Model-free estimation of completeness, uncertainties, and outliers in atomistic machine learning using information theory
Top Cited Papers
Open Access
- 29 April 2025
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-13
Abstract
An accurate description of information is relevant for a range of problems in atomistic machine learning (ML), such as crafting training sets, performing uncertainty quantification (UQ), or extracting physical insights from large datasets. However, atomistic ML often relies on unsupervised learning or model predictions to analyze information contents from simulation or training data. Here, we introduce a theoretical framework that provides a rigorous, model-free tool to quantify information contents in atomistic simulations. We demonstrate that the information entropy of a distribution of atom-centered environments explains known heuristics in ML potential developments, from training set sizes to dataset optimality. Using this tool, we propose a model-free UQ method that reliably predicts epistemic uncertainty and detects out-of-distribution samples, including rare events in systems such as nucleation. This method provides a general tool for data-driven atomistic modeling and combines efforts in ML, simulations, and physical explainability.Keywords
All Related Versions
Funding Information
- DOE | LDRD | Lawrence Livermore National Laboratory (22-ERD-055, 23-SI-006, 23-SI-006, 23-SI-006, 23-SI-006)
- U.S. Department of Energy (DE-SC0025642)
This publication has 60 references indexed in Scilit:
- LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scalesComputer Physics Communications, 2022
- Neural Network Potential Energy Surfaces for Small Molecules and ReactionsChemical Reviews, 2020
- A coherent set of model equations for various surface and interface energies in systems with liquid and solid metals and alloysAdvances in Colloid and Interface Science, 2020
- Constructing high‐dimensional neural network potentials: A tutorial reviewInternational Journal of Quantum Chemistry, 2015
- Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentialsJournal of Computational Physics, 2015
- Correlations between Surface and Interface Energies with Respect to Crystal NucleationJournal of Colloid and Interface Science, 2002
- Systematic analysis of local atomic structure combined with 3D computer graphicsComputational Materials Science, 1994
- Correlation entropy in a classical liquidPhysics Letters A, 1987
- Life, information theory, and topologyBulletin of Mathematical Biology, 1955
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948