Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF)

• Published in: Ciência e agrotecnologia Vol. 41; no. 6; pp. 648 - 664
• Main Authors: Silva, Sérgio Henrique Godinho, Teixeira, Anita Fernanda dos Santos, Menezes, Michele Duarte de, Guilherme, Luiz Roberto Guimarães, Moreira, Fatima Maria de Souza, Curi, Nilton
• Format: Journal Article
• Language: English
• Published: Editora da Universidade Federal de Lavras 01.12.2017; Universidade Federal de Lavras
• Subjects: AGRICULTURE, MULTIDISCIPLINARY; Análises de solo; predição espacial; sensor próximo; sensor próximo; Soil analyses; Análises de solo; spatial prediction; proximal sensor; predição espacial

ABSTRACT Determination of soil properties helps in the correct management of soil fertility. The portable X-ray fluorescence spectrometer (pXRF) has been recently adopted to determine total chemical element contents in soils, allowing soil property inferences. However, these studies are still scarce...