Climate and Ecosystem of Arid and Semi-arid Regions

Climate and Ecosystem of Arid and Semi-arid Regions

Performance Evaluation of Soft Computing-Based Methods for Daily Streamflow Prediction

Document Type : Original Article

Authors
Edris Merufinia 1
Edris Merufinia 2
Sadigha Shakofti 3
Roya Yazdanimehr 4
1 Ph.D. in Water Resources Engineering, Tehran Science and Research Branch, Water Resources Specialist, West Azerbaijan Regional Water Company, Iran
2 Ph.D. in Civil Engineering, Water Resources Engineering and Management, Advisor to the CEO, West Azerbaijan Water and Wastewater Engineering Company, Urmia, Iran
3 Ph.D. student, Department of Natural Resources Engineering, Watershed Management, Faculty of Agriculture and Natural Resources, University of Hormozgan, Iran
4 M.Sc. Student in Watershed Science and Engineering, Major in Watershed Management, Faculty of Natural Resources and Environment, Malayer University, Iran
10.22075/ceasr.2025.40107.1063
Abstract
Background and Objectives: Accurate daily river flow forecasting particularly in humid catchments characterized by dynamic hydrological regimes plays a vital role in sustainable water resources management, hydrological planning, and flood risk mitigation. In recent years, soft computing–based models, including machine learning and deep learning approaches, have garnered significant attention in water engineering due to their inherent capacity to capture complex, nonlinear, nonstationary, and multivariate relationships. However, empirical evidence indicates that a systematic and comparative evaluation of advanced artificial intelligence models especially under humid catchment conditions and at daily temporal resolution remains insufficient. This research gap not only limits a comprehensive understanding of the strengths and limitations of each method but also poses serious challenges to the transferability, robustness, and operational reliability of these models in practical decision-making. To address this gap, the present study evaluates and compares the performance of machine learning and deep learning models for daily river flow prediction, with a specific focus on a humid basin subject to climate variability, thereby clarifying methodological innovations and operational applicability of these AI-driven approaches.
Materials and Methods: In this study, daily meteorological and hydrometric data spanning the period from 1969 to 2018 were first collected. Precipitation (Pt), evaporation (Et), and river flow discharge with one- to three-day lags (Qt₋₁ to Qt-3) were used as input variables. Pearson correlation coefficients were calculated between input and output variables, based on which five input scenarios and model configurations were selected. Data preprocessing (including homogenization, outlier removal, reconstruction of missing values, and normalization) was performed, and the dataset was split into training and testing subsets in a 70:30 ratio. For modeling, one machine learning algorithm Support Vector Regression (SVR) and two deep learning models Convolutional Neural Network (CNN) and Generative Adversarial Network (GAN) were employed. Model performance was evaluated using multiple metrics: Coefficient of determination (R²), Root Mean Square Error (RMSE), Percent Bias (PBIAS), and Kling–Gupta Efficiency (KGE). The results were compared in tabular form, and final outcomes were visually presented using scatter, time series, violin plot, and Taylor diagrams.
Results: The results indicated that SVR model achieved the best performance in Scenario 5 (SN5), yielding R² of 0.85, RMSE of 5.675 m³/s, PBIAS close to zero (0.475%), and KGE of 0.877 during the testing phase. In this scenario, SVR outperformed the CNN and GAN models by 3.8% and 3.4% in terms of R², and by 14.1% and 14.0% in terms of KGE, respectively. Moreover, the CNN and GAN models demonstrated acceptable performance only in the more complex scenarios (SN3 to SN5), while exhibiting poor results in the simpler scenarios (SN1 and SN2), with R² values below 0.04. Overall, SVR with the optimal input combination (SN5) provided the most stable and accurate predictions, showing statistically significant superiority over the other two models across all effective scenarios.
Conclusion: In daily river discharge forecasting within highly variable basins, model input structure exerts a far greater influence than algorithmic complexity so much that excluding lagged discharge values led to complete predictive failure (R² < 0.04), even when employing deep learning architectures. Among the evaluated models, Support Vector Regression (SVR) under the optimal scenario (SN5) achieved the most accurate and unbiased performance in the testing phase, with R² = 0.850, RMSE = 5.675 m³/s, and PBIAS = 0.475%, significantly outperforming both CNN and GAN. These findings substantiate a fundamental principle in hydroinformatics: Under conditions of limited data and high climatic stress, model selection should be guided by alignment with the hydrological character of the data, rather than by algorithmic novelty alone, a conclusion with direct implications for designing operational forecasting systems and adaptive water governance in vulnerable regions.
Keywords
Streamflow prediction
soft computing
Deep learning
Pearson correlation coefficient
Tajan Basin
Subjects
1. Adnan, R. M., Mostafa, R. R., Elbeltagi, A., Yaseen, Z. M., Shahid, S., & Kisi, O. (2022). Development of new machine learning model for streamflow prediction: Case studies in Pakistan. Stochastic Environmental Research and Risk Assessment, 36(4), 999–1033.
2. Avand, M., Moradi, H. R., & Hazbavi, Z. (2024). Interactive changes in climatic and hydrological droughts, water quality, and land use/cover of Tajan watershed, Northern Iran. Water, 16(13), 1784.
3. Ayana, Ö., Kanbak, D. F., Kaya Keleş, M., & Turhan, E. (2023). Monthly streamflow prediction and performance comparison of machine learning and deep learning methods. Acta Geophysica, 71(6), 2905–2922.
4. Bargam, B., Boudhar, A., Kinnard, C., Bouamri, H., Nifa, K., & Chehbouni, A. (2024). Evaluation of the support vector regression (SVR) and the random forest (RF) models accuracy for streamflow prediction under a data-scarce basin in Morocco. Discover Applied Sciences, 6(6), 306.
5. Cho, K., & Kim, Y. (2022). Improving streamflow prediction in the WRF-Hydro model with LSTM networks. Journal of Hydrology, 605, 127297.
6. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
7. Danesh, M., Gharehbaghi, A., Mehdizadeh, S., & Danesh, A. (2025). A comparative assessment of machine learning and deep learning models for the daily river streamflow forecasting. Water Resources Management, 39(4), 1911–1930.
8. Ghimire, S., Yaseen, Z. M., Farooque, A. A., Deo, R. C., Zhang, J., & Tao, X. (2021). Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks. Scientific Reports, 11(1), 17497.
9. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative adversarial networks. Communications of the ACM, 63(11), 139–144.
10. Grey, V., Fletcher, T., Smith-Miles, K., Hatt, B., & Coleman, R. (2025). Harnessing the strengths of machine learning and geostatistics to improve streamflow prediction in ungauged basins; the best of both worlds. Journal of Hydrology, 133936.
11. Ikram, R. M. A., Hazarika, B. B., Gupta, D., Heddam, S., & Kisi, O. (2023). Streamflow prediction in mountainous region using new machine learning and data preprocessing methods: a case study. Neural Computing and Applications, 35(12), 9053–9070.
12. Ismail-Fawaz, A., Devanne, M., Weber, J., & Forestier, G. (2022). Deep learning for time series classification using new hand-crafted convolution filters. 2022 IEEE International Conference on Big Data (Big Data), 972–981.
13. Kedam, N., Tiwari, D. K., Kumar, V., Khedher, K. M., & Salem, M. A. (2024). River stream flow prediction through advanced machine learning models for enhanced accuracy. Results in Engineering, 22, 102215.
14. Khosravi, K., Golkarian, A., & Tiefenbacher, J. P. (2022). Using optimized deep learning to predict daily streamflow: A comparison to common machine learning algorithms. Water Resources Management, 36(2), 699–716.
15. Krichen, M. (2023). Generative adversarial networks. 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), 1–7.
16. Kumar, V., Kedam, N., Sharma, K. V., Mehta, D. J., & Caloiero, T. (2023). Advanced machine learning techniques to improve hydrological prediction: A comparative analysis of streamflow prediction models. Water, 15(14), 2572.
17. Kumshe, U. M. M., Abdulhamid, Z. M., Mala, B. A., Muazu, T., Muhammad, A. U., Sangary, O., Ba, A. F., Tijjani, S., Adam, J. M., & Ali, M. A. H. (2024). Improving short-term daily streamflow forecasting using an autoencoder based CNN-LSTM model. Water Resources Management, 38(15), 5973–5989.
18. Latif, S. D., & Ahmed, A. N. (2023). Streamflow prediction utilizing deep learning and machine learning algorithms for sustainable water supply management. Water Resources Management, 37(8), 3227–3241.
19. López-Chacón, S. R., Salazar, F., & Bladé, E. (2025). Hybrid physically based and machine learning model to enhance high streamflow prediction. Hydrological Sciences Journal, 70(2), 311–333.
20. Merufinia, E., Sharafati, A., Abghari, H., & Hassanzadeh, Y. (2023). On the simulation of streamflow using hybrid tree-based machine learning models: A case study of Kurkursar basin, Iran. Arabian Journal of Geosciences, 16(1), 28.
21. Meshram, S. G., Meshram, C., Santos, C. A. G., Benzougagh, B., & Khedher, K. M. (2022). Streamflow prediction based on artificial intelligence techniques. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 46(3), 2393–2403.
22. Miau, S., & Hung, W. H. (2020). River flooding forecasting and anomaly detection based on deep learning. Ieee Access, 8, 198384–198402.
23. Naabil, E., Lamptey, B. L., Arnault, J., Olufayo, A., & Kunstmann, H. (2017). Water resources management using the WRF-Hydro modelling system: Case-study of the Tono dam in West Africa. Journal of Hydrology: Regional Studies, 12, 196–209.
24. Nasir, N., Irwan, D., Ahmed, A. N., Ibrahim, S. L., Ibrahim, I., Sherif, M., & El-Shafie, A. (2025). Harnessing machine learning for streamflow prediction: A comparative study of advanced models in the Upper Klang River Basin, Malaysia. Journal of Hydrology: Regional Studies, 60, 102565.
25. Saeidi, P., Mehrdadi, N., Karbassi, A., & Ardestani, M. (2022). Integrated river-estuary modeling to assess spawning and habitation area for Caspian WhiteFish in response to upstream pollution sources (case study: Tajan River estuary). International Journal of Environmental Research, 16(5), 93.
26. Solanki, H., Vegad, U., Kushwaha, A., & Mishra, V. (2025). Improving streamflow prediction using multiple hydrological models and machine learning methods. Water Resources Research, 61(1), e2024WR038192.
27. Sun, K., Rajabtabar, M., Samadi, S., Rezaie-Balf, M., Ghaemi, A., Band, S. S., & Mosavi, A. (2021). An integrated machine learning, noise suppression, and population-based algorithm to improve total dissolved solids prediction. Engineering Applications of Computational Fluid Mechanics, 15(1), 251–271.
28. Vatanchi, S. M., Etemadfard, H., Maghrebi, M. F., & Shad, R. (2023). A comparative study on forecasting of long-term daily streamflow using ANN, ANFIS, BiLSTM and CNN-GRU-LSTM. Water Resources Management, 37(12), 4769–4785.
29. Vinokić, L., Dotlić, M., Prodanović, V., Kolaković, S., Simonovic, S. P., & Stojković, M. (2025). Effectiveness of three machine learning models for prediction of daily streamflow and uncertainty assessment. Water Research X, 27, 100297.
30. Wang, L., Guo, Y., & Fan, M. (2022). Improving annual streamflow prediction by extracting information from high-frequency components of streamflow. Water Resources Management, 36(12), 4535–4555.
31. Wang, Z., Xu, N., Bao, X., Wu, J., & Cui, X. (2024). Spatio-temporal deep learning model for accurate streamflow prediction with multi-source data fusion. Environmental Modelling & Software, 178, 106091.
32. Xu, W., Chen, J., Zhang, X. J., Xiong, L., & Chen, H. (2022). A framework of integrating heterogeneous data sources for monthly streamflow prediction using a state-of-the-art deep learning model. Journal of Hydrology, 614, 128599.
33. Yu, X., Wang, Y., Wu, L., Chen, G., Wang, L., & Qin, H. (2020). Comparison of support vector regression and extreme gradient boosting for decomposition-based data-driven 10-day streamflow forecasting. Journal of Hydrology, 582, 124293.
34. Zhou, Y., Duan, Y., Yao, H., Li, X., & Li, S. (2025). Incorporating hydrological constraints with deep learning for streamflow prediction. Expert Systems with Applications, 259, 125379.
Climate and Ecosystem of Arid and Semi-arid Regions
Volume 2, Issue 2 - Serial Number 3
December 2025
Pages 206-226

  • Receive Date 19 December 2025
  • Revise Date 27 November 2025
  • Accept Date 04 January 2026