analiza aiqbench
This research advances machine learning by introducing an information-matching framework for active learning that optimizes training data selection specifically for predicting complex material properties like plastic strength in metals. By targeting intermediate quantities of interest, the method achieves precise parameter constraints with minimal computational cost while addressing model error through uncertainty inflation corrections. These findings offer a robust strategy for developing bespoke interatomic potentials where first-principles methods are too expensive to scale directly.
Inverse design of bespoke interatomic potentials via active learning by information-matching
arXiv:2606.08148v2 Announce Type: replace-cross 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.
Authors:Yonatan Kurniawan (1), Logan D. Williams (2), Amit Samanta (2), Ilia Nikiforov (3), Daniel Schwalbe-Koda (4), Mark K. Transtrum (5), Ellad B. Tadmor (3), Vincenzo Lordi (2), Vasily V. Bulatov (2) ((1) Department of Physics and Astronomy, Brigham Young University, Provo, UT, USA, (2) Lawrence Livermore National Laboratory, Livermore, CA, USA, (3) Department of Aerospace Engineering and Mechanics, University of Minnesota, Minneapolis, MN, USA, (4) Department of Materials Science and Engineering, University of California, Los Angeles, CA, USA, (5) Cross Stream Consulting, Springville, UT, USA)
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.
Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
arXiv:2606.08148 [cond-mat.mtrl-sci]
(or arXiv:2606.08148v2 [cond-mat.mtrl-sci] for this version)
Text integral sub licența deschisă a publicației · 294 cuvinte