Work

Enhanced hydrogen production from methane pyrolysis using CatBoost with reptile search algorithm optimization

Year: 2025

Type: article

Abstract: The growing demand for clean energy solutions and the rapid depletion of fossil fuel resources have made it important to find carbon-free energy options. One promising approach is hydrogen production via methane pyrolysis. In this study, we employed the CatBoost machine learning (ML) algorithm to predict hydrogen yield (H2) and methane (CH4) conversion during the pyrolysis process. To further enhance predictive performance, the Reptile Search Algorithm (RSA) was integrated to optimize the hyperparameters of the CatBoost model, resulting in a hybrid Cat-RSA model. Model evaluation revealed that the RSA optimization significantly improved the prediction accuracy of both H2 yield and CH4 conversion. The Cat-RSA model achieved impressive performance with coefficient of determination (R2) values of 0.9422 for H2 yield and 0.9721 for CH4 conversion. Furthermore, the model’s precision is underscored by low Root Mean Squared Error (RMSE) values of 5.464 for H2 and 3.864 for CH4 and Mean Absolute Relative Error (MARE) values of 0.2682 for H2 and 0.2137 for CH4. These results are comparable to those reported in previous studies, such as SVM-ABC (R2 = 0.9464) and BR-LMMLP (R2 = 0.9530) for H2 yield and are slightly lower than XGBoost (R2 = 0.9996). Additionally, SHapley Additive exPlanations (SHAP) analysis identified key features, including gas hourly space velocity (GHSV), time, copper wt.% in the catalyst, and temperature, as the significant contributors to the model’s predictions. Furthermore, the Cat-RSA model predicted a maximum hydrogen yield of 91.05% under the following optimal input conditions: Temperature = 714.9 °C, GHSV = 7111.9 mL/h·g, CH4 concentration = 18.4%, time = 14.1 min, and calcined temperature = 476.9 °C. In addition, the optimal catalyst composition featured high proportions of Ni (55.25 wt.%) and Co (30.00 wt.%). This work enhances our understanding of how hydrogen is produced from methane pyrolysis and demonstrates the potential of innovative optimization algorithms in improving ML applications within energy systems.

Source: Energy Nexus

DOI: 10.1016/j.nexus.2025.100576

Authors: Ibrahim Shomope, Amani Al-Othman, Muhammad Tawalbeh, Hussam Alshraideh, Abdulrahman Alraeesi

Institutions: American University of Sharjah, University of Sharjah, Jordan University of Science and Technology, United Arab Emirates University

Language: English

Topic: Catalysts for Methane Reforming

Subfield: Catalysis

Field: Chemical Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,200