2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 18 , Issue 1 , PP: 64-79, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Ruaa Azzah Suhail 1 , Osama Salim Hameed 2 , El-Sayed M. El-Kenawy 3 * , Marwa M. Eid 4
Doi: https://doi.org/10.54216/JISIoT.180105
The reliable estimation of evaporation is essential for proper water resource planning, particularly in scenarios governed by climatic variability. This work proposes the application of advanced deep learning methods—namely Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU)—optimized by the Gray Wolf Optimization (GWO) algorithm in predicting monthly evaporation values over Almaty, Kazakhstan. Furthermore, the models were optimized for best performance through the adjustment of key hyperparameters such as the number of hidden units, dropout rates, and learning rates. Among candidate models for evaluation, the optimal model with smallest MSE (0.6162) and maximum value of R-squared (0.9335) was LSTM-GWO, indicating strong correlation with actual values. Performance measures such as RMSE, MAE, and MAPE strongly indicated the improved generalization strength of LSTM-GWO compared to BiLSTM and GRU. Forecasts for 2023 indicated seasonal patterns persistently expressed as maximum evaporation during summer seasons. The results detail the potential of deep learning algorithms tuned to improve the precision of hydrological forecasting specifically for semi-arid areas.
Evaporation Forecasting , Deep Learning , LSTM , BiLSTM, GRU , Gray Wolf Optimization , Time Series Prediction , Climate Modeling
[1] R. Ak, Y.-F. Li, V. Vitelli, and E. Zio, "Adequacy assessment of a wind-integrated system using neural network-based interval predictions of wind power generation and load," Int. J. Electr. Power Energy Syst., vol. 95, pp. 213–226, 2018.
[2] K. Al Dhaheri, W. L. Woon, and Z. Aung, "Wind speed forecasting using statistical and machine learning methods: A case study in the UAE," in Proc. Int. Workshop Data Analytics Renew. Energy Integration, Springer, 2017.
[3] A. Y. Alanis, C. Simetti, L. J. Ricalde, and F. Odone, "A wind speed neural model with particle swarm optimization Kalman learning," in Proc. World Autom. Congr., IEEE, 2012.
[4] Z. Bashir and M. El-Hawary, "Applying wavelets to short-term load forecasting using PSO-based neural networks," IEEE Trans. Power Syst., vol. 24, no. 1, pp. 20–27, 2009.
[5] Ö. Baydaroğlu and K. Koçak, "Spatiotemporal analysis of wind speed via the Bayesian maximum entropy approach," Environ. Earth Sci., vol. 78, no. 1, p. 17, 2019.
[6] E. Cadenas, W. Rivera, R. Campos-Amezcua, and C. Heard, "Wind speed prediction using a univariate ARIMA model and a multivariate NARX model," Energies, vol. 9, no. 2, p. 109, 2016.
[7] F. Cassola and M. Burlando, "Wind speed and wind energy forecast through Kalman filtering of numerical weather prediction model output," Appl. Energy, vol. 99, pp. 154–166, 2012.
[8] J. P. S. Catalão, H. M. I. Pousinho, and V. M. F. Mendes, "An artificial neural network approach for short-term wind power forecasting in Portugal," in Proc. Int. Conf. Intell. Syst. Appl. Power Syst., IEEE, 2009.
[9] G. Chang, H. Lu, Y. Chang, and Y. Lee, "An improved neural network-based approach for short-term wind speed and power forecast," Renew. Energy, vol. 105, pp. 301–311, 2017.
[10] A. C. Cinar, "Training feed-forward multi-layer perceptron artificial neural networks with a tree-seed algorithm," Arab. J. Sci. Eng., vol. 45, no. 12, pp. 10915–10938, 2020.
[11] I. G. Damousis, M. C. Alexiadis, J. B. Theocharis, and P. S. Dokopoulos, "A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation," IEEE Trans. Energy Convers., vol. 19, no. 2, pp. 352–361, 2004.
[12] R. C. Deo et al., "Multi-layer perceptron hybrid model integrated with the firefly optimizer algorithm for windspeed prediction," Renew. Energy, vol. 116, pp. 309–323, 2018.
[13] P. Du, J. Wang, Z. Guo, and W. Yang, "A novel hybrid forecasting system based on multi-objective optimization for wind speed forecasting," Energy Convers. Manage, vol. 150, pp. 90–107, 2017.
[14] E. Erdem and J. Shi, "ARMA based approaches for forecasting the tuple of wind speed and direction," Appl. Energy, vol. 88, no. 4, pp. 1405–1414, 2011.
[15] A. Gani et al., "A combined method to estimate wind speed distribution using SVM and firefly algorithm," Environ. Prog. Sustain. Energy, vol. 35, no. 3, pp. 867–875, 2016.
[16] Y. Gao and R. Billinton, "Adequacy assessment of generating systems containing wind power considering wind speed correlation," IET Renew. Power Gener., vol. 3, no. 2, pp. 217–226, 2009.
[17] F. S. Gharehchopogh, "Advances in Tree seed algorithm: A comprehensive survey," Arch. Comput. Methods Eng., 2022.
[18] M. Jawad et al., "Genetic algorithm-based NARX neural network short-term and medium-term uncertainty modelling and prediction," J. Eng., vol. 2018, no. 8, pp. 721–729, 2018.
[19] A. Aljuboori and M. M. A. Abdulrazzq, "Enhancing Accuracy in Predicting Continuous Values through Regression," Iraqi J. Comput. Sci. Math., vol. 5, no. 4, Art. no. 25, 2024, doi: 10.52866/2788-7421.1227.
[20] A. Kumar, R. S. Babu, and P. K. Gupta, "A Hybrid Model for Short-Term Wind Speed Prediction Using LSTM and ARIMA," Renewable Energy, vol. 180, pp. 1234–1245, 2022. doi: 10.1016/j.renene.2021.10.038.
[21] J. M. Torres, L. M. González, and F. J. López, "Machine Learning Techniques for Wind Power Forecasting: A Review," Energy Reports, vol. 8, pp. 123–145, 2022. doi: 10.1016/j.egyr.2022.01.001.
[22] Z. Y. Algamal, A. M. Salih, and M. A. Khaleel, "A New Ridge-Type Estimator for the Gamma regression model," Iraqi J. Comput. Sci. Math., vol. 5, no. 1, Art. no. 22, 2024, doi: 10.52866/ijcsm.2024.05.01.006.
[23] J. Sharma et al., Trans., “Enhancing Intrusion Detection Systems with Adaptive Neuro-Fuzzy Inference Systems,” Mesopotamian Journal of CyberSecurity, vol. 5, no. 1, pp. 1–10, Jan. 2025, doi: 10.58496/MJCS/2025/001.
[24] A. M. Salman et al., "Enhancing Cybersecurity with Machine Learning: A Hybrid Approach for Anomaly Detection and Threat Prediction," Mesopotamian J. CyberSecurity, vol. 5, no. 1, pp. 202–215, Mar. 2025, doi: 10.58496/MJCS/2025/014.
[25] N. Almusallam, B. T. Al Nuaimi, H. Alkattan, M. Abotaleb, and K. Dhoska, "Physics-Informed Neural Networks for Solving Heat Equation in Thermal Engineering," Int. J. Tech. Phys. Probl. Eng. (IJTPE), vol. 17, no. 1, pp. 375–382, Mar. 2025.
[26] H. Alkattan, A. A. Subhi, L. Farhan, and G. Al-mashhadani, "Hybrid Model for Forecasting Temperature in Khartoum Based on CRU data," Mesopotamian J. Big Data, 2024, pp. 164–174, doi: 10.58496/MJBD/2024/011.
[27] I. Harris, T. J. Osborn, P. Jones, and D. Lister, "Version 4 of the CRU TS monthly high-resolution gridded multivariate climate dataset," Sci. Data, vol. 7, no. 1, p. 109, 2020, doi: 10.1038/s41597-020-0453-3.
[28] A. J. Ramadhan et al., "Forecasting Monthly Export Price of Sugarcane in India Using SARIMA Modelling," BIO Web Conf., vol. 97, p. 00142, 2024, doi: 10.1051/bioconf/20249700142.
[29] R. S. Chaudhary and V. K. Sharma, "Forecasting Monthly Rainfall Using Machine Learning Techniques: A Case Study of India," Journal of Atmospheric and Solar-Terrestrial Physics, vol. 224, p. 105797, 2021. doi: 10.1016/j.jastp.2021.105797.
[30] A. T. Al-Hasani, B. J. E. Al-Juburi, F. H. Hasan, A. J. Ramadhan, and A. O. A. Adebayo, “Prediction of Monthly Wind Velocity Using Machine Learning,” BIO Web Conf., vol. 97, p. 00107, 2024, doi: 10.1051/bioconf/20249700107.
