Hydrogen production from blended waste biomass: pyrolysis, thermodynamic-kinetic analysis and AI-based modelling
This study investigates the sustainable hydrogen production potential of two underutilized food-derived biomass wastes—spent coffee grounds and jujube pits—via pyrolysis. Thermogravimetric analysis (TGA/DTG), pyrolysis-micro gas chromatography (Py-Micro GC), and kinetic modeling (KAS, FWO, and Friedman methods) were employed to systematically characterize pyrolytic behavior and H₂ yield for individual feedstocks and three blended formulations (Blend 1–3). An AI-enhanced modeling framework was innovatively developed, integrating long short-term memory (LSTM) neural networks to achieve highly accurate prediction of thermogravimetric profiles (R² = 0.9998) and to elucidate inter-material synergistic effects. Results show that Blend 3 delivers the highest hydrogen yield, while Blend 1 exhibits the lowest apparent activation energy (161.75 kJ/mol). This work establishes a scalable, integrated kinetics–AI optimization paradigm for targeted hydrogen production from waste biomass.