Thermodynamic modeling of the LiCl-KCl-LaCl$_3$ system with Bayesian model selection and uncertainty quantification

TL;DR

This paper employs Bayesian model selection and uncertainty quantification to identify the best thermodynamic model for the LiCl-KCl-LaCl3 system, enhancing the understanding of molten salt properties for pyroprocessing applications.

Contribution

It introduces a Bayesian approach to select thermodynamic models and applies uncertainty quantification to molten salt systems, improving predictive accuracy.

Findings

MQMQA model is most favorable based on data

Uncertainty quantification aligns well with experimental results

Thermodynamic predictions aid in optimizing pyroprocessing

Abstract

Chloride molten salts are increasingly used in pyroprocessing techniques for the separation of lanthanides. Understanding thermodynamic properties of these salts is essential to predict their critical characteristics and optimize the separation process. Several thermodynamic models, including the associate model, the two-sublattice ionic model, and the modified quasichemical model with quadruplet approximation (MQMQA), have been utilized in the literature to capture the complexity of molten salts. In the present work, the Bayes factor is used to guide the model selection process for thermodynamic modeling of the KCl-LaCl3 system and provide statistical comparison of various models. The results indicate that the MQMQA model is the most favorable one based on available data. The LiCl-KCl-LaCl3 system has been further modelled with uncertainty quantification (UQ) using MQMQA with the thermodynamic properties of compounds in KCl-LaCl3 predicted by the quasiharmonic approach in terms of first-principles phonon calculations as a function of temperature. The calculated phase stability shows excellent agreement with experimental data, indicating that an appropriate thermodynamic model is important for accurately predicting critical characteristics of complex molten salts.