Applying ANFIS and LSSVM Models for the Estimation of Biochar Aromaticity

The main aim of this work is the determination aromaticity in biochar from easier accessible parameters (e.g., elemental composition). To end, two machine learning models, including adaptive neurofuzzy inference system (ANFIS) and least-squares support vector (LSSVM), were used to predict constant form 98 dataset gathered earlier reported sources. outputs statistical showed that LSSVM model has ability estimate target parameter with R-squared values 0.986 a mean relative error 3.821 for overall dataset. Also, by analyzing sensitivity on input parameters, it was shown carbon percentage greatest effect values, high focus should be placed parameter. Finally, comparing methods proposed paper other models published previous studies, our higher accuracy predicting