Prediction of hydrogen yield from supercritical gasification process of sewage sludge using machine learning and particle swarm hybrid strategy

This study presents an integrated framework of machine learning models (Artificial Neural Network, Ensembled Learning Tree, Support Vector Machine, and Gaussian Process Regression) and particle swarm optimization (PSO) to predict and optimize hydrogen production from SCWG using sewage sludge characteristics and process parameters. According to the results, ELT-PSO is preferred for forecasting hydrogen yield (Coefficient of determination (R²) = 0.997, Root Mean Square Error (RMSE) = 0.093), and it is highly suggested for handling complex variable-target correlation. However, Support Vector Machine (SVM) performed poorly, with R² = 0.83 and RMSE = 2.28. According to SHAP feature importance Temperature, Carbon, Hydrogen, and Pressure are among the parameters that have strong impact. In addition, by adjusting the ML hyperparameters, optimization method (PSO) was used to maximize H2 yield. The optimized ELT-PSO model was utilized to establish a Graphical User Interface that made it simple to calculate H2 yield.