Data-Driven Modeling of Molten Chloride Corrosion Using Static Test Data
Abstract
Molten chloride corrosion has been studied for decades, yet reliable prediction across different alloys, salts, and test conditions remains difficult. In this work, 291 static molten chloride corrosion experiments reported in the literature were compiled into a structured dataset and used to develop an interpretable machine-learning framework for corrosion-rate predictions. To better represent the differences in salt condition across studies, a Chloride Salt Preparation Index (CSPI) was introduced to bring the reported salt-treatment method, atmosphere control, and pre-exposure impurity condition on a common numerical scale. A blended tree-based ensemble provided the most consistent predictive performance, achieving a cross-validated R2 of 0.85 and an MAE of 0.41 mg cm−2 day−1. The graded CSPI retained more useful information than a simple purified/unpurified classification and emerged as the dominant model descriptor. Global sensitivity and SHAP analyses further identified exposure time, temperature, and alloy chemistry as important contributors to the model predictions, with several observed trends consistent with the established molten-chloride corrosion behavior. The conformal prediction intervals were well calibrated, providing an estimate of prediction uncertainty in addition to the point prediction. Overall, the framework demonstrates that historical corrosion data can support quantitative, interpretable, and uncertainty-aware prediction when experimental context is represented explicitly, while also highlighting where more consistent reporting and targeted experiments are needed to improve future molten-salt corrosion models.
Related
- Multiscale Modeling of Zr Corrosion: Predicting Microstructures of Oxide Films
- Visualizing surface-reaction-driven chloride migration and cascading failure in sulfide solid electrolytes
- Physics-integrated neural network modeling of heat and mass transfer in cryogenic liquid storage under static and dynamic conditions
- Data-driven and physics-guided neural approaches for LCR circuit modeling: a comparative analysis
- Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics
BibTeX
@misc{pathik2026datadriven,
title = {{Data-Driven Modeling of Molten Chloride Corrosion Using Static Test Data}},
author = {Md Mahmudul Hasan Pathik},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07125},
eprint = {2611.07125},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07125},
}
RIS
TY - UNPB
TI - Data-Driven Modeling of Molten Chloride Corrosion Using Static Test Data
AU - Md Mahmudul Hasan Pathik
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.07125
UR - https://arxiv.org/abs/2611.07125
AB - Molten chloride corrosion has been studied for decades, yet reliable prediction across different alloys, salts, and test conditions remains difficult. In this work, 291 static molten chloride corrosion experiments reported in the literature were compiled into a structured dataset and used to develop an interpretable machine-learning framework for corrosion-rate predictions. To better represent the differences in salt condition across studies, a Chloride Salt Preparation Index (CSPI) was introduced to bring the reported salt-treatment method, atmosphere control, and pre-exposure impurity condition on a common numerical scale. A blended tree-based ensemble provided the most consistent predictive performance, achieving a cross-validated R^2 of 0.85 and an MAE of 0.41 mg cm^−2 day^−1. The graded CSPI retained more useful information than a simple purified/unpurified classification and emerged as the dominant model descriptor. Global sensitivity and SHAP analyses further identified exposure time, temperature, and alloy chemistry as important contributors to the model predictions, with several observed trends consistent with the established molten-chloride corrosion behavior. The conformal prediction intervals were well calibrated, providing an estimate of prediction uncertainty in addition to the point prediction. Overall, the framework demonstrates that historical corrosion data can support quantitative, interpretable, and uncertainty-aware prediction when experimental context is represented explicitly, while also highlighting where more consistent reporting and targeted experiments are needed to improve future molten-salt corrosion models.
ER -