Hydrogen production from the steam gasification of hydrochar: A multi-output machine learning approach integrated with metaheuristic algorithms

Steam gasification of hydrochar requires high-temperature reactors, making the process costly and time-consuming. This study proposes soft computing approaches as efficient alternatives for predicting multiple output (syngas concentration, H 2 /CO ratio and heating value based on hydrochar composition and steam gasification operating conditions. Four Machine learning (ML) models enhanced with metaheuristic optimization techniques (Genetic Algorithms (GA) and Particle Swarm Optimization (PSO)) were trained on experimental data to predict syngas composition, H 2 /CO and higher heating value. Among the models, Gaussian Process Regression (GPR-GA (Coefficient of Determination, R 2 = 0.83, root mean square error, RMSE = 4.19) and GPR-PSO (R 2 = 0.82, RMSE = 4.3)) showed superior performance for hydrogen concentration prediction accuracy. Two-way Partial dependence plots and SHAP show that Steam to biomass ratio (S/B) and higher heating value has a significant effect on hydrogen concentration. Moreover, the optimal steam to biomass ratio and temperature should be in the range of 2.5–3 and 750–850 °C for highest predicted hydrogen concentration. To facilitate practical applications, graphical user interface (GUI) was developed using the best-performing ML model. GUI allows users to predict syngas compositions in real time and eliminates the need for extensive experimentation, providing a user-friendly platform to optimize syngas production while ensuring efficiency and reliability. • ML models optimized for accurate syngas composition prediction and analysis. • H 2 concentration increases with carbon, steam-to-biomass ratio, and temperature. • GPR-GA and GPR-PSO models outperformed others in hydrogen prediction accuracy. • Developed a Graphical user interface for real-time syngas composition predictions.