EVALUATION OF MACHINE LEARNING MODELS FOR BORON PREDICTION IN ANDISOL SOILS OF NARIÑO-COLOMBIA

David Álvarez Sánchez, Xilena López Estrella, Eduar Manso Ordoñez, Laura López Rivera, Jeison Rodriguez Valenzuela

Abstract


Background. The southern region of Nariño in Colombia has a strong agricultural vocation. However, it has been identified that the technology associated with the recommendation of fertilization especially in microelements in the soil is limited, which generates conflicts in production. This situation demands a different and innovative approach to address these challenges. That is why this research uses the predictive capacity of the machine learning (ML) approach. Objective. To explore the application of ML tools for the prediction of Boron levels in Andisols soils of Nariño has been explored and identifying the most efficient algorithm. Methodology. A total of 1,067 soil samples collected in various fields of five municipalities in the southern subregion of the department were used, where the supervised learning models, Random Forest (RF), K-Nearest Neighbors (K-NN), Support Vector Machine (SVM) and Naive Bayes (NB) were evaluated. Results. The results were analyzed using precision tests, kappa coefficient and confusion matrix. Conclusion. The RF algorithm demonstrated the best performance in estimating Boron levels, achieving 78% accuracy, outperforming SVM (75%), K-NN (69%) and NB (35%). Implications. These results allow for improved decision-making regarding fertilization and micronutrient management in the soil, in order to improve soil quality and therefore crop yield.

Keywords


Prediction; algorithms; supervised learning; sustainable agriculture; soil nutrition; agroecosystems.

Full Text:

PDF

References


Abbas, F., Afzaal, H., Farooque, A.A. and Tang, S., 2020. Crop yield prediction through proximal sensing and machine learning algorithms. Agronomy, 10(7), p.1046. https://doi.org/10.3390/agronomy10071046

Abraham, S., Huynh, C. and Vu, H., 2020. Classification of Soils into Hydrologic Groups Using Machine Learning. Data, 5(1), pp. 2-11. https://doi.org/10.3390/data5010002

Acuña, A.M. and Molina, P.E.C., 2018. Desempeño funcional del boro en las plantas. UDO Agrícola, 7(1), pp. 1-14. https://www.bioline.org.br/pdf?cg07002

Álvarez Sánchez, D.E., Gómez, E. and Ordoñez, H., 2019. Tipología de fincas productoras de arveja (Pisum sativum L.) en la subregión Sur de Nariño, Colombia. Ciencia y Tecnología Agropecuaria, 20(3), pp. 659–677. https://doi.org/10.21930/rcta.vol20_num3_art:1593

Álvarez Sánchez, D.E., Arévalo Rodríguez, A., Benavides Martínez, I.F., Salazar González, C. and Betancourth García, C., 2023. Use of Trained Convolutional Neural Networks for Analysis of Symptoms Caused by Botrytis fabae Sard. Revista de Ciencias Agrícolas, 40(1), pp. e1198. https://doi.org/10.22267/rcia.20234001.198

Alzate, J.G., Benavides-Cardona, C.A. and Sánchez, D.E.Á., 2022. Aplicación de Urea, DAP y KCl sobre almácigos de café (Coffea arabica L.) de la variedad Castillo. Revista de Investigación Agraria y Ambiental, 13(1), pp. 35-55. https://doi.org/10.22490/21456453.4297

Apráez, E., Gálvez, A. and Apraez, J., 2019. Factores edafoclimáticos en la producción y calidad del pasto Saboya (Holcus lanatus L.) en el Altiplano de Nariño. Revista de Ciencias Agrícolas, 36(1), pp. 16-32. https://doi.org/10.22267/rcia.193601.95

Aworka, R., Cedric, L.S., Adoni, W.Y.H., Zoueu, J.T., Mutombo, F.K., Kimpolo, C.L.M., Nahhal, T. and Krichen, M., 2022. Agricultural decision system based on advanced machine learning models for yield prediction: Case of East African countries. Smart Agricultural Technology, 2, pp. 100-148. https://doi.org/10.1016/j.atech.2022.100048

Barbier, M., 2019. Biodisponibilidad de boro derivado de tres fuentes de boro en dos tipos de suelo. Palmas, 40 (Especial), pp. 158-167. https://publicaciones.fedepalma.org/index.php/palmas/article/view/13045

Bayat, H., Asghari, S., Rastgou, M. and Sheykhzadeh, G.R., 2020. Estimating Proctor parameters in agricultural soils in the Ardabil plain of Iran using support vector machines, artificial neural networks and regression methods. Catena, 189, pp. 10-44. https://doi.org/10.1016/j.catena.2020.104467.

Becerra-Rondón, A., Ducati, J. and Haag, R., 2022. Satellite-based estimation of NO2 concentrations using a machine-learning model: A case study on Rio Grande do Sul, Brazil. Atmósfera, 37, pp. 175- 190. https://doi.org/10.20937/ATM.53116

Bouasria, A., Namr, K.I., Rahimi, A. and Ettachfini, E.M., 2020. Estimate soil organic matter from remote Sensing data by using statistical predictive models. In International Conference on Advanced Intelligent Systems for Sustainable Development, pp. 1106-1115. https://doi.org/10.1007/978-3-030-90633-7_98

Camacho, Y.M., Acosta, D.F., López, C.A., Cely, G.E. and Serrano, P.A., 2020. Transformación electroquímica de un Andisol en relación con la dinámica del fósforo. Biotecnología en el Sector Agropecuario y Agroindustrial, 18(2), pp. 94-102. https://doi.org/10.18684/BSAA(18)94-102

Castro-Rincón, E., Cardona-Iglesias, J.L., Hernández-Oviedo, F., Valenzuela-Chiran, M. and Avellaneda-Avellaneda, Y., 2019. Evaluación de tres cultivares de Lolium perenne L. con vacas lecheras, en el trópico alto de Nariño-Colombia. Pastos y Forrajes, 42(2), pp. 161-170. https://www.redalyc.org/journal/2691/269161217009/html/

Chen, S., Webb, G.I., Liu, L. and Ma, X., 2020. A novel selective naïve Bayes algorithm. Knowledge- Based Systems, 192, pp. 10-53. https://doi.org/10.1016/j.knosys.2019.105361

Choi, E.Y., Park, H.I., Ju, J.H. and Yoon, Y.H., 2015. Boron availability alters its distribution in plant parts of tomato. Horticulture, Environment, and Biotechnology, 56(2), pp. 145-151. https://doi.org/10.1007/s13580-015-0044-y

Culchac, L.Y., Estrada, J.S. and Ordóñez, H.R., 2021. Cuantificación de bacterias nitrificantes en un suelo Typic melanudands en tres condiciones de uso de suelo en Pasto, Nariño, Colombia. Ciencia y Tecnología Agropecuaria, 22(2), pp. 1-15. https://doi.org/10.21930/rcta.vol22_num2_art:1424

El-Sayed, M.A., Abd-Elazem, A.H., Moursy, A.R.A., Mohamed, E.S., Kucher, D.E. and Fadl, M.E., 2023. Integration Vis-NIR spectroscopy and artificial intelligence to predict some soil parameters in arid region: A case study of Wadi Elkobaneyya, South Egypt. Agronomy, 13(3), pp. 35-49. https://doi.org/10.3390/agronomy13030935

Ennaji, O., Vergütz, L. and El Allali, A., 2023. Machine learning in nutrient management: A review. Artificial Intelligence in Agriculture, 9, pp. 1-11. https://doi.org/10.1016/j.aiia.2023.06.001

Galupino, J. and Dungca, J., 2022. Machine learning models to generate a subsurface soil profile: A case of Makati City, Philippines. GEOMATE Journal, 23(95), pp. 57-64. https://geomatejournal.com/geomate/article/view/3029

Instituto Geográfico Agustín Codazzi, 2004. Estudio general de suelos y zonificación de tierras departamento de Nariño. IGAC. 2017. Guía de muestreo. https://antiguo.igac.gov.co

Ismaili, M., Krimissa, S., Namous, M., Htitiou, A., Abdelrahman, K., Fnais, M. S., Lhissou, R., Eloudi, H., Faouzi, E. and Benabdelouahab, T., 2023. Assessment of soil suitability using Machine Learning in arid and semi-arid regions. Agronomy, 13(1), pp. 165-178. https://doi.org/10.3390/agronomy13010165

Kaushik, K., Bhardwaj, A., Dahiya, S., Maashi, M. S., Al Moteri, M., Aljebreen, M. and Bharany, S., 2022. Multinomial Naive Bayesian classifier framework for systematic analysis of smart IoT devices. Sensors, 22(19), pp. 1-16. https://doi.org/10.3390/s22197318

Kebonye, N.M., Agyeman, P.C. and Biney, J.K.M., 2023. Optimized modelling of country wide soil organic carbon levels via an interpretable decision tree. Smart Agricultural Technology, 3, pp. 100-106. https://doi.org/10.1016/j.atech.2022.100106

Lagos, J. and Huertas, J., 2019. Efectos de una enmienda orgánica sobre las propiedades fisicoquímicas de un Andisol, en Túquerres, Nariño, Colombia. Agro sur, 47(3), pp.39-54. https://doi.org/10.4206/agrosur 2019.v47n3-05

Malik, P., Sengupta, S. and Jadon, J.S., 2021. Comparative analysis of soil properties to predict fertility and crop yield using Machine Learning Algorithms. 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), pp.1004-1007. https://doi.org/10.1109/Confluence51648.2021.9377147

Mallah, S., Delsouz Khaki, B., Davatgar, N., Scholten, T., Amirian-Chakan, A., Emadi, M., Kerry, R., Mosavi, A.H. and Taghizadeh-Mehrjardi, R., 2022. Predicting soil textural classes using Random Forest models: Learning from imbalanced dataset. Agronomy, 12(11), pp. 1-16. https://doi.org/10.3390/agronomy12112613

Marcillo-Paguay, C.A., Benavides-Cardona, C.A., Ramos-Zambrano, H.S. and Romero, J.V., 2022. Respuesta agronómica y económica de papa (Solanum tuberosum subsp. Andigena) a la fertilización diferencial en cuatro ambientes de Nariño, Colombia. Revista Colombiana de Ciencias Hortícolas, 16(2), pp. 1-11. https://doi.org/10.17584/rcch.2022v16i2.13559

Mason-Jones, K., Schmücker, N. and Kuzyakov, Y., 2018. Contrasting effects of organic and mineral nitrogen challenge the N-Mining Hypothesis for soil organic matter priming. Soil Biology and Biochemistry, 124, pp. 38-46. https://doi.org/10.1016/j.soilbio.2018.05.024

Medina, M., Arismendi, J. and Cerón-Muñoz, M., 2019. Descripción de las relaciones entre parámetros químicos en suelos de fincas lecheras del norte de Antioquia, Colombia. Livestock Research for Rural Development, 31(7), pp.#102. http://www.lrrd.org/lrrd31/7/ceron31102.html

Meshram, V., Patil, K., Hanchate, D. and Ramkteke, S.D., 2021. Machine learning in agriculture domain: A state-of-art survey. Artificial Intelligence in the Life Sciences, 1, pp. 1-11. https://doi.org/10.1016/j.ailsci.2021.100010

Mohd, M., Hashim, N., Abd, S. and Lasekan, O., 2022. Characterisation of pineapple cultivars under different storage conditions using infrared thermal imaging coupled with Machine Learning Algorithms. Agriculture, 12(7), pp.1013. https://doi.org/10.3390/agriculture12071013

Novoa, M. A., Miranda, D., & Melgarejo, L., 2018. Efecto de las deficiencias y excesos de fósforo, potasio y boro en la fisiología y el crecimiento de plantas de aguacate (Persea americana, cv. Hass). Revista Colombiana de Ciencias Hortícolas, 12(2), pp. 293-307. http://repositorio.uptc.edu.co/handle/001/2932

Pant, H., Lohani, M.C. and Bhatt, A., 2019. Impact of physico-chemical properties for soils type classification of OAK using different machine learning techniques. International Journal of Computer Applications, 177(17), pp. 38-44. http://doi.org/10.5120/ijca2019919617

Rajkovi?, D., Marjanovi? Jeromela, A., Pezo, L., Lon?ar, B., Zanetti, F., Monti, A., & Kondi? Špika, A., 2021. Yield and quality prediction of winter rapeseed—Artificial neural network and random forest models. Agronomy, 12(1), p.58. https://doi.org/10.3390/agronomy12010058

Ramírez, C.A., 2020. Aplicación del Machine Learning en agricultura de precisión. Revista CINTEX, 25(2), pp. 14-27. https://doi.org/10.33131/24222208.356

Rodríguez-Rodríguez, D.M., Checa-Coral, Ó.E., Ruiz-Eraso, H., Muriel-Figueroa, J. and Yepes- Chamorro, B., 2022. Niveles de fertilización con calcio, magnesio y azufre en genotipos de arveja voluble (Pisum sativum L.) en Nariño. Actualidad & Divulgación Científica, 25(2), pp. 1-8. https://doi.org/10.31910/rudca.v25.n2.2022.1847

Soil Survey Staff., 1999. Soil taxonomy: A basic system of soil classification for making and interpreting soil surveys. 2nd edition. Natural Resources Conservation Service. U.S. Department of Agriculture Handbook 436. https://doi.org/10.1111/j.1475-2743.2001.tb00008.x

Volverás-Mambuscay, B., Merchancano-Rosero, J.D., Campo-Quesada, J.M. and López-Rendón, J.F., 2020. Propiedades físicas del suelo en el sistema de siembra en wachado en Nariño, Colombia. Agronomía Mesoamericana, 31(3), pp. 743-760. https://doi.org/10.15517/am.v31i3.39233

Yepes, J., Oré, G., Alcântara, M.S., Hernandez-Figueroa, H.E. and Teruel, B., 2022. Classification of sugarcane yields according to soil fertility properties using supervised machine learning methods. Engenharia Agrícola, 42(5), pp. 1-9. https://doi.org/10.1590/1809-4430- eng.agric.v42n5e20210239/2022

Zhang, J., He, Y., Yuan, L., Liu, P., Zhou, X., & Huang, Y.,2019. Machine learning-based spectral library for crop classification and status monitoring. Agronomy, 9(9), p.496. https://doi.org/10.3390/agronomy9090496

Zhu, J., Jin, X., Li, S., Han, Y. and Zheng, W., 2022. Prediction of soil available Boron content in Visible- Near-Infrared hyperspectral based on different preprocessing transformations and characteristic wavelengths modeling. Computational Intelligence and Neuroscience, 20(22), pp.1- 16. https://doi.org/10.1155/2022/9748257

Zolfaghari, M., Moradi, M., Moradi, G. and Taghizadeh-Mehrjardi, R., 2023. Machine Learning models for prediction of soil properties in the Riparian Forests. Land, 12(1), pp. 32. https://doi.org/10.3390/land12010032




URN: http://www.revista.ccba.uady.mx/urn:ISSN:1870-0462-tsaes.v28i1.55959

DOI: http://dx.doi.org/10.56369/tsaes.5595

Bookmark and Share


Copyright (c) 2025 Laura Lopez Rivera

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.