LTAU-FF: Loss Trajectory Analysis for Uncertainty in atomistic Force Fields
Open Access
- 20 February 2025
- journal article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (1) , 015048
Abstract
Model ensembles are effective tools for estimating prediction uncertainty in deep learning atomistic force fields. However, their widespread adoption is hindered by high computational costs and overconfident error estimates. In this work, we address these challenges by leveraging distributions of per-sample errors obtained during training and employing a distance-based similarity search in the model latent space. Our method, which we call LTAU (Loss Trajectory Analysis for Uncertainty), efficiently estimates the full probability distribution function of errors for any test point using the logged training errors, achieving speeds that are 2–3 orders of magnitudes faster than typical ensemble methods and allowing it to be used for tasks where training or evaluating multiple models would be infeasible. We apply LTAU towards estimating parametric uncertainty in atomistic force fields (LTAU-FF), demonstrating that it produces well-calibrated confidence intervals and predicts errors that correlate strongly with the true errors for data near the training domain. Furthermore, we show that the errors predicted by LTAU-FF can be used in practical applications for detecting out-of-domain data, tuning model performance, and predicting failure during simulations. We believe that LTAU will be a valuable tool for uncertainty quantification in atomistic force fields and is a promising method that should be further explored in other domains of machine learning.Keywords
All Related Versions
Funding Information
- Lawrence Livermore National Laboratory (DE-AC52-07NA27344)
This publication has 44 references indexed in Scilit:
- A survey on epistemic (model) uncertainty in supervised learning: Recent advances and applicationsNeurocomputing, 2022
- E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentialsNature Communications, 2022
- Linear Atomic Cluster Expansion Force Fields for Organic Molecules: Beyond RMSEJournal of Chemical Theory and Computation, 2021
- Correction to “The Open Catalyst 2020 (OC20) Dataset and Community Challenges”ACS Catalysis, 2021
- Machine-learning interatomic potentials for materials scienceActa Materialia, 2021
- Open Catalyst 2020 (OC20) Dataset and Community ChallengesACS Catalysis, 2021
- Neural Network Potential Energy Surfaces for Small Molecules and ReactionsChemical Reviews, 2020
- Uncertainty Quantification Using Neural Networks for Molecular Property PredictionJournal of Chemical Information and Modeling, 2020
- Machine Learning Interatomic Potentials as Emerging Tools for Materials ScienceAdvanced Materials, 2019
- Molecular Similarity-Based Domain Applicability Metric Efficiently Identifies Out-of-Domain CompoundsJournal of Chemical Information and Modeling, 2018