Inverse design of bespoke interatomic potentials via active learning by information-matching
Abstract
Interatomic potentials (IPs) enable large-scale atomistic simulations beyond the reach of first-principles methods, but their predictive reliability depends critically on the selection of training data, quantified uncertainty, and model expressiveness. Active learning (AL) provides a principled framework for constructing efficient and accurate IPs, yet most strategies reduce parameter uncertainty without explicitly accounting for the specific material properties being predicted. The information-matching (IM) approach addresses this limitation by requiring that the selected training data provide at least as much parameter space information as needed to achieve prescribed uncertainty targets for selected quantities of interest (QoIs). Here, we apply IM to develop bespoke IPs specifically tailored for predicting plastic strength in metals. Due to the high computational cost of simulating plastic strength, we employ an indirect IM strategy that targets inexpensive intermediate QoIs that correlate with strength. The IM method enables precise parameter constraints with minimal training data, yielding precise predictions for both the intermediate QoIs and plastic strength. Yet, model error remains a key limitation, and a post hoc uncertainty inflation correction provides a viable means to mitigate this limitation. These findings illustrate both the promise and limits of uncertainty-aware AL for predicting complex material properties.
Versions
Related
- Benchmarking machine-learning interatomic potentials using classical force fields
- MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
- Cluster-based Structural Similarity for Dataset Visualization and Data Selection for Machine Learning Interatomic Potentials
- BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials
- Leveraging Machine Learning Interatomic Potentials into Fitting Fast and Accurate AMBER-Compatible Precise Force Field
BibTeX
@misc{kurniawan2026inverse,
title = {{Inverse design of bespoke interatomic potentials via active learning by information-matching}},
author = {Yonatan Kurniawan and Logan D. Williams and Amit Samanta and Ilia Nikiforov and Daniel Schwalbe-Koda and Mark K. Transtrum and Ellad B. Tadmor and Vincenzo Lordi and Vasily V. Bulatov},
howpublished = {arXiv},
year = {2026},
month = jul,
doi = {10.48550/arxiv.2606.08148},
eprint = {2606.08148},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.08148},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Inverse design of bespoke interatomic potentials via active learning by information-matching
AU - Yonatan Kurniawan
AU - Logan D. Williams
AU - Amit Samanta
AU - Ilia Nikiforov
AU - Daniel Schwalbe-Koda
AU - Mark K. Transtrum
AU - Ellad B. Tadmor
AU - Vincenzo Lordi
AU - Vasily V. Bulatov
PY - 2026
DA - 2026/07/29
PB - arXiv
DO - 10.48550/arxiv.2606.08148
UR - https://arxiv.org/abs/2606.08148
AB - Interatomic potentials (IPs) enable large-scale atomistic simulations beyond the reach of first-principles methods, but their predictive reliability depends critically on the selection of training data, quantified uncertainty, and model expressiveness. Active learning (AL) provides a principled framework for constructing efficient and accurate IPs, yet most strategies reduce parameter uncertainty without explicitly accounting for the specific material properties being predicted. The information-matching (IM) approach addresses this limitation by requiring that the selected training data provide at least as much parameter space information as needed to achieve prescribed uncertainty targets for selected quantities of interest (QoIs). Here, we apply IM to develop bespoke IPs specifically tailored for predicting plastic strength in metals. Due to the high computational cost of simulating plastic strength, we employ an indirect IM strategy that targets inexpensive intermediate QoIs that correlate with strength. The IM method enables precise parameter constraints with minimal training data, yielding precise predictions for both the intermediate QoIs and plastic strength. Yet, model error remains a key limitation, and a post hoc uncertainty inflation correction provides a viable means to mitigate this limitation. These findings illustrate both the promise and limits of uncertainty-aware AL for predicting complex material properties.
ER -