Influence of soil physicochemical variables on soybean yield across different soil profiles
DOI:
https://doi.org/10.33837/msj.v9i2.1799Keywords:
random Forest, soil profile, deep soil profile, management depth, relative variable importance, soybean yield, machine learningAbstract
Deep soil fertility management is decisive for the productive potential of soybean because it expands the volume of soil effectively explored by roots and reduces physical and chemical constraints to plant growth. This study aimed to quantify the relative contribution of soil physicochemical attributes, sampled from 0 to 200 cm depth, to the prediction of soybean yield in high-performance fields from the Brazilian Soybean Strategic Committee (CESB). A Random Forest classification model was fitted and evaluated using out-of-bag (OOB) error, class purity–based metrics, SHAP values for model interpretation, and partial dependence curves combined with a purity metric across yield classes. The model showed adequate predictive performance (OOB error ≈ 17.5%), and five predictors were consistently important across yield classes and depths: clay content, cation exchange capacity (CEC), phosphorus, pH and copper. We conclude that management decisions targeted at high yields should consider sufficiency levels by depth layer, integrating liming, gypsum application, fertilization and decompaction practices that maximize the volume of soil that can be effectively explored by roots and the extension of the ideally exploitable profile. The results reinforce the need for deep soil diagnosis, with sampling beyond the traditional 0–20 and 20–40 cm layers, and demonstrate the potential of machine-learning approaches to integrate large volumes of soil data and support more accurate, yield-oriented management recommendations.
References
Alves, L. A., Fontoura, S. M. V., Tiecher, T., Pesini, G., Flores, J. P. M., Filippi, D., Moraes, R. P. de Pias, O. H. de C., & Bayer, C. (2025). Long-term soil acidity dynamics and crop yield response to phosphogypsum and limestone with different reactivities in a no-till Oxisol. European Journal of Agronomy, 171, 127803. DOI: https://doi.org/10.1016/j.eja.2025.127803
Barik, K. C., & Chandel, A. S. (2001). Effect of copper fertilization on plant growth, seed yield, copper and phosphorus uptake in soybean (Glycine max) and their residual availability in Mollisol. Indian Journal of Agronomy, 46(2), 319–326. DOI: https://doi.org/10.59797/ija.v46i2.3266
Barrow, N. J., & Hartemink, A. E. (2023). The effects of pH on nutrient availability depend on both soils and plants. DOI: https://doi.org/10.1007/s11104-023-05960-5
Bartosiewicz, B., Wawer, R., Poręba, L., & Siebielec, G. (2025). The impact of cover crops on soil quality. Current Agronomy, 54(2), 118–128. DOI: https://doi.org/10.2478/cag-2025-0010
Barbosa, J. Z., Motta, A. C. V., Poggere, G., & Prior, S. A. (2025). Winners of the Brazilian soybean yield contest: Climatic, soil, management, and economic factors. Oil Crop Science, 10(4), 294–302. DOI: https://doi.org/10.1016/j.ocsci.2025.07.003
Batista, M. A., Inoue, T. T., Esper Neto, M., & Muniz, A. S. (2018). Princípios de fertilidade do solo, adubação e nutrição mineral. In J. U. T. Brandão Filho, P. S. L. Freitas, L. O. S. Berian, & R. Goto (Eds.), Hortaliças-fruto (pp. 113–162). EDUEM. DOI: https://doi.org/10.7476/9786586383010.0006
Bender, R. R., Haegele, J. W., & Below, F. E. (2015). Nutrient uptake, partitioning, and remobilization in modern soybean varieties. Agronomy Journal, 107(2), 563–573. DOI: https://doi.org/10.2134/agronj14.0435
Berveglieri, A., Imai, N. N., Watanabe, F. S. Y., Tommaselli, A. M. G., Ederli, G. M. P., Araújo, F. F. de, Lupatini, G. C., & Honkavaara, E. (2024). Remote prediction of soybean yield using UAV-based hyperspectral imaging and machine learning models. AgriEngineering, 6(3), 3242–3260. DOI: https://doi.org/10.3390/agriengineering6030185
Bossolani, J. W., Crusciol, C. A. C., Portugal, J. R., Moretti, L. G., Garcia, A., Rodrigues, V. A., Fonseca, M. de C. da, Bernart, L., Vilela, R. G., Mendonça, L. P., & Reis, A. R. dos. (2021). Long-term liming improves soil fertility and soybean root growth, reflecting improvements in leaf gas exchange and grain yield. European Journal of Agronomy, 128, 126308. DOI: https://doi.org/10.1016/j.eja.2021.126308
Caires, E. F., & Guimarães, A. M. (2018). A novel phosphogypsum application recommendation method under continuous no-till management in Brazil. Agronomy Journal, 110(5), 1987–1995. DOI: https://doi.org/10.2134/agronj2017.11.0642
Comitê Estratégico Soja Brasil. (2024). Desafio Nacional de
Máxima Produtividade de Soja. Disponível em: URL: <https://www.cesbrasil.org.br/>
Companhia Nacional de Abastecimento. (2024). Acompanhamento da safra brasileira de grãos (Vol. 11, Safra 2023/24, No. 11, Décimo primeiro levantamento). CONAB. URL: https://www.gov.br/conab
Cox, M. S., Gerard, P. D., Wardlaw, M. C., & Abshire, M. J. (2003). Variability of selected soil properties and their relationships with soybean yield. Soil Science Society of America Journal, 67(4), 1296–1302. DOI: https://doi.org/10.2136/sssaj2003.1296
Crusciol, C. A. C., Marques, R. R., Carmeis Filho, A. C. A., Soratto, R. P., Costa, C. H. M. da, Ferrari Neto, J., Castro, G. S. A., Pariz, C. M., Castilhos, A. M., & Franzluebbers, A. J. (2019). Lime and gypsum combination improves crop and forage yields and estimated meat production and revenue in a variable charge tropical soil. Nutrient Cycling in Agroecosystems, 115(3), 417–432. DOI: https://doi.org/10.1007/s10705-019-10017-0
Esper Neto, M., Lara, L. M., Oliveira, S. M. de, Santos, R. F., Braccini, A. L., Inoue, T. T., & Batista, M. A. (2021). Nutrient removal by grain in modern soybean varieties. Frontiers in Plant Science, 12, 615019. DOI: https://doi.org/10.3389/fpls.2021.615019
Fageria, N. K. (2009). The use of nutrients in crop plants. CRC Press.
Filippi, D., Denardin, L. G. de O., Ambrosini, V. G., Alves, L. A., Flores, J. P. M., Martins, A. P., Pias, O. H. de C., & Tiecher, T. (2021). Concentration and removal of macronutrients by soybean seeds over 45 years in Brazil: A meta-analysis. Revista Brasileira de Ciência do Solo, 45, e0200186. DOI: https://doi.org/10.36783/18069657rbcs20200186
Frene, J. P., Pandey, B. K., & Castrillo, G. (2024). Under pressure: Elucidating soil compaction and its effect on soil functions. Plant and Soil, 502, 267–278. DOI: https://doi.org/10.1007/s11104-024-06573-2
Gazolla-Neto, A., Fernandes, M. C., Vergara, R. O., Gadotti, G. I., & Villela, F. A. (2016). Spatial distribution of the chemical properties of the soil and of soybean yield in the field. Revista Ciência Agronômica, 47(2), 325–333. DOI: https://doi.org/10.5935/1806-6690.20160038
Hanyabui, E., Apori, S. O., Frimpong, K. A., Atiah, K., Abindaw, T., Ali, M., Asiamah, J. Y., & Byalebeka, J. (2020). Phosphorus sorption in tropical soils. AIMS Agriculture and Food, 5(4), 599–616. DOI: https://doi.org/10.3934/agrfood.2020.4.599
Havlin, J. L., Tisdale, S. L., Nelson, W. L., & Beaton, J. D. (2014). Soil fertility and fertilization: An introduction to nutrient management (8th ed.). Pearson Prentice Hall.
Kuhn, M. (2008). Building predictive models in R using the caret package. Journal of Statistical Software, 28(5), 1–26. DOI: https://doi.org/10.18637/jss.v028.i05
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in neural information processing systems (Vol. 30). Curran Associates. DOI: https://doi.org/10.48550/arXiv.1705.07874
Malavolta, E. (1979). ABC da adubação. (4th ed.). Editora Agronômica CERES.
Marin, F. R., Zanon, A. J., Monzon, J. P., Andrade, J. F., Silva, E. H. F. M., Richter, G. L., Antolin, L. A. S., Ribeiro, B. S. M. R., Ribas, G. G., Battisti, R., Heinemann, A. B., & Grassini, P. (2022). Protecting the Amazon forest and reducing global warming via agricultural intensification. Nature Sustainability, 5(12), 1018–1026. DOI: https://doi.org/10.1038/s41893-022-00968-8
Minato, E. A., Brignoli, F. M., Esper Neto, M., Besen, M. R., Cassim, B. M. A. R., Lima, R. S., Tormena, C. A., Inoue, T. T., & Batista, M. A. (2023). Lime and gypsum application to low-acidity soils: Changes in soil chemical properties, residual lime content and crop agronomic performance. Soil and Tillage Research, 234, 105860. DOI: https://doi.org/10.1016/j.still.2023.105860
Moreira, A., & Moraes, L. A. C. (2019). Soybean response to copper applied to two soils with different levels of organic matter and clay. Journal of Plant Nutrition, 42(16), 1857–1867. DOI: https://doi.org/10.1080/01904167.2019.1655039
Moraes, F. A. de, Moreira, S. G., Peixoto, D. S., Silva, J. C. R., Macedo, J. R., Silva, M. M., Silva, B. M., Sanchez, P. A., & Nunes, M. R. (2023). Lime incorporation up to 40 cm deep increases root growth and crop yield in highly weathered tropical soils. European Journal of Agronomy, 144, 126763. DOI: https://doi.org/10.1016/j.eja.2023.126763
Müller, M., Schneider, J.R., Klein, V.A., Silva, E., Junior, J.P.S., Souza, A.M., & Chavarria, G. (2021). Soybean root growth in response to chemical, physical, and biological soil variations. Frontiers in Plant Science, 12, 602569. DOI: https://doi.org/10.3389/fpls.2021.602569
Oliveira, D. B. de, Lacerda, J. J. de J., Cavalcante, A. P., Bezerra, K. G., Silva, A. P. M. da, Miranda, A. C. G., Rambo, T. P., Maschio, R., Andrade, H. A. F. de, Costa, P. M., Sousa, C. A. F. de, Oliveira Júnior, J. O. L., Sagrilo, E., & Souza, H. A. de. (2024). Lime and gypsum rates effects in new soybean areas in the Cerrado of Matopiba, Brazil. Agriculture, 14(7), 1034. DOI: https://doi.org/10.3390/agriculture14071034
Penn, C. J., & Camberato, J. J. (2019). A critical review on soil chemical processes that control how soil pH affects phosphorus availability to plants. Agriculture, 9(6), 120. DOI: https://doi.org/10.3390/agriculture9060120
R Core Team. (2025). R: A language and environment for statistical computing [Computer software]. R Foundation for Statistical Computing. URL: https://www.R-project.org/
Raij, B. van. (2011). Fertilidade do solo e manejo dos nutrientes. International Plant Nutrition Institute.
Rosa, S. F. da, Reinert, D. J., Reichert, J. M., Fleig, F. D., Rodrigues, M. F., & Gelain, N. S. (2018). Propriedades físicas e químicas de um Argissolo sob cultivo de Eucalyptus dunnii Maiden no Pampa Gaúcho. Ciência Florestal, 28(2), 580–590. DOI: https://doi.org/10.5902/1980509832040
Sawchik, J., & Mallarino, A. P. (2008). Variability of soil properties, early phosphorus and potassium uptake, and incidence of soybean sudden death syndrome. Agronomy Journal, 100(5), 1450–1462. DOI: https://doi.org/10.2134/agronj2007.0303
Silva, G. F. da, Luperini, B. C. O., Barcelos, J. P. de Q., Putti, F. F., Mooney, S. J., & Calonego, J. C. (2025). Mechanical chiseling versus root bio-tillage on soil physical quality and soybean yield in a long-term no-till system. Agronomy, 15(5), 1249. DOI: https://doi.org/10.3390/agronomy15051249
Silva, J. M., Almeida, C. X. de, Pena, L. K., Jorge, R. F., Silva, L. R. da, & Duarte, I. R. G. (2022). Estimativa da macroporosidade e microporosidade em função de sistemas de manejo e plantas de cobertura em Latossolo Vermelho cultivado com soja. Research, Society and Development, 11(3), e54411326833. DOI: https://doi.org/10.33448/rsd-v11i3.26833
Sposito, G. (2008). The chemistry of soils (2nd ed.). Oxford University Press.
Teixeira, P. C., Donagemma, G. K., Fontana, A., & Teixeira, W. G. (2017). Manual de métodos de análise de solo (3rd ed.). Embrapa.
Vitantonio-Mazzini, L. N., Gómez, D., Gambin, B. L., Di Mauro, G., Iglesias, R., Costanzi, J., Jobbágy, E. G., & Borrás, L. (2020). Sowing date, genotype choice, and water environment control soybean yields in central Argentina. Crop Science, 61(1), 715–728. DOI: https://doi.org/10.1002/csc2.20315
von Bloh, M., Nóia Júnior, R. de S., Wangerpohl, X., Saltık, A. O., Haller, V., & Kaiser, L. (2023). Machine learning for soybean yield forecasting in Brazil. Agricultural and Forest Meteorology, 341, 109670. DOI: https://doi.org/10.1016/j.agrformet. 2023.109670
Weil, R. R., & Brady, N. C. (2017). The nature and properties of soils (15th ed.). Pearson.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Walter Baida Garcia Coutinho, Verônica Manhães SantClair, Paulo Roberto Cecon, Anderson Rodrigo Silva, Wilhan Valasco Santos, Sebastião Martins Filho, Antônio Policarpo Souza Carneiro, Ana Carolina Campana Nascimento
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
a) The Authors retain the copyright and grant the journal the right to first publication, with the work simultaneously licensed under the Creative Commons Attribution License that allows the sharing of the work with acknowledgment of authorship and initial publication in this journal.
b) Authors are authorized to assume additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (eg, publishing in institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.
c) Authors are allowed and encouraged to publish and distribute their work online (eg in institutional repositories or on their personal page) at any point before or during the editorial process, as this can generate productive changes, as well as increase impact and citation of the published work.
