Machine Learning Estimation of Daily ET₀ in Northern Algeria
Abstract
Accurate estimation of reference evapotranspiration (ET₀) is essential for efficient water resource management, particularly in agriculture, where precise irrigation planning is critical for sustainability. A correct estimate allows for the precise amount of water needed for crops, preventing waste and overexploitation of resources, and improving irrigation efficiency and water conservation in the long term. This study evaluates four machine learning models such as Support Vector Regression (SVR), Random Forest (RF), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM) for predicting ET₀. Model performance was assessed against ET₀ values computed using the Penman–Monteith (PM) and Hargreaves Samani (HS) equations, based on NASA POWER reanalysis data and CMIP6 climate datasets. Both data sources were validated against observed meteorological measurements from three weather stations as well as Soumaa, Boukourdane and Mouzaia in northern Algeria,where,the results demonstrate a strong correlation between predicted and observed ET₀ values, with SVR and RF consistently achieving high accuracy. The Soumaa station, using the NASA POWER-based model, yielded the best performance (R² = 0.92, MAE = 0.06 mm/day, RMSE = 0.08 mm/day), whereas the Boukourdane station exhibited larger prediction discrepancies. CMIP6-based models also produced robust estimates under varying climatic conditions. The CNRM and IPSL models showed the highest temperature agreement at Boukourdane (r = 0.8649) and minimal ET₀ bias at Soumaa, while Mouzaia exhibited the largest underestimation using IPSL (−7.3344 mm/day). While NASA POWER data provide superior short-term accuracy, CMIP6-based approaches offer significant value for long-term climate projections. Random Forest and MLP consistently achieved nearly perfect agreement with observed ET₀ at Boukourdane and Soumaa, whereas performance decreased at Mouzaia due to stronger local climatic variability and terrain influence. However, the findings fundamentally underscore that integrating machine learning models with climate projections is pivotal for advancing irrigation decision-making and promoting sustainable water resource management under changing climatic conditions.
Keywords: evapotranspiration, CMIP6, NASA POWER, water resource management, irrigation scheduling, bias correction, spatial analysis, prediction models
© 2026 Serbian Geographical Society, Belgrade, Serbia.
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Serbia.
Full Text:
PDFReferences
Acharki, S., Raza, A., Vishwakarma, D. K., Amharref, M., Bernoussi, A. S., Singh, S. K., Al-Ansari, N., Dewidar, A. Z., Al-Othman, A. A., & Mattar, M. Y. (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, Article 2542. https://doi.org/10.1038/s41598-024-83859-6
Achite, M., Sattari, M. T., Toubal, A. K., Wałęga, A., Krakauer, N. Y., Sihag, P., & Pham, Q. B. (2021). Modeling Reference Evapotranspiration in a Semiarid Area Using Data-driven Techniques: A Case Study in Lower Cheliff plain, Algeria. Research Square, 1-34. https://doi.org/10.21203/rs.3.rs-773420/v1
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 based on ANN and GEP models. Water, 14(8), Article 1210. https://doi.org/10.3390/w14081210
Al-Hasani, B., Abdellatif, M., Carnacina, I., Harris, C., Al‐Quraishi, A. M. F., Maaroof, B. F., & Zubaidi, S. L. (2023). Integrated geospatial approach for adaptive rainwater harvesting site selection under the impact of climate change. Stochastic Environmental Research and Risk Assessment, 38(3), Article 1009. https://doi.org/10.1007/s00477-023-02611-0
Allen, R. G., Smith, M., Pereira, L. S., Raes, D., & Wright, J. L. (2001). Revised FAO Procedures for Calculating Evapotranspiration: Irrigation and Drainage Paper No. 56 with Testing in Idaho. Watershed Management and Operations Management 2000. https://doi.org/10.1061/40499(2000)125
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.
Aly, M. S., Darwish, S. M., & Aly, A. (2023). High performance machine learning approach for reference evapotranspiration estimation. Stochastic Environmental Research and Risk Assessment, 38(2), Article 689. https://doi.org/10.1007/s00477-023-02594-y
Amani, S., Shafizadeh‐Moghadam, H., & Morid, S. (2024). Utilizing Machine Learning Models with Limited Meteorological Data as Alternatives for the FAO-56PM Model in Estimating Reference Evapotranspiration. Water Resources Management, 38(6), Article 1921. https://doi.org/10.1007/s11269-023-03670-2
Almorox, J., Senatore, A., Quej, V. H., & Mendicino, G. (2018). Worldwide assessment of the Penman–Monteith temperature approach for the estimation of monthly reference evapotranspiration. Theoretical and Applied Climatology, 131(1), 693–703. https://doi.org/10.1007/s00704-016-1996-2
Ba-ichou, A., Zegoumou, A., Benhlima, S., & Bekr, M. A. (2024a). Daily reference evapotranspiration estimation utilizing deep learning models with varied combinations of weather data. E3S Web of Conferences, 492, Article 1002. https://doi.org/10.1051/e3sconf/202449201002
Bellout, A., Vaz, E., & Penfound, E. (2020). Rethinking agricultural land use in Algiers: A spatial analysis of the Eastern Mitidja Plain. Habitat International, 104, Article 102239. https://doi.org/10.1016/j.habitatint.2020.102239
Ben Ferhat, T., & Saidou, A. (2025). The phenomenon of climatic drought and its spatial impacts in the Algerian Sahara regions - Tidikelt region, in Salah Province, for the period 2000-2020. Bulletin of the Serbian Geographical Society, 105(2), 39–56. https://doi.org/10.2298/GSGD2502039F
Bjarke, N. R., Barsugli, J. J., & Livneh, B. (2023). Ensemble of CMIP6 derived reference and potential evapotranspiration with radiative and advective components. Scientific Data, 10(1). https://doi.org/10.1038/s41597-023-02290-0
Bouchentouf, S., & Benabdeli, K. (2021). Water resources and food security in Algeria: Diagnosis and new strategy proposition. African Journal of Agricultural Research, 17(3), Article 414. https://doi.org/10.5897/ajar2020.15125
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, Article 351. https://doi.org/10.1007/s00704-025-05561-5
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Claro, et al. (2024). An evolutionary parsimonious approach to estimate daily reference evapotranspiration. Scientific Reports, 14, Article 6736. https://doi.org/10.1038/s41598-024-56770-3
Di Nunno, F., & Granata, F. (2023). Futurs trends of reference evapotranspiration in Sicily based on CORDEX data and machine learning algorithms. Agricultural Water Management, 280, Article 108232. https://doi.org/10.1016/j.agwat.2023.108232
Daher, H., & Kirtman, B. P. (2025). Future climate assessment in the Mediterranean region using downscaled CMIP6 data. Frontiers in Climate, 7. https://doi.org/10.3389/fclim.2025.1691944
Dohler, R. E., Zanetti, S. S., Cecílio, R. A., Pezzopane, J. E. M., & Xavier, A. C. (2020). Application of different calibration methods for the Hargreaves-Samani model in Southeast Brazil. Research, Society and Development, 9(8). https://doi.org/10.33448/rsd-v9i8.4811
Eyring, V., Bony, S., Meehl, G. A., Senior, C. A., Stevens, B., Stouffer, R. J., & Taylor, K. E. (2016). Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization. Geoscientific Model Development, 9(5), 1937–1958. https://doi.org/10.5194/gmd-9-1937-2016
Elbeltagi, A., Deng, J., Wang, K., Malik, A., & Maroufpoor, S. (2020). Modeling long-term dynamics of crop evapotranspiration using deep learning in a semi-arid environment. Agricultural Water Management, 241, Article 106334. https://doi.org/10.1016/j.agwat.2020.106334
FAO. (2021). The State of the World’s Land and Water Resources for Food and Agriculture 2021 – Systems at breaking point. Food and Agriculture Organization of the United Nations. https://doi.org/10.4060/CB9910EN
Farag, A. A. (2025). Machine learning approaches for enhanced estimation of reference evapotranspiration (ETo): a comparative evaluation. Scientific Reports, 15(1), Article 38485. https://doi.org/10.1038/s41598-025-23166-w
Ferreira, L. B., da Cunha, F. F., de Oliveira, R. A., & Fernandes Filho, E. I. (2019). Estimation of reference evapotranspiration in Brazil with limited meteorological data using ANN and SVM–A new approach. Journal of Hydrology, 572, 556–570. https://doi.org/10.1016/j.jhydrol.2019.03.028
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Granata, F. (2019). Evapotranspiration evaluation models based on machine learning algorithms - A comparative study. Agricultural Water Management, 217, 303–315. https://doi.org/10.1016/j.agwat.2019.03.015
Hargreaves, G. H., & Samani, Z. A. (1985). Reference crop evapotranspiration from temperature. Applied Engineering in Agriculture, 1(2), 96–99. https://doi.org/10.13031/2013.26773
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hendy, Z. M., Abdelhamid, M. A., Gyasi‐Agyei, Y., & Mokhtar, A. (2023). Estimation of reference evapotranspiration based on machine learning models and timeseries analysis: a case study in an arid climate. Applied Water Science, 13(11). https://doi.org/10.1007/s13201-023-02016-y
Hamouda, G. B., Tomozeiu, R., Pavan, V., Antolini, G., Snyder, R. L., & Ventura, F. (2021). Impacts of climate change and rising atmospheric CO2 on future projected reference evapotranspiration in Emilia-Romagna (Italy). Theoretical and Applied Climatology, 146, Article 801. https://doi.org/10.1007/s00704-021-03745-3
Kay, M., Bunning, S., Burke, J., Boerger, V., Bojić, D., Bosc, P., Clark, M., Dale, D. A., England, M., Hoogeveen, J., Koo‐Oshima, S., Moreno, P., Muchoney, D., Nachtergaele, F., Sánchez, C., Salman, M. T., Schlingloff, S., Ünver, O., Vargas, R., … Ziadat, F. (2022). The State of the World’s Land and Water Resources for Food and Agriculture 2021 – Systems at breaking point. FAO. https://doi.org/10.4060/cb9910en
Kumar, U. (2023). Modelling monthly reference evapotranspiration estimation using machine learning approach in data-scarce North Western Himalaya region (Almora), Uttarakhand. Journal of Earth System Science, 132(3). https://doi.org/10.1007/s12040-023-02138-6
McCarthi, J. J., Canziani, O., Leary, N., Dokken, D. J., & White, K. S. (2025). Climate Change 2022: Impacts, Adaptation and Vulnerability. Climate Change and Law Collection. https://doi.org/10.1163/9789004322714_cclc_2022-0258-0930
Meddi, M., & Eslamian, S. (2021). Incertitudes liées aux précipitations et aux ressources en eau dans les pays du Maghreb face aux changements climatiques. In N. Oguge, D. Ayal, L. Adeleke, & I. da Silva (Eds.), Manuel africain d’adaptation aux changements climatiques (pp. 1967-2003). https://doi.org/10.1007/978-3-030-45106-6_114
Mezouane, H., Hank, D., & Delli, R. (2025). Agricultural Water Management under Water Scarcity in Algeria: Practices and Future Perspectives. Open Agriculture Journal, 20(1). https://doi.org/10.2174/0118743315442659251120053241
Mokhtar, A., Hamed, M. M., He, H., Salem, A., & Hendy, Z. M. (2024). Egypt’s water future: AI predicts evapotranspiration shifts across climate zones. Journal of Hydrology: Regional Studies, 56, Article 101968. https://doi.org/10.1016/j.ejrh.2024.101968
Mustapha, M., Zineddine, M., Gmira, M., Mouhtadi, M. E., & Alaoui, A. E. (2025). Machine Learning Approaches for Predicting Reference Evapotranspiration: A Comparative Study Using Ground and Gridded Climate Data in Fes Region. World Water Policy, 11(2), Article 652. https://doi.org/10.1002/wwp2.12255
NASA. (2023). NASA POWER Project Data Sets. https://power.larc.nasa.gov/data-access-viewer/
Nouri, M., & Veysi, S. (2024). CMIP6 multi-model ensemble projection of reference evapotranspiration using machine learning algorithms. Agricultural Water Management, 306, Article 109190. https://doi.org/10.1016/j.agwat.2024.109190
Pereira, L. S., Paredes, P., Melton, F., Johnson, L., Wang, T., López-Urrea, R., ... & Allen, R. G. (2020). Prediction of crop coefficients from fraction of ground cover and height. Background and validation using ground and remote sensing data. Agricultural Water Management, 241, Article 106197. https://doi.org/10.1016/j.agwat.2020.106663
Rodrigues, G. C., & Braga, R. P. (2021). Estimation of Daily Reference Evapotranspiration from NASA POWER Reanalysis Products in a Hot Summer Mediterranean Climate. Agronomy, 11(10), Article 2077. https://doi.org/10.3390/agronomy11102077
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), Article 594. https://doi.org/10.3390/agronomy12030594
Saci, R., Keblouti, M., Katipoğlu, O. M., Đurin, B., Majour, H., Sayad, L., Bouzahar, F., & Benchaiba, L. (2025). Assessing the efficacy of various predictive models in simulating monthly reference evapotranspiration patterns and its impact on water resource management for agriculture in the Kebir-West watershed, North-East of Algeria. Journal of Hydrology and Hydromechanics, 73(3), 284–294. https://doi.org/10.2478/johh-2025-0022
Shafizadeh‐Moghadam, H., Amani, S., & Morid, S. (2023). Utilizing machine learning models with limited meteorological data as alternatives for the FAO-56 model in estimating potential evapotranspiration. European Water Resources Association. https://doi.org/10.21203/rs.3.rs-3324487/v1
Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
Snyder, R. L., & Eching, S. (2002). Penman-Monteith daily (24-hour) and Hargreaves-Samani Equations for Estimating Reference Evapotranspiration from Monthly Data. Regents of the University of California.
Sabancı, D., Yürekli, K., Cömert, M. M., Kılıçarslan, S., & Erdoğan, M. (2023). Predicting reference evapotranspiration based on hydro-climatic variables: comparison of different machine learning models. Hydrological Sciences Journal, 68(7), Article 1050. https://doi.org/10.1080/02626667.2023.2203824
Seraiche, L., Ghodbane, M., Selmane, T., & Dougha, M. (2026). Hydrochemical assessment and groundwater pollution in the Southern Hodna Chott Region (Algeria): Characteristics, pollution levels, and drinking water quality implications. Bulletin of the Serbian Geographical Society, 106(1), 21–36. https://doi.org/10.2298/GSGD2601021S
Sharafi, S., & Ghaleni, M. M. (2024). Revealing accuracy in climate dynamics: enhancing evapotranspiration estimation using advanced quantile regression and machine learning models. Applied Water Science, 14(7). https://doi.org/10.1007/s13201-024-02211-5
Sun, X., Zhang, B., Dai, M., Gao, R. X., Jing, C., Ma, K., Gu, S., Gu, L., Zhen, W., & Gu, X. (2024). Research on methods for estimating reference crop evapotranspiration under incomplete meteorological indicators. Frontiers in Plant Science, 15. https://doi.org/10.3389/fpls.2024.1354913
Tan, M. L., Armanuos, A. M., Ahmadianfar, I., Demir, V., Heddam, S. H., Al Areeq, A. M., Abba, S. I., Halder, B., Kilinic, H., & Yaseen, Z. (2023). Evaluation of NASA POWER and ERA5 Land for estimating tropical precipitation and temperature extremes. Journal of Hydrology, 624, Article 129940. https://doi.org/10.1016/j.jhydrol.2023.129940
Themeßl, M. J., Gobiet, A., & Heinrich, G. (2012). Empirical-statistical downscaling and error correction of regional climate models and its impact on the climate change signal. Climatic Change, 112(2), 449–468. https://doi.org/10.1007/s10584-011-0224-4
Thrasher, B., Wang, W., Michaelis, A., Melton, F., Lee, T., & Nemani, N. (2022). NASA Global Daily Downscaled Projections, CMIP6. Scientific Data, 9, Article 262. https://doi.org/10.1038/s41597-022-01393-4
Wu, L., Peng, Y., Fan, J., & Wang, Y. (2019). Machine learning models for the estimation of monthly mean daily reference evapotranspiration based on cross-station and synthetic data. Hydrology Research, 50(6), Article 1730. https://doi.org/10.2166/nh.2019.060
Yassin, M. A., Alazba, A. A., & Mattar, M. A. (2016). Artificial neural networks versus gene expression programming for estimating reference evapotranspiration in arid climate. Agricultural Water Management, 163, 110–124. https://doi.org/10.1016/j.agwat.2015.09.009
Refbacks
- There are currently no refbacks.