Enhancing prediction of elemental composition through machine learning decision tree models for biomass gasification optimization

The worldwide transition to cleaner, sustainable energy sources, prompted by population growth and industrialization, responds to uncertain fossil fuel prices and environmental concerns, highlighting the substantial benefits of renewable energy in reducing greenhouse gas emissions and addressing climate change. Derived from non-fossilized organic materials, biomass emerges as a significant and sustainable contributor to renewable energy. Its diverse nature is complemented by a range of conversion technologies, encompassing combustion, pyrolysis, gasification, and liquefaction, providing versatile avenues for biomass energy transformation. Gasification, the transformative process of converting organic matter into combustible gases under controlled oxygen levels, is accomplished through direct oxygen supply or pyrolysis. This method yields a dependable gaseous fuel versatile for heating, industrial processes, power generation, and liquid fuel production. Machine learning employs advanced statistical techniques for modeling across diverse industries, showcasing particular efficacy in optimizing thermochemical processes by precisely identifying the optimal operating conditions required for achieving desired product properties. These models utilize proximate biomass data to predict the elemental compositions of N2 and H2. Assessment of both single and two hybrid models indicated that the introduced optimizers significantly enhanced the estimation of N2 and H2 when combined with Decision Tree (DT), with Decision Tree Coupled with Artificial Hummingbird Algorithm (DTAH) proving particularly effective. Notably, DTAH demonstrated outstanding performance with remarkable R2 values of 0.990 for N2 and 0.992 for H2. Additionally, the minimal Root Mean Square Error (RMSE) values of 1.291 and 1.550 for N2 and H2 predictions respectively underscore the precision of DTAH, establishing it as a suitable choice for practical real-world applications.