English

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

Machine Learning 2024-10-22 v1 Materials Science

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 (r2r^{2} > 0.99, MAPE < 1%), outperforming the alternatives.

Keywords

Cite

@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