On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events
Jonathan Vandermause,Steven B. Torrisi,Simon Batzner,Simon Batzner,Yu Xie,Lixin Sun,Alexie M. Kolpak,Boris Kozinsky,Boris Kozinsky +8 more
- Vol. 6, Iss: 1, pp 1-11
Reads0
Chats0
TLDR
In this paper, an adaptive Bayesian inference method for automating the training of interpretable, low-dimensional, and multi-element interatomic force fields using structures drawn on the fly from molecular dynamics simulations is presented.Abstract:
Machine learned force fields typically require manual construction of training sets consisting of thousands of first principles calculations, which can result in low training efficiency and unpredictable errors when applied to structures not represented in the training set of the model. This severely limits the practical application of these models in systems with dynamics governed by important rare events, such as chemical reactions and diffusion. We present an adaptive Bayesian inference method for automating the training of interpretable, low-dimensional, and multi-element interatomic force fields using structures drawn on the fly from molecular dynamics simulations. Within an active learning framework, the internal uncertainty of a Gaussian process regression model is used to decide whether to accept the model prediction or to perform a first principles calculation to augment the training set of the model. The method is applied to a range of single- and multi-element systems and shown to achieve a favorable balance of accuracy and computational efficiency, while requiring a minimal amount of ab initio training data. We provide a fully open-source implementation of our method, as well as a procedure to map trained models to computationally efficient tabulated force fields.read more
Citations
More filters
Journal ArticleDOI
Gaussian Process Regression for Materials and Molecules.
Volker L. Deringer,Albert P. Bartók,Noam Bernstein,David M. Wilkins,Michele Ceriotti,Gábor Csányi +5 more
TL;DR: In this paper, the authors provide an introduction to Gaussian process regression (GPR) machine learning methods in computational materials science and chemistry, focusing on the regression of atomistic properties: in particular, on the construction of interatomic potentials, or force fields, in the Gaussian approximation potential (GAP) framework.
Journal ArticleDOI
The MLIP package: moment tensor potentials with MPI and active learning
Ivan S. Novikov,Konstantin Gubaev,Konstantin Gubaev,Evgeny V. Podryabinkin,Alexander V. Shapeev +4 more
TL;DR: In this article, the MLIP package is used to construct moment tensor potentials using active learning, focusing on the efficient ways to sample configurations for the training set, how expanding the training sets changes the error of predictions, how to set up ab initio calculations in a cost-effective manner, etc.
Journal ArticleDOI
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
Boris Kozinsky,Simon Batzner +1 more
TL;DR: NequIP as mentioned in this paper is an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations, which achieves state-of-the-art accuracy on a challenging and diverse set of molecules and materials while exhibiting remarkable data efficiency.
Journal ArticleDOI
De novo exploration and self-guided learning of potential-energy surfaces
TL;DR: In this paper, the authors show that ML potentials can be built in a largely automated fashion, exploring and fitting potential energy surfaces from the beginning (de novo) within one and the same protocol.
Journal ArticleDOI
Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships
Steven B. Torrisi,Steven B. Torrisi,Matthew R. Carbone,Brian A. Rohr,Joseph Montoya,Yang Ha,Junko Yano,Santosh K. Suram,Linda Hung +8 more
TL;DR: This work shows that across thousands of transition metal oxide spectra, the relative importance of features describing the curvature of the spectrum can be localized to individual energy ranges, and it can separate the importance of constant, linear, quadratic, and cubic trends, as well as the white line energy.
References
More filters
Journal ArticleDOI
QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials
Paolo Giannozzi,Stefano Baroni,Stefano Baroni,Nicola Bonini,Matteo Calandra,Roberto Car,Carlo Cavazzoni,Davide Ceresoli,Guido L. Chiarotti,Matteo Cococcioni,Ismaila Dabo,Andrea Dal Corso,Andrea Dal Corso,Stefano de Gironcoli,Stefano de Gironcoli,Stefano Fabris,Stefano Fabris,Guido Fratesi,Ralph Gebauer,Ralph Gebauer,Uwe Gerstmann,Christos Gougoussis,Anton Kokalj,Michele Lazzeri,Layla Martin-Samos,Nicola Marzari,Francesco Mauri,Riccardo Mazzarello,Stefano Paolini,Alfredo Pasquarello,Lorenzo Paulatto,Lorenzo Paulatto,Carlo Sbraccia,Sandro Scandolo,Sandro Scandolo,Gabriele Sclauzero,Gabriele Sclauzero,Ari P. Seitsonen,Alexander Smogunov,Paolo Umari,Renata M. Wentzcovitch +40 more
TL;DR: QUANTUM ESPRESSO as discussed by the authors is an integrated suite of computer codes for electronic-structure calculations and materials modeling, based on density functional theory, plane waves, and pseudopotentials (norm-conserving, ultrasoft, and projector-augmented wave).
Journal ArticleDOI
Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
Paolo Giannozzi,Stefano Baroni,Nicola Bonini,Matteo Calandra,Roberto Car,Carlo Cavazzoni,Davide Ceresoli,Guido L. Chiarotti,Matteo Cococcioni,Ismaila Dabo,A. Dal Corso,Stefano Fabris,Guido Fratesi,S. de Gironcoli,Ralph Gebauer,U. Gerstmann,Christos Gougoussis,Anton Kokalj,Michele Lazzeri,Layla Martin-Samos,Nicola Marzari,Francesco Mauri,Riccardo Mazzarello,Stefano Paolini,Alfredo Pasquarello,Lorenzo Paulatto,Carlo Sbraccia,Sandro Scandolo,Gabriele Sclauzero,Ari P. Seitsonen,Alexander Smogunov,Paolo Umari,Renata M. Wentzcovitch +32 more
TL;DR: Quantum ESPRESSO as discussed by the authors is an integrated suite of computer codes for electronic-structure calculations and materials modeling, based on density functional theory, plane waves, and pseudopotentials (norm-conserving, ultrasoft, and projector-augmented wave).
Journal ArticleDOI
Double-slit photoelectron interference in strong-field ionization of the neon dimer.
Maksim Kunitski,Nicolas Eicke,Pia Huber,Jonas Köhler,S. Zeller,J. Voigtsberger,Nikolai Schlott,K. Henrichs,H. Sann,Florian Trinter,Lothar Ph. H. Schmidt,Anton Kalinin,Markus Schöffler,Till Jahnke,Manfred Lein,Reinhard Dörner +15 more
TL;DR: The authors show the double-slit interference effect in the strong-field ionization of neon dimers by employing COLTRIMS method to record the momentum distribution of the photoelectrons in the molecular frame.
Journal ArticleDOI
Computer simulation of local order in condensed phases of silicon
TL;DR: A model potential-energy function comprising both two- and three-atom contributions is proposed to describe interactions in solid and liquid forms of Si, suggesting a temperature-independent inherent structure underlies the liquid phase, just as for ``simple'' liquids with only pair interactions.
Journal ArticleDOI
The Atomic Simulation Environment - A Python library for working with atoms
Ask Hjorth Larsen,Ask Hjorth Larsen,Jens Jørgen Mortensen,Jakob Blomqvist,Ivano E. Castelli,Rune Christensen,Marcin Dulak,Jesper Friis,Michael N. Groves,Bjørk Hammer,Cory Hargus,Eric D. Hermes,Paul C. Jennings,Peter Bjerre Jensen,James R. Kermode,John R. Kitchin,Esben L. Kolsbjerg,Joseph Kubal,Kristen Kaasbjerg,Steen Lysgaard,Jon Bergmann Maronsson,Tristan Maxson,Thomas Olsen,Lars Pastewka,Andrew A. Peterson,Carsten Rostgaard,Jakob Schiøtz,Ole Schütt,Mikkel Strange,Kristian Sommer Thygesen,Tejs Vegge,Lasse B. Vilhelmsen,Michael Walter,Zhenhua Zeng,Karsten Wedel Jacobsen +34 more
TL;DR: The atomic simulation environment (ASE) provides modules for performing many standard simulation tasks such as structure optimization, molecular dynamics, handling of constraints and performing nudged elastic band calculations.
Related Papers (5)
Generalized neural-network representation of high-dimensional potential-energy surfaces.
Jörg Behler,Michele Parrinello +1 more