Generalizable Prediction Model of Molten Salt Mixture Density with Chemistry-Informed Transfer Learning

2024/10/19 by Barra, Julian, Shahbazi, Shayan, Birri, Anthony +6
#FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Materials Science (cond-mat.mtrl-sci)

paper · doi:10.48550/arxiv.2410.15120

Abstract

Optimally designing molten salt applications requires knowledge of their thermophysical properties, but existing databases are incomplete, and experiments are challenging. Ideal mixing and Redlich-Kister models are computationally cheap but lack either accuracy or generality. To address this, a transfer learning approach using deep neural networks (DNNs) is proposed, combining Redlich-Kister models, experimental data, and ab initio properties. The approach predicts molten salt density with high accuracy (r² > 0.99, MAPE < 1%), outperforming the alternatives.

Related

• Uncertainty and Exploration of Deep Learning-based Atomistic Models for Screening Molten Salt Properties and Compositions
• SuperSalt: Equivariant Neural Network Force Fields for Multicomponent Molten Salts System
• Machine-Learning Potentials for sodium-potassium chloride mixtures: Predicting thermophysical properties and phase behavior of multicomponent salts
• SPINN: An Optimal Self-Supervised Physics-Informed Neural Network Framework
• Transferable Deep Learning Potential Reveals Intermediate-Range Ordering Effects in LiF-NaF-ZrF4 Molten Salt