This study explores the feasibility of utilizing bedded salt deposits as sites for underground hydrogen storage. We introduce an innovative artificial intelligence framework that applies multi-criteria decision-making and spatial data analysis to identify the most suitable locations for storing hydrogen in salt caverns. Our approach integrates a unified platform with eight distinct machine-learning algorithms—KNN, SVM, LightGBM, XGBoost, MLP, CatBoost, GBR, and MLR—creating rock salt deposit suitability maps for hydrogen storage. The performance of these algorithms was evaluated using various metrics, including Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Correlation Coefficient (R2), compared against an actual dataset. The CatBoost model demonstrated exceptional performance, achieving an R2 of 0.88, MSE of 0.0816, MAE of 0.1994, RMSE of 0.2833, and MAPE of 0.0163. The novel methodology, leveraging advanced machine learning techniques, offers a unique perspective in assessing the potential of underground hydrogen storage. This approach is a valuable asset for various stakeholders, including government bodies, geological services, renewable energy facilities, and the chemical/petrochemical industry, aiding them in identifying optimal locations for hydrogen storage.
Read full abstract