Employing Machine Learning Approaches to Determine the Heat Capacity of Cellulosic Biomass Samples with Different Origins

Abstract

Heat capacity is among the most well-known thermal properties of cellulosic biomass samples. This study assembles a general machine learning model to estimate the heat capacity of the cellulosic biomass samples with different origins. Combining the uncertainty and ranking analyses over 819 artificial intelligence (AI) models from seven different categories confirmed that the least-squares support vector regression (LSSVR) with the Gaussian kernel function is the best estimator. This model is validated using 700 laboratory heat capacities of four cellulosic biomass samples in wide temperature ranges (AARD=0.32%, MSE=1.88×10-3, and R2=0.999991). The data validity investigation approved that only one out of 700 experimental data is an outlier. The LSSVR model considers the effect of crystallinity, temperature, and sulfur and ash content of the cellulosic samples on their heat capacity. The LSSVR improves the achieved accuracy using the empirical correlation by more than 62%.