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.
@article{arxiv.2410.15120,
title = {Generalizable Prediction Model of Molten Salt Mixture Density with Chemistry-Informed Transfer Learning},
author = {Julian Barra and Shayan Shahbazi and Anthony Birri and Rajni Chahal and Ibrahim Isah and Muhammad Nouman Anwar and Tyler Starkus and Prasanna Balaprakash and Stephen Lam},
journal= {arXiv preprint arXiv:2410.15120},
year = {2024}
}
Comments
Manuscript contains 25 pages including references and other information. Manuscript contains 4 figures and 3 tables. To be submitted to ACS Journal of Chemical Theory and Computation