• en
  • pt-br
2 results

Digital Soil Mapping Using Machine Learning Algorithms in a Tropical Mountainous Area

Martin Meier, Eliana de Souza, Marcio Rocha Francelino, Elpídio Inácio Fernandes Filho, Carlos Ernesto Gonçalves Reynaud Schaefer


ABSTRACT: Increasingly, applications of machine learning techniques for digital soil mapping (DSM) are being used for different soil mapping purposes. Considering the variety of models available, it is important to know their performance in relation to soil data and environmental variables involved in soil mapping. This paper investigated the performance of eight machine learning algorithms for soil mapping in a tropical mountainous area of an official rural settlement in the Zona da Mata region in Brazil. Morphometric maps generated from […]

Visual Abstract

Local knowledge as related to chemical and physical soil attributes and land use

Luiz Arnaldo Fernandes, Paulo Sérgio do Nascimento Lopes, Santos D'Angelo, Carlos Alberto Dayrell, Regynaldo Arruda Sampaio


The knowledge of farmers about the use of land can assist in soils survels. This study was conducted on the Fazenda Americana, located in northwester Minas Gerais State, Brazil, to relate the local knowledge of the environments to soil chemical and physical attributes and to the Land Use Capacity System, with an Agrarian reform focus. Based on the local knowledge seven environments were identified: baixa, vereda, chapada, tabuleiro, carrasco, tabuleiro misto and espigão (terms roughly translatable as: lowland, palm swamp, […]