A recent study by Sait et al., published in Agronomy, explores methods to optimize biochar production from palm kernel shells (PKS) using statistical (response surface methodology, RSM) and artificial intelligence-based modeling (artificial neural networks, ANN). The researchers analyzed the effects of pyrolysis temperature, nitrogen flow rate, and residence time on biochar yield, aiming to improve sustainability in agricultural waste management.

Under optimal conditions of 799.71°C pyrolysis temperature, 150.01 mL/min nitrogen flow rate, and 107.61 minutes residence time, the RSM model achieved a maximum biochar yield of 37.87%. This study revealed that temperature was the most influential parameter, supported by a high coefficient of determination (R² = 0.989) for the quadratic response surface model. Among four ANN models tested, the optimized ANN also showed strong predictive accuracy (R² = 0.9). However, the RSM model outperformed ANN in yield prediction accuracy.

Physicochemical analysis of biochar demonstrated high carbon content (92.9% at 800°C), mesoporous structure, and substantial surface area, making it suitable for applications like soil amendment, water filtration, and carbon sequestration.

This hybrid analytical approach underscores the potential of PKS biochar for waste valorization and environmental benefits, combining advanced modeling techniques to refine production parameters. The findings promote the use of sustainable materials for agricultural and industrial applications.


SOURCE: Sait, et al (2025) Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques. Agronomy. https://doi.org/10.3390/agronomy15010181


Leave a Reply

Trending

Discover more from Biochar Today

Subscribe now to keep reading and get access to the full archive.

Continue reading