Prediction of nitrate leaching from soil amended with biosolids by machine learning algorithms

Abstract

This study focused on employing machine learning algorithms to forecast nitrate leaching from soils treated with biochar and vermicompost derived from sugarcane bagasse. input variables including bulk density, porosity, organic carbon, nitrogen, phosphorus, anion exchange capacity, cation exchange capacity, pH, and electrical conductivity, while nitrate leaching was the target variable for prediction. A comparative analysis of machine learning models indicated that Random Forest Regression outperformed linear regression in the prediction of nitrate leaching. Additionally, among the input variables, anion exchange capacity, cation exchange capacity, bulk density, and EC showed the most significant influence in utilizing these models as predictive tools for nitrate leaching from soils treated with slow-release fertilizers.