DOE OSTI · 1755257
Enabling robust offline active learning for machine learning potentials using simple physics-based priors
Abstract
Abstract Machine learning surrogate models for quantum mechanical simulations have enabled the field to efficiently and accurately study material and molecular systems. Developed models typically rely on a substantial amount of data to make reliable predictions of the potential energy landscape or careful active learning (AL) and uncertainty estimates. When starting with small datasets, convergence of AL approaches is a major outstanding challenge which has limited most demonstrations to online AL. In this work we demonstrate a Δ-machine learning (ML) approach that enables stable convergence in offline AL strategies by avoiding unphysical configurations with initial datasets as little as a single data point. We demonstrate our framework’s capabilities on a structural relaxation, transition state calculation, and molecular dynamics simulation, with the number of first principle calculations being cut down anywhere from 70%–90%. The approach is incorporated and developed alongside AMP torch , an open-source ML potential package, along with interactive Google Colab notebook examples.
Keep this discovery
Explore connections, maps & timelines
Shuaibi, Muhammed, Sivakumar, Saurabh, Chen, Rui Qi, Ulissi, Zachary W. (ORCID:0000000294014918). 2020-12-29. Enabling robust offline active learning for machine learning potentials using simple physics-based priors. https://doi.org/10.1088/2632-2153%2Fabcc44. https://searchnasa.com/record/osti%3A1755257/enabling-robust-offline-active-learning-for-machine-learning-potentials-using-simple-physics-based-p
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.