A Three-Phase Analysis of Synergistic Effects During Co-pyrolysis of Algae and Wood for Biochar Yield Using Machine Learning

TL;DR

This study systematically analyzes the synergistic effects of co-pyrolysis of algae and wood on biochar yield using machine learning and deep learning models across three phases, providing insights into prediction accuracy and biomass interactions.

Contribution

It introduces a three-phase framework combining kinetic analysis, correlation studies, and classification of biomass ratios, utilizing ML/DL techniques to enhance biochar yield prediction and understanding of biomass synergy.

Findings

Decision tree regressor achieved perfect biochar yield prediction (MSE=0).

Support Vector Regression showed high accuracy (0.972) in correlation analysis.

Support Vector and Random Forest were effective for classifying biochar yield above/below 40%.

Abstract

Pyrolysis techniques have served to be a groundbreaking technique for effectively utilising natural and man-made biomass products like plastics, wood, crop residue, fruit peels etc. Recent advancements have shown a greater yield of essential products like biochar, bio-oil and other non-condensable gases by blending different biomasses in a certain ratio. This synergy effect of combining two pyrolytic raw materials i.e co-pyrolysis of algae and wood biomass has been systematically studied and grouped into 3 phases in this research paper-kinetic analysis of co-pyrolysis, correlation among proximate and ultimate analysis with bio-char yield and lastly grouping of different weight ratios based on biochar yield up to a certain percentage. Different ML and DL algorithms have been utilized for regression and classification techniques to give a comprehensive overview of the effect of the synergy of two different biomass materials on biochar yield. For the first phase, the best prediction of biochar yield was obtained by using a decision tree regressor with a perfect MSE score of 0.00, followed by a gradient-boosting regressor. The second phase was analyzed using both ML and DL techniques. Within ML, SVR proved to be the most convenient model with an accuracy score of 0.972 with DNN employed for deep learning technique. Finally, for the third phase, binary classification was applied to biochar yield with and without heating rate for biochar yield percentage above and below 40%. The best technique for ML was Support Vector followed by Random forest while ANN was the most suitable Deep Learning Technique.