Learning thermodynamically constrained equations of state with uncertainty
APL Machine Learning · 01.03.2024 · 2 (1)
DOI: 10.1063/5.0165298 ↗Kurz gefasst
Fachartikel in der Zeitschrift APL Machine Learning, online erschienen am 08.01.2024. Verfasst von Himanshu Sharma und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Defense Threat Reduction Agency, Lawrence Livermore National Laboratory.
Abstract (Originalsprache)
Numerical simulations of high energy-density experiments require equation of state (EOS) models that relate a material’s thermodynamic state variables—specifically pressure, volume/density, energy, and temperature. EOS models are typically constructed using a semi-empirical parametric methodology, which assumes a physics-informed functional form with many tunable parameters calibrated using experimental/simulation data. Since there are inherent uncertainties in the calibration data (parametric uncertainty) and the assumed functional EOS form (model uncertainty), it is essential to perform uncertainty quantification (UQ) to improve confidence in EOS predictions. Model uncertainty is challenging for UQ studies since it requires exploring the space of all possible physically consistent functional forms. Thus, it is often neglected in favor of parametric uncertainty, which is easier to quantify without violating thermodynamic laws. This work presents a data-driven machine learning approach to constructing EOS models that naturally captures model uncertainty while satisfying the necessary thermodynamic consistency and stability constraints. We propose a novel framework based on physics-informed Gaussian process regression (GPR) that automatically captures total uncertainty in the EOS and can be jointly trained on both simulation and experimental data sources. A GPR model for the shock Hugoniot is derived, and its uncertainties are quantified using the proposed framework. We apply the proposed model to learn the EOS for the diamond solid state of carbon using both density functional theory data and experimental shock Hugoniot data to train the model and show that the prediction uncertainty is reduced by considering thermodynamic constraints.
Förderung
- Defense Threat Reduction Agency
- Lawrence Livermore National Laboratory
Zitieren
APA
Sharma, H., Gaffney, J. A., Tsapetis, D., & Shields, M. D. (2024). Learning thermodynamically constrained equations of state with uncertainty. APL Machine Learning, 2(1). https://doi.org/10.1063/5.0165298
Vancouver
Sharma H, Gaffney JA, Tsapetis D, Shields MD. Learning thermodynamically constrained equations of state with uncertainty. APL Machine Learning. 2024;2(1). doi:10.1063/5.0165298
BibTeX
@article{Sharma2024,
author = {Sharma, Himanshu and Gaffney, Jim A. and Tsapetis, Dimitrios and Shields, Michael D.},
title = {Learning thermodynamically constrained equations of state with uncertainty},
journal = {APL Machine Learning},
year = {2024},
volume = {2},
number = {1},
doi = {10.1063/5.0165298}
}
EUVIMED