COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION

Bestami Taşar

TR EN

YAĞIŞ-AKIŞ TAHMİNİ İÇİN MAKİNE ÖĞRENİMİNE DAYALI MODELLERİN KARŞILAŞTIRMALI DEĞERLENDİRMESİ

Abstract

Yağış-akış tahmini, hidrolojik modellemede önemli bir konudur. Ancak havza süreçleri doğrusal olmayan ve dinamik bir yapı göstermektedir. Bu çalışmada, farklı girdi konfigürasyonlarının günlük akım tahmini üzerindeki etkisi veri odaklı yöntemlerle incelenmiştir. Çalışmada 01/01/2020–13/09/2025 dönemini kapsayan toplam 1826 günlük gözlem kullanılmıştır. Veri setinin 1461 adedi eğitim, 365 adedi ise test amacıyla ayrılmıştır. Üç farklı model seti oluşturulmuş ve bunlar Çoklu Doğrusal Regresyon (MLR), Çok Katmanlı Algılayıcı (MLP), M5 Model Ağacı (M5 TREE) ve Rastgele Ağaç (RT) yöntemleri ile değerlendirilmiştir. Model performansı RMSE, MAE, MAPE, NSE, R ve R² ölçütleri ile belirlenmiştir. Sonuçlar, girdi yapısı genişledikçe tahmin başarısının arttığını göstermiştir. En iyi genel sonuçlar Model Set 3 ile elde edilmiştir. MLP3 en düşük RMSE (3,582 m³/s) ile en yüksek NSE (0,974) ve R² (0,974) değerlerini vermiştir. M5 TREE3 ise en düşük MAE (2,118 m³/s) ve MAPE (%4,601) değerlerini üretmiştir. Buna karşılık, RT modelleri daha zayıf ve daha kararsız sonuçlar vermiştir. Genel olarak, bulgular girdi konfigürasyonunun yağış-akış modellemesinde algoritma seçimi kadar önemli olduğunu göstermiştir. Ayrıca, uygun gecikmeli değişkenler kullanıldığında doğrusal olmayan makine öğrenmesi modellerinin daha güvenilir tahminler üretebildiği belirlenmiştir.

Keywords

COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION

Abstract

Accurate rainfall–runoff prediction is important in hydrological modeling. However, watershed processes are nonlinear and dynamic. This study examined the effect of different input configurations on daily streamflow prediction using data-driven methods. A total of 1,826 daily observations covering the period 01/01/2020–09/13/2025 were used. The dataset was split into 1,461 for training and 365 for testing. Three model sets were developed and evaluated using Multiple Linear Regression (MLR), Multilayer Perceptron (MLP), M5 Model Tree (M5 TREE), and Random Tree (RT). Model performance was assessed using RMSE, MAE, MAPE, NSE, R, and R². The results showed that prediction accuracy improved as the input structure became more comprehensive. Model Set 3 produced the best overall results. MLP3 achieved the lowest RMSE (3.582 m³/s) and the highest NSE (0.974) and R² (0.974). M5 TREE3 produced the lowest MAE (2.118 m³/s) and MAPE (4.601%). In contrast, RT models showed weaker and less stable performance. Overall, the results showed that input configuration is as important as algorithm selection in rainfall–runoff modeling. The findings also indicated that nonlinear machine learning models can provide more reliable predictions when suitable lagged variables are included.

Keywords

References

ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000). Artificial neural networks in hydrology. I: Preliminary concepts. Journal of Hydrologic Engineering, 5(2), 115–123. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115)
Beven, K. (2001). Rainfall–runoff modelling: The primer. John Wiley & Sons.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Dalkilic, H. Y., Kumar, D., Samui, P., Dixon, B., Yesilyurt, S. N., & Katipoğlu, O. M. (2023). Application of deep learning approaches to predict monthly stream flows. Environmental Monitoring and Assessment, 195, 705. https://doi.org/10.1007/s10661-023-11331-5
Dawson, C. W., & Wilby, R. L. (2001). Hydrological modelling using artificial neural networks. Progress in Physical Geography, 25(1), 80–108. https://doi.org/10.1177/030913330102500104
Demirci, M. (2019). Destek vektör makineleri ve M5 karar ağacı yöntemleri kullanılarak yağış akış ilişkisinin tahmini. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 10(3), 1113-1124. https://doi.org/10.24012/dumf.525658
Guo, J., Liu, Y., Zou, Q., Ye, L., Zhu, S., & Zhang, H. (2023). Study on optimization and combination strategy of multiple daily runoff prediction models coupled with physical mechanism and LSTM. Journal of Hydrology, 624, 129969. https://doi.org/10.1016/j.jhydrol.2023.129969
Guzel, H. (2025). Estimation of Rainfall-Runoff Relationship Using Soft Computing Techniques. Applied Ecology & Environmental Research, 23(2), 1923-1936. https://doi.org/10.15666/aeer/2302_19231936

Hao, Z., Singh, V. P., & Xia, Y. (2020). Seasonal drought prediction: Advances, challenges, and future prospects. Reviews of Geophysics, 56(1). https://doi.org/10.1002/2016RG000549
Hipel, K. W., & McLeod, A. I. (1994). Time series modelling of water resources and environmental systems. Elsevier.
Katipoğlu, O. M. (2023). Modeling the effect of meteorological variables on streamflow estimation: Application of data mining techniques in mixed rainfall–snowmelt regime Munzur River, Türkiye. Environmental Science and Pollution Research, 30, 96312–96328. https://doi.org/10.1007/s11356-023-29220-2
Katipoğlu, O. M., & Sarıgöl, M. (2023). Improving the accuracy of rainfall-runoff relationship estimation using signal processing techniques, bio-inspired swarm intelligence and artificial intelligence algorithms. Earth Science Informatics, 16, 3125–3141. https://doi.org/10.1007/s12145-023-01081-w
Kratzert, F., Klotz, D., Herrnegger, M., Sampson, A., Hochreiter, S., & Nearing, G. (2019). Toward improved predictions in ungauged basins: Exploiting the power of machine learning. Water Resources Research, 55(12), 11344–11354. https://doi.org/10.1029/2019WR026065
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., & Nearing, G. (2018). Rainfall–runoff modelling using long short-term memory (LSTM) networks. Hydrology and Earth System Sciences, 22, 6005–6022. https://doi.org/10.5194/hess-22-6005-2018
Kumar, S., Choudhary, M. K., & Thomas, T. (2024). A hybrid technique to enhance the rainfall-runoff prediction of physical and data-driven model: a case study of Upper Narmada River Sub-basin, India. Scientific Reports, 14(1), 26263. https://doi.org/10.1038/s41598-024-77655-5
Legates, D. R., & McCabe, G. J. (1999). Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water Resources Research, 35(1), 233–241. https://doi.org/10.1029/1998WR900018
Liao, S., Wang, H., Liu, B., Ma, X., Zhou, B., & Su, H. (2023). Runoff forecast model based on an EEMD-ANN and meteorological factors using a multicore parallel algorithm. Water Resources Management, 37(4), 1539-1555. https://doi.org/10.1007/s11269-023-03442-y
Maier, H. R., & Dandy, G. C. (2000). Neural networks for the prediction and forecasting of water resources variables: A review. Environmental Modelling & Software, 15(1), 101–124. https://doi.org/10.1016/S1364-8152(99)00007-9
Moradkhani, H., Hsu, K. L., Gupta, H., & Sorooshian, S. (2005). Uncertainty assessment of hydrologic model states and parameters. Water Resources Research, 41(5). https://doi.org/10.1029/2004WR003604
Mosavi, A., Ozturk, P., & Chau, K. W. (2018). Flood prediction using machine learning models: Literature review. Water, 10(11), 1536. https://doi.org/10.3390/w10111536
Quinlan, J. R. (1992). Learning with continuous classes. In Proceedings of the 5th Australian Joint Conference on Artificial Intelligence (pp. 343–348). https://doi.org/10.1142/1897
Samantaray, S., Das, S. S., Sahoo, A., & Satapathy, D. P. (2022). Monthly runoff prediction at Baitarani river basin by support vector machine based on Salp swarm algorithm. Ain Shams Engineering Journal, 13(5), 101732. https://doi.org/10.1016/j.asej.2022.101732
Shen, C. (2018). A transdisciplinary review of deep learning research and its relevance for water resources scientists. Water Resources Research, 54(11), 8558–8593. https://doi.org/10.1029/2018WR022643
Taşar, B., Kaya, Y. Z., Varçin, H., Üneş, F., & Demirci, M. (2017). Forecasting of suspended sediment in rivers using artificial neural networks approach. International Journal of Advanced Engineering Research and Science, 4(12), 79-84. https://doi.org/10.22161/ijaers.4.12.14
Tikhamarine, Y., Souag-Gamane, D., Ahmed, A. N., Kisi, O., & El-Shafie, A. (2020). Improving artificial intelligence models accuracy for monthly streamflow forecasting using data preprocessing techniques. Journal of Hydrology, 582, 124435. https://doi.org/10.1016/j.jhydrol.2019.124435
Tyralis, H., Papacharalampous, G., & Langousis, A. (2019). A brief review of random forests for water scientists and practitioners and their recent history in water resources. Water, 11(5), 910. https://doi.org/10.3390/w11050910
U.S. Geological Survey. (n.d.). *National Water Information System: Web interface. https://waterdata.usgs.gov/nwis
Üneş, F., Demirci, M., Zelenakova, M., Çalışıcı, M., Taşar, B., Vranay, F., & Kaya, Y. Z. (2020). River flow estimation using artificial intelligence and fuzzy techniques. Water, 12(9), 2427. https://doi.org/10.3390/w12092427
Verma, R. (2022). ANN-based rainfall-runoff model and its performance evaluation of Sabarmati River Basin, Gujarat, India. Water Conservation Science and Engineering, 7(4), 525-532. https://doi.org/10.1007/s41101-022-00160-1
Wang, Y., & Witten, I. H. (1997). Induction of model trees for predicting continuous classes. In Proceedings of the European Conference on Machine Learning (pp. 128–137).
Witten, I.H., Frank, E. (2005). Data mining: practical machine learning tools and techniques (2nd edn.). Morgan Kaufmann, San Francisco.

Details

Primary Language

English

Subjects

Deep Learning, Modelling and Simulation, Water Resources Engineering, Water Resources and Water Structures

Journal Section

Research Article

Authors

Bestami Taşar ^*
0000-0003-4842-3937
Türkiye

Publication Date

September 3, 2026

Submission Date

February 20, 2026

Acceptance Date

June 25, 2026

Published in Issue

Year 2026 Volume: 29 Number: 3

IZ

https://izlik.org/JA76BA85MA

Cite

RIS / Bibtex

APA

Taşar, B. (2026). COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 29(3), 1246-1260. https://izlik.org/JA76BA85MA

AMA

1.Taşar B. COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION. KSU J. Eng. Sci. 2026;29(3):1246-1260. https://izlik.org/JA76BA85MA

Chicago

Taşar, Bestami. 2026. “COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29 (3): 1246-60. https://izlik.org/JA76BA85MA.

EndNote

Taşar B (September 1, 2026) COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29 3 1246–1260.

IEEE

[1]B. Taşar, “COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION”, KSU J. Eng. Sci., vol. 29, no. 3, pp. 1246–1260, Sept. 2026, [Online]. Available: https://izlik.org/JA76BA85MA

ISNAD

Taşar, Bestami. “COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29/3 (September 1, 2026): 1246-1260. https://izlik.org/JA76BA85MA.

JAMA

1.Taşar B. COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION. KSU J. Eng. Sci. 2026;29:1246–1260.

MLA

Taşar, Bestami. “COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, vol. 29, no. 3, Sept. 2026, pp. 1246-60, https://izlik.org/JA76BA85MA.

Vancouver

1.Bestami Taşar. COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION. KSU J. Eng. Sci. [Internet]. 2026 Sep. 1;29(3):1246-60. Available from: https://izlik.org/JA76BA85MA