Mapping soil drainage classes: Comparing expert knowledge and machine learning strategies

• DOI: 10.1016/j.soilad.2024.100028
• Publication Date: 2024-12-22T00:50:18Z
• Authors: Danilo César de M...; Nélida E.Q. Silvero; Bradley A. Miller; Nicolas Augusto R...; Jorge Tadeu Fim R...; Bruno dos Anjos B...; Gustavo Vieira Ve...; Jean Jesus Macedo...; Renan Falcioni; Marcos Rafael Nanni; Marcelo Rodrigo A...; Elpídio Inácio Fe...; Uemeson José dos ...; José Alexandre Me...
• Keywords: Ferralsol; DegreeDisciplines::Social and Behavioral Sciences::Geography::Remote Sensing; Environmental covariates; DegreeDisciplines::Physical Sciences and Mathematics::Earth Sciences::Soil Science; Remote sensing; Soil color; Predictive modeling

Soil drainage is an essential factor that influences plant growth and various biophysical processes, such as nutrient cycling and greenhouse gas fluxes. Therefore, soil drainage maps are fundamental tools for managing crops, forests, and the environment. This study compared two approaches to mapping soil drainage classes in the state of São Paulo, Brazil, using geographic information systems (GIS). The first approach employed expert knowledge (EK) to develop a simple model based on soil color and texture, while the second used machine learning (ML) with an extensive set of covariates and a decision tree algorithm. To evaluate the full, operational implementation of soil mapping, this study assessed the two approaches in terms of accuracy, labor efficiency, transferability, interpretability, and agreement/disagreement statistical methods. In terms of accuracy, the ML-based strategy showed greater agreement with the reference map (53 %) compared to the EK approach (50 %). However, the EK strategy was more time- and resource-efficient, as well as being more transferable and interpretable due to the simplicity of its rules based on soil properties. Given its higher interpretability and ease of application, the EK approach was recommended as the most suitable for operational soil drainage mapping in tropical environments. ; This article is published as de Mello, Danilo César, Nélida EQ Silvero, Bradley A. Miller, Nicolas Augusto Rosin, Jorge Tadeu Fim Rosas, Bruno dos Anjos Bartsch, Gustavo Vieira Veloso et al. "Mapping Soil Drainage Classes: Comparing Expert Knowledge and Machine Learning Strategies." Soil Advances (2024): 100028. doi:10.1016/j.soilad.2024.100028. ; This research was funded by the National Council for Scientific and Technological Development (CNPq): Programa de Apoio à Fixação de Jovens Doutores no Brasil, grant number 168180/2022 −7; Fundação Araucária: CP 19/2022—Jovens Doutores; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), grant number 001; Fundação de Amparo à Pesquisa do ...