Predicting bulk density in Brazilian soils for carbon stocks calculation: a comparative study of multiple linear regression and Random Forest models using continuous and categorical variables.

SANTOS, W. P. dos; VAZ, C. M. P.; MARTIN NETO, L.; ANSELMI, A.; TOMASELLA, J.; COSTA, F. de S.; ALBUQUERQUE, J. A.; LIER, Q. de J. van; GALBIERI, R.; PERINA, F. J.

Predicting bulk density in Brazilian soils for carbon stocks calculation: a comparative study of multiple linear regression and Random Forest models using continuous and categorical variables.

Autores

Descripción

The present study aims to develop pedotransfer functions for estimating ρb using stepwise multiple linear regression applied to soil properties from available databases, which are considered suitable predictors (PTF-1).

Palabras clave

Química del suelo, Densidad aparente, Carbono orgánico del suelo, Disponibilidad de nutrientes, Funciones de edafotransferancia, Predicción, Análisis estadístico, Análisis de regresión, Química do Solo, Carbono, Estoque, Disponibilidade de Nutriente, Estimativa, Análise Estatística, Regressão Linear, Soil chemistry, Bulk density, Soil organic carbon, Nutrient availability, Pedotransfer functions, Prediction, Statistical analysis, Regression analysis