Evaluación de modelos de inteligencia artificial para la estimación de la evapotranspiración de referencia en agricultura de precisión bajo clima semiárido.
DOI:
https://doi.org/10.63728/riisds.v11i1.173Resumen
La estimación precisa de la evapotranspiración de referencia (ET₀) es esencial para la programación del riego en sistemas agrícolas de alta eficiencia hídrica. Este estudio compara el desempeño de dos enfoques de modelado, específicamente el algoritmo XGBoost y una red neuronal LSTM, para estimar ET₀ diaria en un entorno semiárido del noroeste de México, utilizando datos meteorológicos derivados del sistema NASA POWER entre enero de 2020 y julio de 2024. Ambos modelos fueron entrenados sobre un conjunto homogéneo de 1,827 días y evaluados mediante métricas estándar, incluyendo MAE, RMSE, R², NSE, MAPE y el coeficiente d de Willmott, con un análisis diferenciado entre las temporadas seca y húmeda. El modelo XGBoost alcanzó un MAE de 0.145 mm día⁻¹ y un R² de 0.983, superando en todos los indicadores al modelo LSTM, el cual mostró mayor error absoluto y variabilidad estacional. El análisis SHAP identificó como variables más influyentes a la radiación solar de onda corta, el déficit de presión de vapor y la velocidad del viento, en coherencia con la teoría agrometeorológica. Además, XGBoost mostró mayor estabilidad frente a eventos extremos y menor sesgo sistemático. Estos resultados posicionan a XGBoost como una herramienta precisa, interpretable y computacionalmente eficiente para su integración en sistemas automatizados de toma de decisiones y plataformas IoT agrícolas. No obstante, se reconocen limitaciones geográficas y metodológicas que sugieren la necesidad de validaciones multirregionales y de explorar arquitecturas híbridas en futuros trabajos.
Citas
Allen, R. G., Pereira, L. S., Raes, D., & Smith, M. (1998). Crop evapotranspiration: Guidelines for computing crop water requirements. Food and Agriculture Organization of the United Nations. https://www.fao.org/4/x0490e/x0490e00.htm
Ayaz, A., Rajesh, M., Singh, S. K., Rehana, S., Lab for Spatial Informatics, International Institute of Information Technology, Hyderabad, India, & National Institute of Water & Atmospheric Research Ltd (NIWA), New Zealand. (2021). Estimation of reference evapotranspiration using machine learning models with limited data. AIMS Geosciences, 7(3), 268–290. https://doi.org/10.3934/geosci.2021016
Başağaoğlu, H., Chakraborty, D., Lago, C. D., Gutierrez, L., Şahinli, M. A., Giacomoni, M., Furl, C., Mirchi, A., Moriasi, D., & Şengör, S. S. (2022). A Review on Interpretable and Explainable Artificial Intelligence in Hydroclimatic Applications. Water, 14(8), 1230. https://doi.org/10.3390/w14081230
Bojorquez Delgado, G. (2025). Conjunto de datos meteorológicos y evapotranspiración de referencia (ET₀_PM) para la agricultura de precisión en el noroeste semiárido de México (2020–2024) [Dataset]. Zenodo. https://doi.org/10.5281/ZENODO.16922140
Bojorquez-Delgado, G., Bojorquez-Delgado, J., & Flores-Rosales, M. A. (2023). Descomposición y análisis temporal del NDVI en un predio agrícola para determinar la salud y variabilidad de cultivos de maíz en Guasave, Sinaloa. Revista Interdisciplinaria de Ingeniería Sustentable y Desarrollo Social, 9(1), 30–43. https://doi.org/10.63728/riisds.v9i1.92
Bour, S., Kayhomayoon, Z., Hassani, F., Ghordoyee Milan, S., Bazrafshan, O., & Berndtsson, R. (2025). Enhancement of standardized precipitation evapotranspiration index predictions by machine learning based on regression and soft computing for Iran’s arid and hyper–arid region. PLOS ONE, 20(3), e0319678. https://doi.org/10.1371/journal.pone.0319678
Chen, X., Wang, S., Gao, H., Huang, J., Shen, C., Li, Q., Qi, H., Zheng, L., & Liu, M. (2022). Comparison of deep learning models and a typical process-based model in glacio-hydrology simulation. Journal of Hydrology, 615, 128562. https://doi.org/10.1016/j.jhydrol.2022.128562
Córdova, M., Carrillo-Rojas, G., Crespo, P., Wilcox, B., & Célleri, R. (2015). Evaluation of the Penman-Monteith (FAO 56 PM) Method for Calculating Reference Evapotranspiration Using Limited Data. Mountain Research and Development, 35(3), 230. https://doi.org/10.1659/MRD-JOURNAL-D-14-0024.1
Djaman, K., & Irmak, S. (2013). Actual Crop Evapotranspiration and Alfalfa- and Grass-Reference Crop Coefficients of Maize under Full and Limited Irrigation and Rainfed Conditions. Journal of Irrigation and Drainage Engineering, 139(6), 433–446. https://doi.org/10.1061/(ASCE)IR.1943-4774.0000559
Dong, J., Xing, L., Cui, N., Zhao, L., Guo, L., Wang, Z., Du, T., Tan, M., & Gong, D. (2024). Estimating reference crop evapotranspiration using improved convolutional bidirectional long short-term memory network by multi-head attention mechanism in the four climatic zones of China. Agricultural Water Management, 292, 108665. https://doi.org/10.1016/j.agwat.2023.108665
Gao, P., Xie, J., Yang, M., Zhou, P., Chen, W., Liang, G., Chen, Y., Han, X., & Wang, W. (2021). Improved Soil Moisture and Electrical Conductivity Prediction of Citrus Orchards Based on IoT Using Deep Bidirectional LSTM. Agriculture, 11(7), 635. https://doi.org/10.3390/agriculture11070635
Ge, J., Zhao, L., Yu, Z., Liu, H., Zhang, L., Gong, X., & Sun, H. (2022). Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model. Plants, 11(15), 1923. https://doi.org/10.3390/plants11151923
Graciano-Obeso, A., López-Atondo, J. U., & Báez-Higuera, J. A. (2024). Influencia de la aplicación de hongos entomopatógenos sobre el rendimiento de tomate en Guasave, Sinaloa. Revista Interdisciplinaria de Ingeniería Sustentable y Desarrollo Social, 10(1), 451–463. https://doi.org/10.63728/riisds.v10i1.58
Helali, J., Mohammadi Ghaleni, M., Mianabadi, A., Asadi Oskouei, E., Momenzadeh, H., Haddadi, L., & Saboori Noghabi, M. (2024). Enhancing references evapotranspiration forecasting with teleconnection indices and advanced machine learning techniques. Applied Water Science, 14(10), 219. https://doi.org/10.1007/s13201-024-02289-x
Irmak, S., Irmak, A., Allen, R. G., & Jones, J. W. (2003). Solar and Net Radiation-Based Equations to Estimate Reference Evapotranspiration in Humid Climates. Journal of Irrigation and Drainage Engineering, 129(5), 336–347. https://doi.org/10.1061/(ASCE)0733-9437(2003)129:5(336)
Irmak, S., Odhiambo, L. O., Specht, J. E., & Djaman, K. (2013). Hourly and daily single and basal evapotranspiration crop coefficients as a function of growing degree days, days after emergence, leaf area index, fractional green canopy cover, and plant phenology for soybean. Transactions of the ASABE, 56(5), 1785–1803. https://doi.org/10.13031/trans.56.10219
Jagtap, S. T., Phasinam, K., Kassanuk, T., Jha, S. S., Ghosh, T., & Thakar, C. M. (2022). Towards application of various machine learning techniques in agriculture. Materials Today: Proceedings, 51, 793–797. https://doi.org/10.1016/j.matpr.2021.06.236
Jia, W., Zhang, Y., Wei, Z., Zheng, Z., & Xie, P. (2023). Daily reference evapotranspiration prediction for irrigation scheduling decisions based on the hybrid PSO-LSTM model. PLOS ONE, 18(4), e0281478. https://doi.org/10.1371/journal.pone.0281478
Lepot, M., Aubin, J.-B., & Clemens, F. (2017). Interpolation in Time Series: An Introductive Overview of Existing Methods, Their Performance Criteria and Uncertainty Assessment. Water, 9(10), 796. https://doi.org/10.3390/w9100796
Li, M., Zhou, Q., Han, X., & Lv, P. (2024). Prediction of reference crop evapotranspiration based on improved convolutional neural network (CNN) and long short-term memory network (LSTM) models in Northeast China. Journal of Hydrology, 645, 132223. https://doi.org/10.1016/j.jhydrol.2024.132223
Liang, Y., Feng, D., Sun, Z., & Zhu, Y. (2023). Evaluation of Empirical Equations and Machine Learning Models for Daily Reference Evapotranspiration Prediction Using Public Weather Forecasts. Water, 15(22), 3954. https://doi.org/10.3390/w15223954
Liu, D., Wang, Z., Wang, L., Chen, J., Li, C., & Shi, Y. (2024). Improved remote sensing reference evapotranspiration estimation using simple satellite data and machine learning. Science of The Total Environment, 947, 174480. https://doi.org/10.1016/j.scitotenv.2024.174480
Liyew, C. M., Ferraris, S., Di Nardo, E., & Meo, R. (2025). A review of feature selection methods for actual evapotranspiration prediction. Artificial Intelligence Review, 58(10), 292. https://doi.org/10.1007/s10462-025-11298-4
Matos, K. A., Bowen, G. J., Good, S. P., & Allen, S. T. (2025). Evapotranspiration Partitioning Across US Ecoregions: A Multi‐Site Study Using Field Stable‐Isotope Observations. Geophysical Research Letters, 52(14), e2025GL115367. https://doi.org/10.1029/2025GL115367
Moratiel, R., Bravo, R., Saa, A., Tarquis, A. M., & Almorox, J. (2020). Estimation of evapotranspiration by the Food and Agricultural Organization of the United Nations (FAO) Penman–Monteith temperature (PMT) and Hargreaves–Samani (HS) models under temporal and spatial criteria – a case study in Duero basin (Spain). Natural Hazards and Earth System Sciences, 20(3), 859–875. https://doi.org/10.5194/nhess-20-859-2020
Mushtaq, H., Akhtar, T., Hashmi, M. Z. U. R., Masood, A., & Saeed, F. (2024). Hydrologic interpretation of machine learning models for 10-daily streamflow simulation in climate sensitive upper Indus catchments. Theoretical and Applied Climatology, 155(6), 5525–5542. https://doi.org/10.1007/s00704-024-04932-8
Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I—A discussion of principles. Journal of Hydrology, 10(3), 282–290.
Noor, M. N., Yahaya, A. S., Ramli, N. A., & Al Bakri Abdullah, M. M. (2015). Filling the Missing Data of Air Pollutant Concentration Using Single Imputation Methods. Applied Mechanics and Materials, 754–755, 923–932. https://doi.org/10.4028/www.scientific.net/AMM.754-755.923
Roy, D. K., Sarkar, T. K., Kamar, S. S. A., Goswami, T., Muktadir, M. A., Al-Ghobari, H. M., Alataway, A., Dewidar, A. Z., El-Shafei, A. A., & Mattar, M. A. (2022). Daily Prediction and Multi-Step Forward Forecasting of Reference Evapotranspiration Using LSTM and Bi-LSTM Models. Agronomy, 12(3), 594. https://doi.org/10.3390/agronomy12030594
Sarkar, S. S., Bedi, J., & Jain, S. (2025). A deep learning based framework for enhanced reference evapotranspiration estimation: Evaluating accuracy and forecasting strategies. Scientific Reports, 15(1), 15136. https://doi.org/10.1038/s41598-025-99713-2
Sharafi, S., & Mohammadi Ghaleni, M. (2024). Revealing accuracy in climate dynamics: Enhancing evapotranspiration estimation using advanced quantile regression and machine learning models. Applied Water Science, 14(7), 162. https://doi.org/10.1007/s13201-024-02211-5
Soylu, M. E., Lenters, J. D., Istanbulluoglu, E., & Loheide, S. P. (2012). On evapotranspiration and shallow groundwater fluctuations: A Fourier‐based improvement to the White method. Water Resources Research, 48(6), 2011WR010964. https://doi.org/10.1029/2011WR010964
Tausif, M., Iqbal, M. W., Bashir, R. N., AlGhofaily, B., Elyassih, A., & Khan, A. R. (2025). Federated learning based reference evapotranspiration estimation for distributed crop fields. PLOS ONE, 20(2), e0314921. https://doi.org/10.1371/journal.pone.0314921
Willmott, C. J. (1981). ON THE VALIDATION OF MODELS. Physical Geography, 2(2), 184–194. https://doi.org/10.1080/02723646.1981.10642213
Wu, T., Zhang, W., Jiao, X., Guo, W., & Hamoud, Y. A. (2020). Comparison of five Boosting-based models for estimating daily reference evapotranspiration with limited meteorological variables. PLOS ONE, 15(6), e0235324. https://doi.org/10.1371/journal.pone.0235324
Xu, X., Du, Z., Bai, Z., Wang, S., Wang, C., & Li, D. (2023). Fault diagnosis method of dissolved oxygen sensor electrolyte loss based on impedance measurement. Computers and Electronics in Agriculture, 212, 108123. https://doi.org/10.1016/j.compag.2023.108123
Yan, X., Yang, N., Ao, R., Mohammadian, A., Liu, J., Cao, H., & Yin, P. (2023). Deep learning for daily potential evapotranspiration using a HS-LSTM approach. Atmospheric Research, 292, 106856. https://doi.org/10.1016/j.atmosres.2023.106856
Yang, D., Yang, S., Huang, J., Zhang, S., Zhang, S., Zhang, J., & Bai, Y. (2025). Improving time upscaling of instantaneous evapotranspiration based on machine learning models. Big Earth Data, 9(1), 127–154. https://doi.org/10.1080/20964471.2024.2423431
Yin, J., Deng, Z., Ines, A. V. M., Wu, J., & Rasu, E. (2020). Forecast of short-term daily reference evapotranspiration under limited meteorological variables using a hybrid bi-directional long short-term memory model (Bi-LSTM). Agricultural Water Management, 242, 106386. https://doi.org/10.1016/j.agwat.2020.106386
Zhou, H., Shao, J., Liu, H., Du, Z., Zhou, L., Liu, R., Bernhofer, C., Grünwald, T., Dušek, J., Montagnani, L., Tagesson, T., Black, T. A., Jassal, R., Woodgate, W., Biraud, S., Varlagin, A., Mammarella, I., Gharun, M., Shekhar, A., … Zhou, X. (2021). Relative importance of climatic variables, soil properties and plant traits to spatial variability in net CO2 exchange across global forests and grasslands. Agricultural and Forest Meteorology, 307, 108506. https://doi.org/10.1016/j.agrformet.2021.108506
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2025 Revista Interdisciplinaria de Ingeniería Sustentable y Desarrollo Social
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
