A blended ensemble model for biomass HHV prediction from ultimate analysis

This work proposes a new blended stacked ensemble machine-learning model (BEM) to predict biomass's higher heating value (HHV) from the ultimate analysis. Gorilla troop optimization (GTO) is utilized to estimate the hyperparameter values of BEM, leading to GBEM. In GBEM, support vector regression (SUVR), Gaussian process regression (GAPR), and Decision Tree (DETR) are used as the base learner, whereas adaptive linear neural network (ADALINE) is used as a meta-learner, respectively. Furthermore, Linear Regression (LIR), generalized additive model (GEAM), and bagging of regression trees (BAGG) are also designed for comparison purposes. Results reveal that GBEM predicts the HHV with a lower AARD% (2.959%) value than other designed ML predictive models. In addition to this, a predictive equation that gives the relationship between HHV and the ultimate analysis parameters C, H, O, N, and S is also derived using GTO.