Título:	A novel methodological framework for predicting and mapping agriculture-related soil attributes using Euclidean distance, regular grids, and machine learning algorithms.
Autoria:	VELOSO, G. V. MELLO, D. C. de FERNANDES-FILHO, E. I. SOUZA, C. M. P. de SILVA, L. A. P. da ESPIRITO SANTO, M. M. VASQUES, G. M. COELHO, M. R. DEMATTÊ, J. A. M.
Afiliação:	GUSTAVO VIEIRA VELOSO, UNIVERSIDADE FEDERAL DE VIÇOSA; DANILO CÉSAR DE MELLO, UNIVERSIDADE DE SÃO PAULO; ELPÍDIO INÁCIO FERNANDES-FILHO, UNIVERSIDADE FEDERAL DE VIÇOSA; CRISTIANO MARCELO PEREIRA DE SOUZA, UNIVERSIDADE FEDERAL DO VALE DO SÃO FRANCISCO; LUCAS AUGUSTO PEREIRA DA SILVA, UNIVERSIDADE ESTADUAL DA PARAÍBA; MARIO MARCOS ESPIRITO SANTO, UNIVERSIDADE ESTADUAL DE MONTES CLAROS; GUSTAVO DE MATTOS VASQUES, CNPS; MAURICIO RIZZATO COELHO, CNPS; JOSÉ A. M. DEMATTÊ, UNIVERSIDADE DE SÃO PAULO.
Ano de publicação:	2026
Referência:	PLOS One, v. 21, n. 5, e0343624, 2026.
Conteúdo:	Recent advances in statistical and machine learning (ML) methods have improved the prediction of soil attributes at fine spatial scales, yet the comparative performance and reliability of these techniques remain unclear. This study compared Ordinary Kriging (OK), Inverse Distance Weighting (IDW), and ML algorithms in predicting and spatializing soil attributes, while also evaluating prediction uncertainty and com- putational processing time. Conducted in Minas Gerais State (Brazil), the analysis used Euclidean distance based predictors derived from X-Y coordinates and regular grids with 5, 7, and 10 divisions. Soil attribute maps (CEC, phosphorus, sand, and clay) were generated using OK, IDW, Random Forest (RF), Cubist, Support Vector Machine (SVM), and Earth. Model performance was assessed using R2, RMSE, MAE, and the coefficient of variation. IDW and OK showed the lowest predictive accuracy (R2 = 0.52–0.58), whereas ML methods, especially RF and SVM achieved superior performance (R2 = 0.62–0.70). Among ML algorithms, Earth performed worst, while RF produced the highest accuracy for all attributes except sand, for which SVM performed best. Processing time was shortest for IDW, followed by OK; among ML models, Earth was fastest, followed by RF, SVM, and Cubist. Larger regular grids improved ML prediction and spatialization but increased computational cost. ML methods thus outperform traditional geostatistical interpolators, benefiting from the use of numerous covariates and flexible algorithmic structures, although requiring greater computational time. These findings demonstrate the robustness and practical potential of ML approaches for soil attribute mapping.
Thesagro:	Mapa
Palavras-chave:	Machine Learning Atributos do solo Krigagem ordinária Ponderação pelo inverso da distância Soil attributes Ordinary kriging Inverse distance weighting
Digital Object Identifier:	https://doi.org/10.1371/journal.pone.0343624
Tipo do material:	Artigo de periódico
Acesso:	openAccess
Aparece nas coleções:	Artigo em periódico indexado (CNPS)