Proximal sensor-enhanced soil mapping in complex soil-landscape areas of Brazil

作     者：Sérgio H.G.SILVA David C.WEINDORF Wilson M.FARIA Leandro C.PINTO Michele D.MENEZES Luiz R.G.GUILHERME Nilton CURI Sérgio H.G.SILVA;David C.WEINDORF;Wilson M.FARIA;Leandro C.PINTO;Michele D.MENEZES;Luiz R.G.GUILHERME;Nilton CURI

作者机构：Department of Soil ScienceFederal University of LavrasLavras 37200-000(Brazil) Department of Earth and Atmospheric SciencesCentral Michigan UniversityMount Pleasant 48858(USA) 

出 版 物：《Pedosphere》 (土壤圈（英文版）)

年 卷 期：2021年第31卷第4期

页      面：615-626页

核心收录：

学科分类：0818[工学-地质资源与地质工程] 09[农学] 0903[农学-农业资源与环境] 0901[农学-作物学] 090301[农学-土壤学] 

基　　金：BL Allen Endowment in Pedology at Texas Tech University,USA the Brazilian funding agencies National Council for Scientific and Technological Development (CNPq) (Nos.301930/2019-8 and 306389/2019-7) the Coordination for the Improvement of Higher Education Personnel (CAPES),Brazil (No.590-2014) Research Support Foundation of the State of Minas Gerais (FAPEMIG),Brazil (No.PPM 00305-17) for the financial support provided 

主　　题：magnetic susceptibility magnetometer portable X-ray fluorescence spectrometer soil class soil spatial analysis spatial resolution terrain variables 

摘      要：Portable X-ray fluorescence(pXRF) spectrometry and magnetic susceptibility(MS) via magnetometer have been increasingly used with terrain variables for digital soil mapping. However, this methodology is still emerging in many countries with tropical soils. The objective of this study was to use proximal soil sensor data associated with terrain variables at varying spatial resolutions to predict soil classes using the Random Forest(RF) algorithm. The study was conducted on a 316-ha area featuring highly variable soil classes and complex soil-landscape relationships in Minas Gerais State, Brazil. The overall accuracy and Kappa index were evaluated using soils that were classified at 118 sites, with 90 being used for modeling and 28 for validation. Digital elevation models(DEMs) were created at 5-, 10-, 20-, and 30-m resolutions using contour lines from two sources. The resulting DEMs were processed to generate 12 terrain variables. Total Fe, Ti, and SiO_(2) contents were obtained using pXRF, with MS determined via a magnetometer. Soil class prediction was performed using the RF algorithm. The quality of the soil maps improved when using only the five most important covariates and combining proximal sensor data with terrain variables at different spatial resolutions. The finest spatial resolution did not always provide the most accurate maps. The high soil complexity in the area prevented highly accurate predictions. The most important variables influencing the soil mapping were MS, Fe, and Ti. Proximal sensor data associated with terrain information were successfully used to map Brazilian soils at variable spatial resolutions.