Machine learning approaches for predicting syngas production in biomass gasification

• DOI: 10.1515/cppm-2024-0096
• Publication Date: 2025-05-22T06:30:13Z
• Authors: Zhe Zhang; Zhigao Chen
• Keywords: Biomass gasification

Abstract Fossil fuel dependence causes environmental and resource issues, intensified by climate change population growth. Renewable sources like solar, wind, biomass are rising. Biomass contributes 10–14 % of global energy, with gasification offering stable output useful byproducts. However, efficiency concerns challenge its economic viability, prompting the need for predictive models under diverse conditions. This study introduces a novel hybrid modeling approach that integrates Naive Bayes (NB) two advanced metaheuristic optimization algorithms, Jellyfish Search Optimizer (JSO) Cheetah (CO), to enhance prediction accuracy elemental compositions nitrogen hydrogen from proximate data. The proposed schemes indicate drastically improved estimation accuracy, among these, NBCO, i.e., + hybrid, was most effective. NBCO achieved RMSE values 1.472 1.955 hydrogen, validating better ability. By utilizing synergistic properties NB JSO CO, this work presents sound model complementing viable tool optimizing renewable energy processes. With enhanced composition, enable control processes increased in production, reduced emissions, decreased operation costs. Accuracy determining optimizes gasifier efficiency, enabling cleaner, more cost-effective production. provides feasible solution businesses policymakers seeking maximize potential as source while minimizing problems.