Hyperactive Learning (HAL) for Data-Driven Interatomic Potentials

2022/10/09 by Cas van der Oord, van der Oord, Cas, Matthias Sachs +7 · 19 citations
Computer Science · Engineering · Materials Science · Mathematics · Physics and Astronomy · #Computational Drug Discovery Methods #Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Fuel Cells and Related Materials #Machine Learning (stat.ML) #Machine Learning in Materials Science #physics.comp-ph #stat.ML

paper · pdf · doi:10.48550/arxiv.2210.04225

21 pages, 11 figures

openalex publication_date 2022/10/09 · arxiv created 2022/11/07 · arxiv updated 2022/11/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Data-driven interatomic potentials have emerged as a powerful class of surrogate models for \it ab initio potential energy surfaces that are able to reliably predict macroscopic properties with experimental accuracy. In generating accurate and transferable potentials the most time-consuming and arguably most important task is generating the training set, which still requires significant expert user input. To accelerate this process, this work presents \it hyperactive learning (HAL), a framework for formulating an accelerated sampling algorithm specifically for the task of training database generation. The key idea is to start from a physically motivated sampler (e.g., molecular dynamics) and add a biasing term that drives the system towards high uncertainty and thus to unseen training configurations. Building on this framework, general protocols for building training databases for alloys and polymers leveraging the HAL framework will be presented. For alloys, ACE potentials for AlSi10 are created by fitting to a minimal HAL-generated database containing 88 configurations (32 atoms each) with fast evaluation times of <100 microsecond/atom/cpu-core. These potentials are demonstrated to predict the melting temperature with excellent accuracy. For polymers, a HAL database is built using ACE, able to determine the density of a long polyethylene glycol (PEG) polymer formed of 200 monomer units with experimental accuracy by only fitting to small isolated PEG polymers with sizes ranging from 2 to 32.

Cited by

• Knowing when to trust machine-learned interatomic potentials
• Uncertainty Quantification for In Silico Chemistry
• Atomic cluster expansion potential for the Si-H system
• Fine-Tuning Bulk-oriented Universal Interatomic Potentials for Surfaces: Accuracy, Efficiency, and Forgetting Control
• Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications
• BLIPs: Bayesian Learned Interatomic Potentials
• Autonomous thermodynamically informed database generation for machine-learned interatomic potentials and application to magnesium
• Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials
• Molecular Dynamics Simulations of SrTiO₃ with Oxygen Vacancies using Neural Network Potentials
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence
• Fine-Tuning Universal Machine-Learned Interatomic Potentials: A Tutorial on Methods and Applications
• A Study on the Fine-Tuning Performance of Universal Machine-Learned Interatomic Potentials (U-MLIPs)
• An Atomic Cluster Expansion Potential for Twisted Multilayer Graphene
• Leveraging active learning-enhanced machine-learned interatomic potential for efficient infrared spectra prediction
• Going beyond density functional theory accuracy: Leveraging experimental data to refine pre-trained machine learning interatomic potentials
• Automated generation of structure datasets for machine learning potentials and alloys
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials
• From oligomers to entangled polymers: How to train a transferable machine learning interatomic potential
• Scalable Data-Driven Basis Selection for Linear Machine Learning Interatomic Potentials

Related

• Hyperparameter Optimization for Atomic Cluster Expansion Potentials
• Machine-learning interatomic potentials from a users perspective: A comparison of accuracy, speed and data efficiency
• Generator of Neural Network Potential for Molecular Dynamics: Constructing Robust and Accurate Potentials with Active Learning for Nanosecond-scale Simulations
• Data-efficient multi-fidelity training for high-fidelity machine\n learning interatomic potentials
• Beyond potentials: integrated machine-learning models for materials