DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Enabling robust offline active learning for machine learning potentials using simple physics-based priors

Journal Article · · Machine Learning: Science and Technology

Abstract Machine learning surrogate models for quantum mechanical simulations have enabled the field to efficiently and accurately study material and molecular systems. Developed models typically rely on a substantial amount of data to make reliable predictions of the potential energy landscape or careful active learning (AL) and uncertainty estimates. When starting with small datasets, convergence of AL approaches is a major outstanding challenge which has limited most demonstrations to online AL. In this work we demonstrate a Δ-machine learning (ML) approach that enables stable convergence in offline AL strategies by avoiding unphysical configurations with initial datasets as little as a single data point. We demonstrate our framework’s capabilities on a structural relaxation, transition state calculation, and molecular dynamics simulation, with the number of first principle calculations being cut down anywhere from 70%–90%. The approach is incorporated and developed alongside AMP torch , an open-source ML potential package, along with interactive Google Colab notebook examples.

Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
OSTI ID:
1755257
Journal Information:
Machine Learning: Science and Technology, Journal Name: Machine Learning: Science and Technology Journal Issue: 2 Vol. 2; ISSN 2632-2153
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (31)

A Critical Review of Machine Learning of Energy Materials journal January 2020
Gaussian approximation potentials: A brief tutorial introduction journal April 2015
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set journal July 1996
Amp: A modular approach to machine learning in atomistic simulations journal October 2016
Simulating Solvation and Acidity in Complex Mixtures with First-Principles Accuracy: The Case of CH 3 SO 3 H and H 2 O 2 in Phenol journal June 2020
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach journal April 2015
Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground journal November 2019
Performance and Cost Assessment of Machine Learning Interatomic Potentials journal October 2019
Machine Learning for Quantum Mechanical Properties of Atoms in Molecules journal July 2015
Understanding the Composition and Activity of Electrocatalytic Nanoalloys in Aqueous Solvents: A Combination of DFT and Accurate Neural Network Potentials journal April 2014
Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide journal July 2020
On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events journal March 2020
Neural network molecular dynamics simulations of solid–liquid interfaces: water at low-index copper surfaces journal January 2016
Addressing uncertainty in atomistic machine learning journal January 2017
Improved tangent estimate in the nudged elastic band method for finding minimum energy paths and saddle points journal December 2000
A climbing image nudged elastic band method for finding saddle points and minimum energy paths journal December 2000
Acceleration of saddle-point searches with machine learning journal August 2016
Perspective: Machine learning potentials for atomistic simulations journal November 2016
Machine learning for interatomic potential models journal February 2020
QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials journal September 2009
The atomic simulation environment—a Python library for working with atoms journal June 2017
From DFT to machine learning: recent approaches to materials science–a review journal May 2019
Methods for comparing uncertainty quantifications for material property predictions journal May 2020
Local Bayesian optimizer for atomic structures journal September 2019
Ab initio molecular dynamics for open-shell transition metals journal November 1993
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons journal April 2010
Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model journal April 2019
Phase Transitions of Hybrid Perovskites Simulated by Machine-Learning Force Fields Trained on the Fly with Bayesian Inference journal June 2019
Generalized Gradient Approximation Made Simple journal October 1996
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces journal April 2007
Artificial neural network correction for density-functional tight-binding molecular dynamics simulations journal June 2019

Similar Records

Learning Planar Ising Models Software
Software · Wed Aug 31 00:00:00 UTC 2022 · OSTI ID:code-92670

Machine Learning in Safeguards at Pebble Bed Reactors
Technical Report · Thu Oct 01 04:00:00 UTC 2020 · OSTI ID:1679954

Machine Learning for Correlated Intelligence. LDRD SAND Report
Technical Report · Sat Jan 22 04:00:00 UTC 2022 · OSTI ID:1841525

Related Subjects