MACHINE LEARNING MODELS (MLP, RANDOM FOREST, LIGHTGBM) FOR DAILY ET₀ ESTIMATION WITH LIMITED DATA IN HUMID MEDITERRANEAN REGION (JIJEL) ALGERIA
DOI:
https://doi.org/10.18623/rvd.v23.n3.4267Palavras-chave:
Reference Evapotranspiration, FAO-56, LightGBM, Multi-Layer Perceptron, Random Forest, Jijel, AlgeriaResumo
An estimativa precisa da evapotranspiração de referência (ET₀) é essencial para o planejamento eficiente da irrigação e a gestão sustentável dos recursos hídricos, especialmente em regiões climaticamente heterogêneas. Este estudo avaliou três modelos de aprendizado automático —Perceptrão Multicamada (MLP), Random Forest (RF) e LightGBM— para prever a ET₀ diária FAO-56 Penman–Monteith na região mediterrânea húmida de Jijel (nordeste da Argélia). Foram utilizados dados meteorológicos diários de dez estações (2000–2024) com seis variáveis: temperatura do ar, humidade relativa, velocidade do vento, duração da insolação, radiação solar e défice de pressão de vapor. O desempenho foi medido com métricas estatísticas em conjuntos de treino, validação e teste. Todos os modelos alcançaram alta precisão (R² > 0,97). O RF obteve o melhor desempenho no treino (R² = 0,997; RMSE ≈ 0,09 mm dia⁻¹), mas mostrou leve sobreajuste no teste. O MLP apresentou a melhor generalização (R² teste = 0,983; RMSE = 0,21 mm dia⁻¹; NSE = 0,983), seguido de perto pelo LightGBM (R² teste ≈ 0,980). A análise de tendências não detectou alterações significativas na ET₀ anual (p = 0,907). Os resultados confirmam a robustez dos enfoques de machine learning, especialmente MLP e LightGBM, para estimar ET₀ de forma fiável em ambientes mediterrâneos húmidos.
Referências
Abdullah, S. S., Malek, M. A., Abdullah, N. S., Kisi, O., & Yap, K. S. (2015). Extreme learning machines: A new approach for prediction of reference evapotranspiration. Journal of Hydrology, 527, 184–195. https://doi.org/10.1016/j.jhydrol.2015.04.073
Acharki, S., Raza, A., Vishwakarma, D. K., ET AL. (2025). Comparative assessment of empirical and hybrid machine learning models for estimating daily reference evapotranspiration in sub-humid and semi-arid climates. Scientific Reports, 15, 2542. https://doi.org/10.1038/s41598-024-83859-6
Achite, M., Jehanzaib, M., Sattari, M. T., Toubal, A. K., Elshaboury, N., Wałęga, A., Krakauer, N., Yoo, J.-Y., & Kim, T.-W. (2022). Modern techniques to modeling reference evapotranspiration in a semiarid area are based on ANN and GEP models. Water, 14(1210). https://doi.org/10.3390/w14081210
Agrawal, Y., Kumar, M., Ananthakrishnan, S., Kumarapuram, G. (2022). Evapotranspiration modeling using different tree based ensembled machine learning algorithm. Water Resources Management, 36(3), 1025–1042. https://doi.org/10.1007/s11269-022-03067-7
Al Hasani, A. A. J. & Shahid, S. (2024). Development of radiation- and temperature-based empirical models for accurate daily reference evapotranspiration estimation in Iraq. Stochastic Environmental Research and Risk Assessment, 38(8), 3127–3148. https://doi.org/10.1007/s00477-024-02736-w
Allen, R. G., Pereira, L. S., Raes, D., Smith, M. (1998). Crop evapotranspiration - Guidelines for computing crop water requirements - FAO Irrigation and drainage paper 56. FAO. https://www.fao.org/4/x0490e/x0490e00.htm
Aly, M. S., Darwish, S. M., & Aly, A. A. (2024). High-performance machine learning approach for reference evapotranspiration estimation. Stochastic Environmental Research and Risk Assessment, 38, 689–713. https://doi.org/10.1007/s00477-023-02594-y
Boukhali, Y., Kabbaj, M. N., Benbrahim, M. (2025). Evapotranspiration estimation using deep learning models for robust sensor performance. Franklin Open, 11, 100335. https://doi.org/10.1016/j.fraope.2025.100335
Bouregaa T. (2025). Trends in climatic variables and machine learning-based reference evapotranspiration predictions in key cereal-producing regions of Algeria. Theoretical and Applied Climatology 156, 351. https://doi.org/10.1007/s00704-025-05561-5
Boutellis, T., Bouchair, A. (2022). Predictive capacity analysis for outdoor thermal comfort assessments: A case study of Jijel City, Algeria. Journal of Advanced Research in Fluid Mechanics and Thermal Sciences 98(1), 18–41. https://doi.org/10.37934/arfmts.98.1.1841
Chang, Y., Zhang, C., Huang, J., Chang, H., Wang, C. (2025). Machine learning for reference crop evapotranspiration modeling: a state-of-the-art review and future directions. Agronomy, 15, 2038. https://doi.org/10.3390/agronomy15092038
Chen, Z., Zhu, Z., Jiang, H., & Sun, S. (2020). Estimating daily reference evapotranspiration based on limited meteorological data using deep learning and classical machine learning methods. Journal of Hydrology, 591, 125286. https://doi.org/10.1016/j.jhydrol.2020.125286
Di Nunno, F., Granata, F. (2023). Future trends in reference evapotranspiration in Sicily based on CORDEX data and machine learning algorithms. Agricultural Water Management, 280, 108232. https://doi.org/10.1016/j.agwat.2023.108232
D-MAPS.COM. (2024). Free maps of Jijel Province, Algeria (online cartographic resources). https://d-maps.com
Elbeltagi, A., Heddam, S., Katipoğlu, O. M., Alsumaiei, A. A., AL Mukhtar, M. (2024). Advanced long-term actual evapotranspiration estimation in humid climates for 1958–2021 based on machine-learning models enhanced by the RReliefF algorithm. Journal of Hydrology: Regional Studies 56: 102043. https://doi.org/10.1016/j.ejrh.2024.102043
Fan, J., Wu, L., Zhang, F., Cai, H., Ma, X., & Bai, H. (2018). Evaluation of SVM, ELM, and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates in China. Agricultural and Forest Meteorology, 252, 225–241. https://doi.org/10.1016/j.agrformet.2018.08.019
Feng, Y., Cui, N., Zhao, L., Hu, X., & Gong, D. (2016). Comparison of ELM, GANN, WNN, and empirical models for estimating reference evapotranspiration in the humid region of Southwest China. Journal of Hydrology, 536, 376–383. https://doi.org/10.1016/j.jhydrol.2016.02.053
Gocić, M., Motamedi, S., Shamshirband, S., Petković, D., CH, S., Hashim, R., & ARIF, M. (2015). Soft computing approaches for forecasting reference evapotranspiration. Computers and Electronics in Agriculture, 113, 164–173. https://doi.org/10.1016/j.compag.2015.02.010
Hargreaves, G. H. and Samani, Z. A. (1985). Reference crop evapotranspiration from temperature. Applied Engineering in Agriculture, 1, 96–99. https://doi.org/10.13031/2013.26773
Heramb, P., Ramana RAO, K. V., Subeesh, A., Srivastava, A. (2023). Predictive modelling of reference evapotranspiration using machine learning models coupled with Grey Wolf Optimizer. Water, 15(5), 856. https://doi.org/10.3390/w15050856
Karimi, S., Shiri, J., & Marti, P. (2020). Supplanting missing climatic inputs in classical and random forest models for estimating reference evapotranspiration in humid coastal areas of Iran. Computers and Electronics in Agriculture 178, 105633. https://doi.org/10.1016/j.compag.2020.105633
Kartal, V. (2024). Prediction of monthly evapotranspiration by artificial neural network model development using the Levenberg–Marquardt method in Elazig, Turkey. Environmental Science and Pollution Research, 31(14), 20953–20969. https://doi.org/10.1007/s11356-024-32464-1
Kerdoud, A. (2017). Vulnerabilité à la pollution des eaux de la plaine alluviale d'oued Nil Wilaya de Jijel (N.E. Algérien) [Master's thesis, Université Mohamed Seddik Ben Yahia, Jijel]. http://dspace.univ-jijel.dz:8080/xmlui/bitstream/handle/123456789/2091/M-Eau.Env.%2010-17.pdf?sequence=1
Kisi, O., & Alizamir, M. (2018). Modelling reference evapotranspiration using a new wavelet conjunction heuristic method: wavelet extreme learning machine vs. wavelet neural networks. Agricultural and Forest Meteorology, 263, 41–48. https://doi.org/10.1016/j.agrformet.2018.08.007
Ladlani, I., Houichi, L., Djemili, L., Heddam, S., & Belouz, K. (2012). Modeling daily reference evapotranspiration (ET₀) in the north of Algeria using generalized regression neural networks (GRNN) and radial basis function neural networks (RBFNN): A comparative study. Meteorology and Atmospheric Physics 118(3–4), 163–178. https://doi.org/10.1007/s00703-012-0205-9
Liang, Y., Feng, D., & Sun, Z. (2023). Comparison of four machine learning models for forecasting daily reference evaporation based on public weather forecast data [preprint]. Discussion of Hydrology and Earth System Sciences https://doi.org/10.5194/hess-2023-158
Malik, A., Saggi, M. K., Rehman, S., Sajjad, H., Inyurt, S., Bhatia, A. S., Rajarajeswari, P., Farooque, A. A., Oudah, A. Y., Yaseen, Z. M., Hoat, D. M. (2022). Deep learning versus gradient boosting machine for pan evaporation prediction. Engineering Applications of Computational Fluid Mechanics, 16(1), 570–587. https://doi.org/10.1080/19942060.2022.2027273
Mandal, N., Chanda, K. (2023). Performance of machine learning algorithms for multi-step-ahead prediction of reference evapotranspiration across various agro-climatic zones and cropping seasons. Journal of Hydrology, 620 (Part A), 129418. https://doi.org/10.1016/j.jhydrol.2023.129418
Mehdizadeh, S. (2018). Estimation of daily reference evapotranspiration (ET₀) using artificial intelligence methods: Offering a new approach for lagged ET₀ data-based modeling. Journal of Hydrology, 559, 794–812. https://doi.org/10.1016/j.jhydrol.2018.02.060
Merniz, N., Tahar, A., Benmehaia, A. M. (2019). Statistical assessment of rainfall variability and trends in northeastern Algeria. Journal of Water and Land Development 40(I–III): 87–96. https://doi.org/10.2478/jwld-2019-0009
Mokhtari, H., Benzaouia, M., Hajji, B., Ayadi, N., & Chaabane, K. (2025). Machine learning forecasting approaches for evapotranspiration: a comparative analysis. In B. Hajji, A. Gagliano, A. Mellit, A. Rabhi, and M. Calì (eds.) Proceedings of the 4th International Conference on Electronic Engineering and Renewable Energy Systems—Volume 1 (ICEERE 2024) (pp. 465–475). Springer. https://doi.org/10.1007/978-981-96-0644-3_42
Monteith, J. L. (1965). Evaporation and environment. Symposia of the Society for Experimental Biology, 19, 205–234. https://repository.rothamsted.ac.uk/item/8v5v7/evaporation-and-environment
Moriasi, D.N., Arnold, J.G., Van Liew, M.W., Bingner, R.L., Harmel, R.D., Veith, T.L. (2007). Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE, 50(3), 885–900. https://doi.org/10.13031/2013.23153
Moriasi, D.N., Gitau, M.W., Pai, N., Daggupati, P. (2015). Hydrologic and water quality models: Performance measures and evaluation criteria. Transactions of the ASABE, 58(6), 1763–1785. https://doi.org/10.13031/trans.58.10715
Nash, J. E., and Sutcliffe, J. (1970). River flow forecasting through conceptual models Part I — A discussion of principles. Journal of Hydrology 10(3): 282–290. https://doi.org/10.1016/0022-1694(70)90255-6
Open-Meteo. (2024). Open-Meteo.com. Historical Weather API [Dataset]. https://open-meteo.com/en/docs/historical-weather-api
Patel, A., Ali, S. T., and Pandey, M. K. (2025). Estimation of reference evapotranspiration using ensemble machine-learning models based on regional scenarios. Applied Water Science, 15, 307. https://doi.org/10.1007/s13201-025-02654-4
Penman, H. L. (1948). Natural evaporation from open water, bare soil, and grass. Proceedings of the Royal Society of London. Series A, Mathematical and Physical Sciences 193(1032), 120–145. https://doi.org/10.1098/rspa.1948.0037
Rodrigues, G. C., Braga, R. P. (2021). A simple procedure to estimate reference evapotranspiration during the irrigation season in a hot summer Mediterranean climate. Sustainability 13(1), 349. https://doi.org/10.3390/su13010349
Shiri, J. (2017). Evaluation of FAO56 PM, empirical, semi-empirical, and gene expression programming approaches for estimating daily reference evapotranspiration in hyper-arid regions of Iran. Agricultural Water Management, 188, 101–114. https://doi.org/10.1016/j.agwat.2017.04.009
Stefanidis, S., Ioannou, K., Proutsos, N., Karmiris, I., Stefanidis, P. (2025). Comparative analysis of machine learning algorithms for potential evapotranspiration estimation using limited data from a high-altitude Mediterranean forest. Atmosphere 16(7), 851. https://doi.org/10.3390/atmos16070851
Szczepanek, R. (2022). Daily streamflow forecasting in mountainous catchments using XGBoost, LightGBM, and CatBoost. Hydrology 9(12): 226. https://doi.org/10.3390/hydrology9120226
Tikhamarine, Y., Malik, A., Kumar, A., Souag Gamane, D., Kisi, O. (2020). Estimation of monthly reference evapotranspiration using novel hybrid machine learning approaches. Hydrological Sciences Journal 64(15): 1824–1842. https://doi.org/10.1080/02626667.2019.1678750
Troncoso García, A. R., Brito, I. S., Troncoso, A., & Martínez Álvarez, F. (2023). Explainable hybrid deep learning and Coronavirus Optimization Algorithm for improving evapotranspiration forecasting. Computers and Electronics in Agriculture, 215, 108387. https://doi.org/10.1016/j.compag.2023.108387
Valiantzas, J. D. (2013). Simplified forms for the standardized FAO 56 Penman–Monteith reference evapotranspiration using limited weather data. Journal of Hydrology, 505, 13–23. https://doi.org/10.1016/j.jhydrol.2013.09.005
Willmott, C.J., Rowe, C.M., Mintz, Y. (1985). Climatology of the terrestrial seasonal water cycle. Journal of Climatology, 5(6), 589–606. https://doi.org/10.1002/joc.3370050602
Wu, L., Huang, G., Fan, J., Ma, X., Zhou, H., & Zeng, W. (2020). Hybrid extreme learning machine with metaheuristic algorithms for monthly pan evaporation prediction. Computers and Electronics in Agriculture, 168, 105115. https://doi.org/10.1016/j.compag.2019.105115
Yao, Z., Wang, Z., Xu, N., Wu, J., & Cui, X. (2025). Interpretable multi-step-ahead prediction of reference evapotranspiration using the attention-based ensemble learning method. Journal of Hydrology, 663, 134084. https://doi.org/10.1016/j.jhydrol.2025.134084
Zhao, X.; Li, Y.; Zhao, Z.; Xing, X.; Feng, G.; Bai, J.; Wang, Y.; Qiu, Z.; Zhang, J. Prediction model for daily reference crop evapotranspiration based on hybrid algorithm in semi arid regions of China. Atmosphere, v. 13, n. 6, p. 922, 2022. DOI : https://doi.org/10.3390/atmos13060922
Zhou, H., Ma, L., Xiang, Y., SU, Y., Li, J., Chen, J., Lu, S., Chen, C., & Wu, Q. (2025). Estimation of reference evapotranspiration using hybrid models optimized by bio-inspired algorithms combined with key meteorological factors. Computers and Electronics in Agriculture, 230, 109862. https://doi.org/10.1016/j.compag.2024.109862
Zhou, Z., Zhao, L., Lin, A., Qin, W., Lu, Y., Li, J., Zhong, Y., & He, L. (2020). Exploring the potential of deep factorization machines and various gradient boosting models for modeling daily reference evapotranspiration in China. Arabian Journal of Geosciences 13: 1287. https://doi.org/10.1007/s12517-020-06293-8
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Submeto (emos) o presente trabalho, texto original e inédito, de minha (nossa) autoria, à avaliação de Veredas do Direito - Revista de Direito, e concordo (amos) que os direitos autorais a ele referentes se tornem propriedade exclusiva da Revista Veredas, sendo vedada qualquer reprodução total ou parcial, em qualquer outra parte ou outro meio de divulgação impresso ou eletrônico, dissociado de Veredas do Direito, sem que a necessária e prévia autorização seja solicitada por escrito e obtida junto ao Editor-gerente. Declaro (amos) ainda que não existe conflito de interesse entre o tema abordado, o (s) autor (es) e empresas, instituições ou indivíduos.
Reconheço (Reconhecemos) ainda que Veredas está licenciada sob uma LICENÇA CREATIVE COMMONS:
Licença Creative Commons Attribution 3.0
