama, T. Ito, T. Oguchi New computational approaches for exploring materials with many exciting properties continue to grow in modern material science. In the field of spinelectronics, however, the effective procedure is still lacking due to a difficulty in treating magnetism, while searching promising ferromagnetic transitionmetal (TM) multilayer thinfilms with large perpendicular magnetocrystalline anisotropy (MCA) is strongly desired, e.g., for successful magnetic tunnel junction devices. Here, in order to show the underlying trends and physics in the magnetism in multilayer thinfilm systems, we carried out first principles calculations by employing sixatomiclayer slabs of Fe and Au (Co and Au) on MgO(001). With an assist of the clusterexpansion method, the magnetic moments are found to follow the SlaterPauling rule, i.e., governed by composition of the constituent TMs. In contrast, the MCA energy dramatically depends on the atomiclayer alignments with very large variation up to 5 meV/atomarea from a negative value of 2 meV/atomarea. Compressing sensing for understanding such dispersive MCA will be further applied. [Preview Abstract] 
Monday, March 13, 2017 1:15PM  1:27PM 
B1.00009: Inferring lowdimensional microstructure representations using convolutional neural networks Nicholas Lubbers, Turab Lookman, Kipton Barros We apply recent advances in machine learning and computer vision to a central problem in materials informatics: The statistical representation of microstructural images. We use activations in a pretrained convolutional neural network to provide a highdimensional characterization of a set of synthetic microstructural images. Next, we use manifold learning to obtain a lowdimensional embedding of this statistical characterization. We show that the lowdimensional embedding extracts the parameters used to generate the images. According to a variety of metrics, the convolutional neural network method yields dramatically better embeddings than the analogous method derived from twopoint correlations alone. [Preview Abstract] 
Monday, March 13, 2017 1:27PM  1:39PM 
B1.00010: Structure prediction for metastable materials: Sn$_{\mathrm{\mathbf{2}}}$\textbf{N}$_{\mathrm{\mathbf{2}}}$ Stephan Lany Recent advances in theoretical structure prediction methods and highthroughput computational techniques are revolutionizing experimental discovery of the thermodynamically stable inorganic materials. Metastable materials represent a new frontier for these studies, since even simple binary nonground state compounds of common elements may be awaiting discovery. An interesting example of a metastable material is Sn$_{\mathrm{2}}$N$_{\mathrm{2}}$, a mixed valence Sn(II)/Sn(IV) tin nitride, which, due to its metastability relative to metallic Sn, N$_{\mathrm{2}}$, and Sn$_{\mathrm{3}}$N$_{\mathrm{4,}}$ remained elusive until recently [1]. This metastability presents a challenge for computational structure prediction, as common ground state search strategies are guided by energy minimization, which will eventually lead to a phaseseparated configuration (Sn$+$N$_{\mathrm{2}})$ instead of the desired Sn$_{\mathrm{2}}$N$_{\mathrm{2}}$ compound. Initial structure sampling has identified a number of candidate structures [1], but did not lead to an unequivocal assignment. We present the results of a new hybrid structure sampling approach predicting a bilayer structure with the possibility of polytypism. [1] C.M. Caskey \textit{et al.}, J. Chem. Phys. 144, 144201 (2016). [Preview Abstract] 
Monday, March 13, 2017 1:39PM  1:51PM 
B1.00011: Learning phase transitions by confusion Evert Van Nieuwenburg, YeHua Liu, Sebastian Huber Classifying phases of matter is a central problem in physics. For quantum mechanical systems, this task can be daunting owing to the exponentially large Hilbert space. Thanks to the available computing power and access to ever larger data sets, classification problems are now routinely solved using machine learning techniques. Here, we propose to use a neural network based approach to find transitions depending on the performance of the neural network after training it with deliberately incorrectly labelled data. We demonstrate the success of this method on the topological phase transition in the Kitaev chain, the thermal phase transition in the classical Ising model, and the manybodylocalization transition in a disordered quantum spin chain. Our method does not depend on order parameters, knowledge of the topological content of the phases, or any other specifics of the transition at hand. It therefore paves the way to a generic tool to identify unexplored transitions. [Preview Abstract] 
Monday, March 13, 2017 1:51PM  2:03PM 
B1.00012: Projected Regression Methods for Inverting Fredholm Integrals: Formalism and Application to Analytical Continuation LouisFrancois Arsenault, Richard Neuberg, Lauren A. Hannah, Andrew J. Millis We present a machine learningbased statistical regression approach to the inversion of Fredholm integrals of the first kind by studying an important example for the quantum materials community, the analytical continuation problem of quantum manybody physics. It involves reconstructing the frequency dependence of physical excitation spectra from data obtained at specific points in the complex frequency plane. The approach provides a natural regularization in cases where the inverse of the Fredholm kernel is illconditioned and yields robust error metrics. The stability of the forward problem permits the construction of a large database of inputoutput pairs. Machine learning methods applied to this database generate approximate solutions which are projected onto the subspace of functions satisfying relevant constraints. We show that for low input noise the method performs as well or better than Maximum Entropy (MaxEnt) under standard error metrics, and is substantially more robust to noise. We expect the methodology to be similarly effective for any problem involving a formally illconditioned inversion, provided that the forward problem can be efficiently solved. [Preview Abstract] 
Monday, March 13, 2017 2:03PM  2:15PM 
B1.00013: Ferret: an opensource code for simulating thermodynamical evolution and phase transformations in complex materials systems at mesoscale Serge Nakhmanson, John Mangeri, Krishna Pitike, Lukasz Kuna, Andrea Jokisaari, S. Pamir Alpay, Olle Heinonen Ferret is an opensource realspace finiteelementmethod (FEM) based code for simulating behavior of materials systems with coupled physical properties at mesoscale. It is built on MOOSE, Multiphysics Object Oriented Simulation Environment, and is being developed by the UConnANL collaboration. Here we provide an overview of computational approach utilized by the code, as well as its technical features and the associated software within our computational tool chain. We also highlight a variety of code application examples that are being pursued in collaboration with a number of different experimental groups. These applications include (a) evaluations of size and microstructuredependent elastic and optical properties of coreshell nanoparticles, including Zn/ZnO and ZnO/TiO$_2$ core/shell material combinations; (b) modeling of the influence of shape, size and elastic distortions of monolithic ZnO and Zn/ZnO core/shell nanowires on their optical properties; (c) studies of the properties and domainwall dynamics in perovskiteferroelectric films, nanowires and nanoridges, and (d) investigation of topological phases and size effects in ferroelectric nanoparticles embedded in a dielectic matrix. [Preview Abstract] 
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. 
© 2020 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