Prediction of hydrogen solubility in aqueous solution using modified mixed effects random forest based on particle swarm optimization for underground hydrogen storage

• Published in: International journal of hydrogen energy Vol. 87; pp. 373 - 388
• Main Authors: Mwakipunda, Grant Charles, Komba, Norga Alloyce, Kouassi, Allou Koffi Franck, Ayimadu, Edwin Twum, Mgimba, Melckzedeck Michael, Ngata, Mbega Ramadhani, Yu, Long
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 18.10.2024
• Subjects: Geological formations; Hydrogen solubility; Machine learning; Underground hydrogen storage; Geological formations; Underground hydrogen storage; Hydrogen solubility; Machine learning
• ISSN: 0360-3199
• DOI: 10.1016/j.ijhydene.2024.09.054

This paper aims to enhance the prediction accuracy of hydrogen solubility in aqueous solution, which is crucial for safe and efficient underground hydrogen storage (UHS). The study developed a new hybrid machine learning (ML) algorithm, particle swarm optimization-mixed effects random forest (PSO-MERF), and compared with Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), Random Forest (RF), and Equation of State (EOS) models. PSO-MERF demonstrated superior performance, achieving a high correlation coefficient (R) of 0.9982, root means square error (RMSE) of 0.0015, and mean absolute error (MAE) of 0.00091, with less computational time (1.01 s). Among the EOS models used, Soave-Redlich-Kwong (SRK) outperformed other models. The results suggest that PSO-MERF hyperparameter optimization leads to more accurate hydrogen solubility predictions, encouraging its use in UHS design and operation for safe and sustainable hydrogen storage. •PSO-MERF developed for hydrogen solubility prediction in aqueous solution for UHS.•PSO-MERF was compared with KNN, XGBoost, RF, and EOS.•PR outperformed other EOS models during prediction.•PSO-MERF outperformed all models in prediction purpose.•Salinity is the most important parameter in UHS operations.