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 L18: Atomistic Simulations via Machine Learning PotentialsInvited Live
|
Hide Abstracts |
Sponsoring Units: DCOMP Chair: Annabella Selloni, Princeton University |
Wednesday, March 17, 2021 8:00AM - 8:36AM Live |
L18.00001: Machine learned force fields: status and challenges Invited Speaker: Gabor Csanyi I will make the somewhat bold claim that over the past 10 years, a new computational task has been defined and solved for extended material systems: this is the analytic fitting of the Born-Oppenheimer potential energy surface as a function of nuclear coordinates under the assumption of medium-range interactions, out to 5-10 Å. The resulting potentials are reactive, many-body, reach accuracies of a few meV/atom, with costs that are on the order of 1-10 ms/atom. Important challenges remain: treatment of long range interactions in a nontrivial way, e.g. environment dependent multipoles, charge transfer, magnetism. Time is ripe for a “shakedown” of the details among various approaches (neural networks, kernels, polynomials), and more standard protocols of putting together the training data. Tradeoffs between system- (or even project-) specific fits vs. more general potentials will be ongoing. I am particularly concerned with amount physics and chemistry that we impute into these approximations, and they can be used to help "extrapolate" correctly into regions of configuration space far from those in the data set. |
Wednesday, March 17, 2021 8:36AM - 9:12AM Live |
L18.00002: Expanding the time- and length-scale of ab initio molecular dynamics with deep neural network potentials Invited Speaker: Marcos Andrade Deep neural networks (DNNs) have successfully reproduced the ab initio potential energy surface of condensed phase systems at orders of magnitude lower computational cost. The computational efficiency of DNNs allows molecular simulations of large systems for tens of nanoseconds with the accuracy of ab initio electronic structure calculations. In this talk, after a brief discussion of the Deep Potential (DP) method, I will focus on recent applications of DP molecular dynamics (DPMD) to the study of chemical reactions, amorphous materials and vibrational spectroscopies of water. Such studies require long-time sampling and/or large system sizes, both still out-of-reach of ab initio molecular dynamics. I shall also discuss a generalized version of DP that allows us to describe the electric dipole and polarizability of insulating systems and thus simulate the vibrational spectroscopies of large systems fully from first principles. The methods presented here can be readily extended to a variety of condensed-phase systems combining computational efficiency with the accuracy of quantum mechanics. This work was done in collaboration with Linfeng Zhang, Hsin-Yu Ko, Grace Sommers, Roberto Car and Annabella Selloni. |
Wednesday, March 17, 2021 9:12AM - 9:48AM Live |
L18.00003: Machine learned exchange and correlation functionals in density functional theory: progress and applications Invited Speaker: Marivi Fernandez The fundamental theorems of density functional theory ensure that there exists an exact functional which provides the exact energy of a system from its exact density. This functional is minimized at a fixed electron number and a fixed external potential by the exact electron density, hence providing both the density and and energy. |
Wednesday, March 17, 2021 9:48AM - 10:24AM Live |
L18.00004: Towards Mainstream Machine Learning Force Fields Invited Speaker: Alexandre Tkatchenko Machine Learning Force Fields (MLFF) should be accurate, efficient, and applicable to molecules, materials, and interfaces thereof. Here I discuss our developments of symmetry-adapted gradient-domain machine learning (sGDML) framework for MLFFs generally applicable for modeling of molecules, materials, and their interfaces. I highlight the key importance of bridging fundamental physical priors and conservation laws with the flexibility of non-linear ML regressors to achieve the challenging goal of constructing chemically-accurate force fields for a broad set of systems. Applications of sGDML will be presented for small and large (bio/DNA) molecules, pristine and realistic solids, and interfaces between molecules and 2D materials. [Refs] Sci. Adv. 3, e1603015 (2017); Nat. Commun. 9, 3887 (2018); Comp. Phys. Comm. 240, 38 (2019); J. Chem. Phys. 150, 114102 (2019). |
Wednesday, March 17, 2021 10:24AM - 11:00AM Live |
L18.00005: Global Neural Network Potential for Material Simulation and Catalysis Invited Speaker: Zhi-Pan Liu While the underlying potential energy surface (PES) determines the structure and other properties of material, it has been frustrated to predict new materials from theory even with the advent of supercomputing facilities. The accuracy of PES and the efficiency of PES sampling are two major bottlenecks, not least because of the great complexity of material PES. This lecture introduces our recent progress in SSW-NN method and its application in catalysis. We designed a “Global-to-Global” approach for material discovery by combining the novel global optimization method with neural network (NN) techniques. We describe in detail the current implementation of the SSW-NN method with particular focuses on the size of the global data set and the simultaneous energy/force/stress NN training procedure. All these methods have been implemented in LASP software (www.lasphub.com). A number of important reactions and functional materials, in particular those related to catalysis e.g. ZnCrO oxides and Titania supported Au particles, are utilized as the examples to demonstrate the automated global data set generation, the improved NN training procedure and the application in reaction discovery and catalysis. As a general tool for reaction/material simulation, the SSW-NN method provides an efficient and predictive platform for large-scale computational material screening. |
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