Coherent energy and force uncertainty in deep learning force fields

2023/12/07 by Peter Bjørn Jørgensen, Jørgensen, Peter Bjørn, Jonas Busk +5
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Computational Drug Discovery Methods #Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Protein Structure and Dynamics

paper · pdf · doi:10.48550/arxiv.2312.04174

openalex publication_date 2023/12/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In machine learning energy potentials for atomic systems, forces are commonly obtained as the negative derivative of the energy function with respect to atomic positions. To quantify aleatoric uncertainty in the predicted energies, a widely used modeling approach involves predicting both a mean and variance for each energy value. However, this model is not differentiable under the usual white noise assumption, so energy uncertainty does not naturally translate to force uncertainty. In this work we propose a machine learning potential energy model in which energy and force aleatoric uncertainty are linked through a spatially correlated noise process. We demonstrate our approach on an equivariant messages passing neural network potential trained on energies and forces on two out-of-equilibrium molecular datasets. Furthermore, we also show how to obtain epistemic uncertainties in this setting based on a Bayesian interpretation of deep ensemble models.

Citations

• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Equivariant message passing for the prediction of tensorial properties and molecular spectra
• On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
• Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules

Related

• Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing
• Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forces
• Robust and scalable uncertainty estimation with conformal prediction for machine-learned interatomic potentials
• Bayesian Neural Networks versus deep ensembles for uncertainty quantification in machine learning interatomic potentials
• On-the-Fly Fine-Tuning of Foundational Neural Network Potentials: A Bayesian Neural Network Approach