Tropical soil pH and sorption complex prediction via portable X-ray fluorescence spectrometry

Tropical soil pH and sorption complex prediction via portable X-ray fluorescence spectrometry

•pXRF was used to predict five different soil properties in tropical soils.•Three different algorithms were tested and compared: Cubist, RF and SMLR.•Sum of bases, base saturation percentage, and Alsat achieved better results.•CaO was the most influential variable for soil properties prediction.•pXR...

Full description

Saved in:
Bibliographic Details
Published in:Geoderma Vol. 361; p. 114132
Main Authors: dos Santos Teixeira, Anita Fernanda, Henrique Procópio Pelegrino, Marcelo, Missina Faria, Wilson, Henrique Godinho Silva, Sérgio, Gabriela Marcolino Gonçalves, Mariana, Weimar Acerbi Júnior, Fausto, Rezende Gomide, Lucas, Linares Pádua Júnior, Alceu, de Souza, Igor Alexandre, Chakraborty, Somsubhra, Weindorf, David C., Roberto Guimarães Guilherme, Luiz, Curi, Nilton
Format: Journal Article
Language:English
Published: Elsevier B.V 01-03-2020
Subjects:
Base saturation
CEC
Cubist
pXRF
Random forest
Soil fertility
CEC
SUB
OOB
Soil fertility
SMLR
Base saturation
RPD
pXRF
Cubist
Random forest
RMSE
SB
CS
SURF
Varex
CV
RF
MSEoob
ME
NIST
Alsat
BSP
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•pXRF was used to predict five different soil properties in tropical soils.•Three different algorithms were tested and compared: Cubist, RF and SMLR.•Sum of bases, base saturation percentage, and Alsat achieved better results.•CaO was the most influential variable for soil properties prediction.•pXRF can accurately predict fertility properties for varying Brazilian soils. Portable X-ray fluorescence (pXRF) spectrometry delivers results rapidly, at low-cost, and without generating chemical residues. This study aimed to predict soil pH, sum of bases (SB), base saturation percentage (BSP), cation exchange capacity (CEC), and Al saturation (Alsat) of 2017 contrasting Brazilian soil samples through the association of pXRF and three different algorithms [Cubist, Random forest (RF), and stepwise multiple linear regression (SMLR)]. Soil samples were collected from the surface (SURF) and subsurface (SUB) horizons in seven Brazilian states. The prediction models were generated for the SURF and SUB horizons separately and combined (SURF + SUB dataset). Overall, the best predictions were achieved via Cubist followed by RF. For the pH predictions, the model combining SURF and SUB horizons data presented better results. Satisfactory results were achieved for the predictions of SB (validation R2 = 0.86), BSP (validation R2 = 0.81) and Alsat (R2 = 0.76). Moreover, promising results were obtained for predicting pH (R2 = 0.63). Notably, CaO appeared as the most influential variable for soil property prediction models. Overall, pXRF showed great potential for predicting soil fertility properties for diversified tropical soils with low cost, rapidity, and without chemical waste generation.
ISSN:0016-7061
1872-6259
DOI:10.1016/j.geoderma.2019.114132