Bulletin of the American Physical Society
APS March Meeting 2021
Volume 66, Number 1
Monday–Friday, March 15–19, 2021; Virtual; Time Zone: Central Daylight Time, USA
Session L21: Machine Learning for Quantum Matter VFocus Live
|
Hide Abstracts |
Sponsoring Units: DCOMP GDS DMP Chair: Emine Kucukbenli, Harvard University |
Wednesday, March 17, 2021 8:00AM - 8:36AM Live |
L21.00001: Closed-loop discovery of optimal materials using artificial intelligence Invited Speaker: Muratahan Aykol Recent progress in applications of machine learning in physics, chemistry and materials science indicate that automation of scientific discovery itself in some parts of these fields is no longer an implausible goal. In this talk, I will present how closed-loop research systems that build on past data and knowledge, automated experiments/computations and automated decision-making can be designed, tested and deployed to solve certain discovery problems in materials science through iterative, sequential optimization. The emphasis will be placed on the need for integration of data-driven methods with proper physics and researcher heuristics in designing agents that guide the selection of experiments or computations. I will describe the details of a particular autonomous computational platform built to find new stable, synthesizable inorganic materials by choosing which crystal structures out of infinitely many options to calculate with automated density functional theory. This cloud-based platform is running 24/7 and has already found thousands of new inorganic ground state or metastable compounds. |
Wednesday, March 17, 2021 8:36AM - 8:48AM Live |
L21.00002: Interpretable and unsupervised phase classification based on averaged input features Julian Arnold, Frank Schäfer, Martin Zonda, Axel U. J. Lode Fully automated classification of phases from observations is of paramount importance to physics. Significant effort has recently been made to render this classification unsupervised and interpretable. Here, we present a physically motivated, computationally cheap, unsupervised, and interpretable method to infer phase boundaries from data [1]. The method relies on the difference between mean input features as an indicator for phase transitions and does not utilize predictive models. Crucially, this mean-based approach allows for direct physical insights into the revealed phase diagram without prior labelling or knowledge of its phases. As an example, we consider the physically rich ground-state phase diagram of the spinless Falicov-Kimball model. The large number of phases makes the analysis of this phase diagram by standard methods a hard task. In particular, supervised methods are bound to fails because phase labels are not known beforehand. We demonstrate that the mean-based method works well in this setting. |
Wednesday, March 17, 2021 8:48AM - 9:00AM Live |
L21.00003: Exploration of Topological Metamaterial Band Structures and Chern numbers using Deep Learning Vittorio Peano, Florian Sapper, Florian Marquardt
|
Wednesday, March 17, 2021 9:00AM - 9:12AM Live |
L21.00004: Unsupervised learning of topological order Gebremedhin Dagnew, Owen Myers, Chris M Herdman, Lauren Haywards Machine learning algorithms have proven useful in exploring phases and phase transitions in condensed matter Hamiltonians. Here, we show that a combination of unsupervised machine learning algorithms can be used to identify topological order in classical Z2 and Z3 lattice gauge theories. In particular, we apply dimensional reduction algorithms such as principal component analysis, clustering algorithms such as k-means, and the internal cluster performance metric known as silhouette analysis directly to raw spin configurations sampled from Monte Carlo simulations. Our method takes advantage of locality to define a patch of spins to be used as units of contrast instead of the individual spins to generate pairwise distance matrices based on the Hamming distance metric. We show that this modification enables us to identify non-local topological order in lattice gauge theories while maintaining performance for systems with local order parameters such as the Ising model. We also demonstrate non-trivial scaling for internal and external performance metrics for varying patch and system sizes. |
Wednesday, March 17, 2021 9:12AM - 9:48AM Live |
L21.00005: Machine learning augmented neutron and x-ray scattering for quantum materials Invited Speaker: Mingda Li Machine learning (ML) has demonstrated great power in materials science but |
Wednesday, March 17, 2021 9:48AM - 10:00AM Live |
L21.00006: Topological quantum phase transitions retrieved through unsupervised machine learning Yanming Che, Clemens Gneiting, Tao Liu, Franco Nori Detecting topological features in physics with unsupervised machine learning has been attracting increasing attention recently. It provides a viable learning framework for the study of topological phase transitions, without prior knowledge and labeled training examples of the system. |
Wednesday, March 17, 2021 10:00AM - 10:12AM Live |
L21.00007: Machine learning dynamics of phase separation in correlated electron magnets Puhan Zhang, Preetha Saha, Gia-Wei Chern The double-exchange mechanism plays an important role in our understanding of the colossal magnetoresistance phenomenon. Although extensive effort has been devoted to studying the equilibrium properties of the double-exchange models, dynamical phenomena in these systems remain much less explored. Real-space simulations of such inhomogeneous states with exchange forces computed from the electron Hamiltonian can be prohibitively expensive for large systems. Here we show that linear-scaling exchange field computation can be achieved using neural networks trained by datasets from exact calculation on small lattices. Our Landau-Lifshitz dynamics simulations based on machine-learning potentials nicely reproduce not only the non-equilibrium relaxation process, but also correlation functions that agree quantitatively with exact simulations. Our work opens new avenues for using deep-learning models to simulate and understand large-scale dynamical phenomena of correlated lattice systems. |
Wednesday, March 17, 2021 10:12AM - 10:24AM Live |
L21.00008: Machine learning spectral indicators of topology Nina Andrejevic, Jovana Andrejevic, Christopher Rycroft, Mingda Li Topological materials discovery has emerged as an important frontier in condensed matter physics due to the exceptional properties arising from nontrivial band topology. Recent theoretical methods based on local and global symmetry indicators have been used to identify several thousand candidate topological materials, yet experimental determination of materials’ topological character often poses significant technical challenges. X-ray absorption spectroscopy (XAS) is a widely-used characterization technique of materials’ local geometric and electronic structure, as it is sensitive to the symmetry and local chemical environment of constituent atoms; thus, it is a potentially useful encoding of topological character. Here, we study the effectiveness of XAS as a predictor of topology using machine learning methods to disentangle key structural information from the complex spectral features. We discuss the utility of experimental spectra to inform materials’ topology and compare the predictive power of individual absorbing elements. |
Wednesday, March 17, 2021 10:24AM - 10:36AM Live |
L21.00009: AI-guided engineering of nanoscale topological materials Srilok Srinivasan, Mathew Cherukara, David Eckstein, Anthony Avarca, Subramanian Sankaranarayanan, Pierre Darancet Nanoscale organic materials have long been known to host topologically protected excitations [1]. Inspired by recent progress in classifying topological phases in armchair, cove-edged and chevron graphene nanoribbons [2, 3,4], we develop a high-throughput framework based on the computation of the Zak phase [5] and the Z2 invariants using tight-binding and density functional theory to explore the topology of low-symmetry 1D and 2D periodic organic compounds. As of today, we have identified 224,071 new topological nanoribbons using our framework [6]. 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 non-trivial artificial lattices. |
Wednesday, March 17, 2021 10:36AM - 10:48AM Live |
L21.00010: Automatic Learning of Topological Phase Boundaries Alexander Kerr, Geo Jose, Colin J Riggert, Kieran Mullen Topological phase transitions, which do not adhere to Landau's phenomenological model (i.e. a spontaneous symmetry breaking process and vanishing local order parameters) have been actively researched in condensed matter physics. Machine learning of topological phase transitions has generally proved difficult due to the global nature of the topological indices. Only recently has the method of diffusion maps been shown to be effective at identifying changes in topological order. However, previous diffusion map results required adjustments of two hyperparameters: a data length-scale and the number of phase boundaries. In this article we introduce a heuristic that requires no such tuning. This heuristic allows computer programs to locate appropriate hyperparameters without user input. We demonstrate this method's efficacy by drawing remarkably accurate phase diagrams in three physical models: the Haldane model of graphene, a generalization of the Su-Schreiffer-Haeger (SSH) model, and a model for a quantum ring with tunnel junctions. These diagrams are drawn, without human intervention, from a supplied range of model parameters. |
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2024 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700