Evaluación de la Eficacia de Modelos de Machine Learning para la toma de decisiones basado en Datos Meteorológicos en la producción agrícola.

Nahomi Machuca; Marlon Renne Navia Mendoza; Luis Cedeño Valarezo

doi:10.46480/esj.9.2.232

Authors

Nahomi Machuca Universidad Laica Eloy Alfaro de Manabí
Marlon Renne Navia Mendoza Universidad Técnica de Manabí
Luis Cedeño Valarezo Escuela Superior Politécnica Agropecuaria de Manabí Manuel Félix López, Carrera de Cumputación, Grupo SISCOM

DOI:

https://doi.org/10.46480/esj.9.2.232

Keywords:

agricultural prediction, predictive models, climate, Gradient Boosting, Random Forest

Abstract

Context: Weather is one of the factors that most often influences agricultural production. This study evaluates the effectiveness of Machine Learning models in predicting agricultural yield based on meteorological data. Methodology: A methodology based on OSEMN (Obtain, Scrub, Explore, Model, Interpret) was applied for data processing and model construction, evaluating their
performance and prediction accuracy through statistical metrics. Models based on Gradient Boosting, Random Forest, XGBoost, and SVM techniques were analyzed. Results: The XGBoost model achieved the best predictive performance in terms of accuracy (MAE = 0.1104, RMSE = 0.1367), followed by Gradient Boosting (MAE = 0.1104, RMSE = 0.1370), while SVM showed the lowest predictive capacity in this context (MAE = 0.1223, RMSE = 0.1529). Conclusions: These findings highlight the potential of
decision tree{based approaches to anticipate production changes and improve planning according to weather conditions.

Downloads

Download data is not yet available.

References

Ángel Marqués Gozalbo. (2022). MODELOS PREDICTIVOS DE PRO-DUCCIÓN AGROINDUSTRIAL CON MACHINE LEARNING A PARTIR DE FUENTES DE INFORMACIÓN PÚBLICA [Master en Trasformación Digital en el Sector Agroalimentario y Fores-tal, Universidad de Córdoba]. http://hdl.handle.net/10396/22527

Chlingaryan, A., Sukkarieh, S., & Whelan, B. (2018). Machine learn-ing approaches for crop yield prediction and nitrogen sta-tus estimation in precision agriculture: A review. In Com-puters and Electronics in Agriculture (Vol. 151, pp. 61–69). Elsevier B.V. https://doi.org/10.1016/j.compag.2018.05.012 DOI: https://doi.org/10.1016/j.compag.2018.05.012

Crane Droesch, A. (2018). Machine learning methods for crop yield prediction and climate change impact assessment in agriculture. Environmental Research Letters, 13(11). https://doi.org/10.1088/1748-9326/aae159 DOI: https://doi.org/10.1088/1748-9326/aae159

García-Arteaga, J. J., Zambrano-Zambrano, J. J., Alcivar-Cevallos, R., & Zambrano-Romero, W. D. (2020). Predicción del rendimiento de cultivos agrícolas usando aprendizaje automático. Revista Arbitrada Interdisciplinaria Koinonía, 5(2), 144. https://doi.org/10.35381/r.k.v5i2.1013 DOI: https://doi.org/10.35381/r.k.v5i2.1013

Gómez Arango, A. M. (2024). Predicción del rendimiento de cultivos agrícolas en los cinco corregimientos de la ciudad de Medellín, utilizando modelos de Machine Learning [Maestría en Ciencia de Datos y Analítica, Universidad EA-FIT]. https://repository.eafit.edu.co/server/api/core/bitstreams/f4dcf9c6-a4e4-4252-b66e-b79a53f54d72/content

Hoyos Patiño, J. F., Velásquez Carrascal, B. L., Rico Bautista, D., & García Diaz, N. (2023). Impacto transformador de la inteli-gencia artificial y aprendizaje autónomo en la producción agropecuaria: un enfoque en la sostenibilidad y eficiencia. Revista Formación Estratégica. https://orcid.org/0000-0002-1808-3874

Khaki, S., Pham, H., & Wang, L. (2021). Simultaneous corn and soybean yield prediction from remote sensing data using deep transfer learning. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-89779-z DOI: https://doi.org/10.1038/s41598-021-89779-z

Khalid Talha. (2024). Global_Agriculture_Climate_Impact_Dataset [Data set]. Kaggle.

Liakos, K. G., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A review. In Sensors (Switzerland) (Vol. 18, Issue 8). MDPI AG. https://doi.org/10.3390/s18082674 DOI: https://doi.org/10.3390/s18082674

Morellos, A., Pantazi, X. E., Moshou, D., Alexandridis, T., Whetton, R., Tziotzios, G., Wiebensohn, J., Bill, R., & Mouazen, A. M. (2016). Machine learning based prediction of soil total ni-trogen, organic carbon and moisture content by using VIS-NIR spectroscopy. Biosystems Engineering, 152, 104–116. https://doi.org/10.1016/j.biosystemseng.2016.04.018 DOI: https://doi.org/10.1016/j.biosystemseng.2016.04.018

Oikonomidis, A., Catal, C., & Kassahun, A. (2023). Deep learning for crop yield prediction: a systematic literature review. In New Zealand Journal of Crop and Horticultural Science (Vol. 51, Issue 1, pp. 1–26). Taylor and Francis Ltd. https://doi.org/10.1080/01140671.2022.2032213 DOI: https://doi.org/10.1080/01140671.2022.2032213

Palma, R. P. (2022). Análisis crítico del coeficiente de determina-ción (R 2 ), como indicador de la calidad de modelos li-neales y no lineales. FCNM, 20(2). https://doi.org/http://orcid.org/0000-0001-9934-7343

Santos, R. P., Beko, M., & Leithardt, V. R. Q. (2022). Modelo de Machine Learning em Tempo Real para Agricultura de Precisão In Anais da XXII Escola Regional de Alto Desem-penho da Região Sul,. https://doi.org/10.5753/eradrs.2022.19166 DOI: https://doi.org/10.5753/eradrs.2022.19166

Van Klompenburg, T., Kassahun, A., & Catal, C. (2020). Crop yield prediction using machine learning: A systematic literature review. In Computers and Electronics in Agriculture (Vol. 177). Elsevier B.V. https://doi.org/10.1016/j.compag.2020.105709 DOI: https://doi.org/10.1016/j.compag.2020.105709

Villavicencio Quintero, D., Cabrera Hernández, E., Godo Alonzo, A., & Santana Ching, I. (2024). Sistema para la toma de de-cisiones en el riego de cultivos protegidos basado en aprendizaje de máquina. RIELAC, 44. http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S1815-59282023000300041&lng=es&nrm=iso