基于化学信息迁移学习的熔盐混合物密度可泛化预测模型
机器学习
2024-10-22 v1 材料科学
摘要
最优设计熔盐应用需要其热力学性质的知识，但现有数据库不完整且实验困难。理想混合和 Redlich-Kister 模型计算廉价但缺乏准确性或通用性。为此，提出一种使用深度神经网络 (DNN) 的迁移学习方法，将 Redlich-Kister 模型、实验数据和 ab initio 属性相结合。该方法以高准确性预测熔盐密度 ( > 0.99, MAPE < 1%)，优于替代方案。
引用
@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}
}
备注
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