Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting

Asli Bor; Merve Okan

doi:10.38088/jise.1375510

EN

Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting

Abstract

In this study, Multilayer Perceptron (MLP) with Levenberg-Marquardt and Bayesian Regularization algorithms machine learning methods are compared for modeling of the rainfall-runoff process. For this purpose, daily flows were forecast using 5844 discharge data monitored between 1999 and 2015 of D21A001 Kırkgöze gauging station on the Karasu River operated by DSI. 6 scenarios were developed during the studies. Our findings indicate that the estimated capability of the Bayesian Regularization algorithm were close to with Levenberg-Marquardt algorithm for training and testing, respectively. This study shows that different network structures and data representing land features can improve prediction for longer lead times. We consider that the ANN model accurately depicted the Karasu flows, and that our study will serve as a guide for more research on flooding and water storage.

Keywords

Thanks

The authors would like to thank the DSI (General Directorate of State Hydraulic Works), Department of Survey, Planning, and Allocations for the providing of the data.

References

[1] Tan Kesgin, R. I., Demir, I., Kesgin, E., Abdelkader, M., & Agaccioglu, H. (2023). A data-driven approach to predict hydrometeorological variability and fluctuations in lake water levels. Journal of Water and Land Development, (58), 158-170. https://doi.org/10.24425/jwld.2023.146608.
[2] Demirel, M. C., Özen, A., Orta, S., Toker, E., Demir, H. K., Ekmekcioğlu, Ö., Tayşi, H., Eruçar, S., Sağ, A. B., Sarı, Ö., Tuncer, E., Hancı, H., Özcan, T. İ., Erdem, H., Koşucu, M. M., Başakın, E. E., Ahmed, K., Anwar, A., Avcuoğlu, M. B., Vanlı, Ö., Stisen, S., Booij, M. J. (2019). Additional Value of Using Satellite-Based Soil Moisture and Two Sources of Groundwater Data for Hydrological Model Calibration. Water, 11(10), 2083. https://doi.org/10.3390/w11102083.
[3] Shamseldin, A. Y. (1997). Application of a neural network technique to rainfall-runoff modelling. Journal of Hydrology, 199(3): 272–294.
[4] Tokar, S. A., and Johnson, P. A. (1999). Rainfall-Runoff Modeling Using Artificial Neural Networks. Journal of Hydrologic Engineering, 4(3): 232–239.
[5] Chang, F.-J., and Chen, Y.-C. (2001). A counterpropagation fuzzy-neural network modeling approach to real time streamflow prediction. Journal of Hydrology, 245: 153–164.
[6] Öztopal, A., Kahya, C., and Asilhan, S. (2001). Yapay Sinir Ağları ile Akış Tahmini. 1. Türkiye Su Kongresi, İstanbul, Türkiye, 8 - 10 Ocak 2001, cilt.1. pp. 311–318.
[7] Jayawardena, A. W., and Fernando, T. M. K. G. (2001). River flow prediction: An artificial neural network approach. Regional Management of Water Resources, Maastricht, The Netherlands. pp. 239–246.
[8] Sivakumar, B., Jayawardena, A., and Fernando, T. M. K. G. (2002). River Flow Forecasting: Use of Phase-Space Reconstruction and Artificial Neural Networks Approaches. Journal of Hydrology, 265: 225–245.

[9] Dorado, J., RabuñAL, J. R., Pazos, A., Rivero, D., Santos, A., and Puertas, J. (2003). Prediction and modeling of the rainfall-runoff transformation of a typical urban basin using ann and gp. Applied Artificial Intelligence, Taylor & Francis, 17(4): 329–343.
[10] Kişi, Ö. (2005). Daily River Flow Forecasting Using Artificial Neural Networks and Auto-Regressive Models. Turkish Journal of Engineering and Environmental Sciences, 29: 9–20.
[11] Demirpençe, H. (2005). Köprüçay Akımlarının Yapay Sinir Ağları ile Tahmini. Antalya Yöresinin İnşaat Mühendisleri Sorunları Kongresi.
[12] Yurdusev, M. A., Acı, M., Turan, M. E., and İçağa, Y. (2008). Akarçay Nehri Aylık Akımlarının Yapay Sinir Ağları ile Tahmini. Celal Bayar Üniversitesi Fen Bilimleri Dergisi, 4(1): 73–88.
[13] Okkan, U., and Mollamahmutoğlu, A. (2010). Çoruh Nehri Günlük Akımlarının Yapay Sinir Ağları ile Tahmin Edilmesi. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 14(3): 251–261.
[14] Okkan, U., and Dalkilic, H. Y. (2010). Demirköprü Barajı Aylık Buharlaşma Yüksekliklerinin Yapay Sinir Ağları ile Tahmin Edilmesi. DSİ Teknik Bülten, 108: 30–36.
[15] Chen, S. M., Wang, Y. M., and Tsou, I. (2013). Using artificial neural network approach for modelling rainfall-runoff due to typhoon. Journal of Earth System Science, 122(2): 399–405.
[16] Kızılaslan, M. A., Sağın, F., Doğan, E., and Sönmez, O. (2014). Aşağı Sakarya Nehri akımlarının yapay sinir ağları ile tahmin edilmesi. SAÜ Fen Bilimleri Dergisi, 18(2): 99–103.
[17] Singh, G., Panda, R. K., and Lamers, M. (2015). Modeling of daily runoff from a small agricultural watershed using artificial neural network with resampling techniques. Journal of Hydroinformatics, 17(1): 56–74.
[18] Khan, M. Y. A., Hasan, F., Panwar, S., and Chakrapani, G. J. (2016). Neural network model for discharge and water-level prediction for Ramganga River catchment of Ganga Basin, India. Hydrological Sciences Journal, Taylor & Francis, 61(11): 2084–2095.
[19] Altunkaynak, A., and Başakin, E. E. (2018). Zaman Serileri Kullanılarak Nehir Akım Tahmini ve Farklı Yöntemlerle Karşılaştırılması. Erzincan University Journal of Science and Technology, 11(1): 92–101.
[20] Nacar, S., Hınıs, M. A., and Kankal, M. (2018). Forecasting Daily Streamflow Discharges Using Various Neural Network Models and Training Algorithms. KSCE Journal of Civil Engineering, 22(9): 3676–3685.
[21] Bor, A., and Okan, M. (2019). FIRAT HAVZASI karasu günlük akimlarinin yapay sinir ağlari ile modellenmesi. 10. Ulusal Hidroloji Kongresi, Muğla, Türkiye, Cilt 2. pp. 857-869.
[22] Fırat, M., and Dikbaş, F. (2006). Göllerde üç boyutlu hidrodinamik modellemede pom ve yapay sinir ağlari yöntemlerinin kullanilmasi : gökpinar baraj gölü örneği. Pamukkale University Engineering College Journal of Engineering Sciences, 12(1): 43–50.
[23] Coulibaly, P., Anctil, F., and Bobée, B. (1999). Prévision hydrologique par réseaux de neurones artificiels : état de l’art. Canadian Journal of Civil Engineering, 26: 293–304.
[24] Minns, A. W., and Hall, M. J. (1996). Artificial neural networks as rainfall-runoff models. Hydrological Sciences Journal, 41: 399–417.
[25] Gümüş, V., Başak, A., and Yenigün, K. (2018). Yapay Sinir Ağları ile Şanlıurfa İstasyonunun Kuraklığının Tahmini. Gazi Üniversitesi Fen Bilimleri Dergisi, 6(3): 621–633.
[26] Haykin, S. (1998). Neural Networks : A Comprehensive Foundation. Prentice-Hall. Upper Saddle River, NJ.
[27] Öztemel, E. (2006). Yapay Sinir Ağları. Papatya Publishing, Istanbul, Turkey.
[28] Şen, Z. (2004). Yapay Sinir Ağları İlkeleri. Turkish Water Foundation, Istanbul,Turkey.
[29] Chen, T. C., Han, D. J., Au, F. T. K., and Tham, L. G. (2003). Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate. Proceedings of the International Joint Conference on Neural Networks, IEEE. pp. 1873–1878.
[30] Hagan, M. T., and Menhaj, M. B. (1994). Training Feedforward Networks with the Marquardt Algorithm. IEEE Transactions on Neural Networks, 5(6): 989–993.
[31] trainlm Levenberg-Marquardt backpropagation. https://www.mathworks.com/help/deeplearning/ref/trainlm.html [Accessed: 07 september 2023].
[32] Xu, M., Zeng, G., Xu, X., Huang, G., Jiang, R., and Sun, W. (2006). Application of Bayesian regularized BP neural network model for trend analysis, acidity and chemical composition of precipitation in North Carolina. Water, Air, and Soil Pollution, 172(1–4): 167–184.
[33] MacKay, D. J. C. (1992). Bayesian Interpolation. Neural Computation, 4(3): 415–447.
[34] Foresee, F. D., and Hagan, M. T. (1997). Gauss-Newton approximation to bayesian learning. IEEE International Conference on Neural Networks - Conference Proceedings, Houston, TX, USA, 9–12 June 1997. pp. 1930–1935.
[35] Kayri, M. (2016). Predictive abilities of Bayesian Regularization and Levenberg-Marquardt Algorithms in Artificial Neural Networks: A Comparative Empirical Study on Social Data. Mathematical and Computational Applications, 21(2).
[36] Gupta, H. V., Sorooshian, S., and Yapo, P. O. (1999). Status of automatic calibration for hydrologic models: comparison with multilevel expert calibration. Journal of Hydraulic Engineering, 4(2): 135–143.
[37] Moriasi, D. N., Arnold, J. G., Liew, M. W. Van, Bingner, R. L., Harmel, R. D., and Veith, T. L. (2007). Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. American Society of Agricultural and Biological Engineers, 50(3): 885–900.
[38] Nash, J. E., and Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology, 10(3): 282–290.
[39] Improve Shallow Neural Network Generalization and Avoid Overfitting. The MathWorks, Inc. https://www.mathworks.com/help/deeplearning/ug/improve-neural-network-generalization-and-avoid-overfitting.html [Accessed: 07 september 2023].

Details

Primary Language

English

Subjects

Numerical Modelization in Civil Engineering , Water Resources Engineering

Journal Section

Research Article

Authors

Asli Bor ^*
0000-0002-1679-5130
Norway

Merve Okan
0000-0001-6095-2992
Türkiye

Early Pub Date

May 19, 2025

Publication Date

June 17, 2025

Submission Date

October 14, 2023

Acceptance Date

January 17, 2025

Published in Issue

Year 2025 Volume: 9 Number: 1

DOI

https://doi.org/10.38088/jise.1375510

IZ

https://izlik.org/JA77WK29GP

Cite

RIS / Bibtex

APA

Bor, A., & Okan, M. (2025). Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting. Journal of Innovative Science and Engineering, 9(1), 62-77. https://doi.org/10.38088/jise.1375510

AMA

1.Bor A, Okan M. Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting. JISE. 2025;9(1):62-77. doi:10.38088/jise.1375510

Chicago

Bor, Asli, and Merve Okan. 2025. “Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting”. Journal of Innovative Science and Engineering 9 (1): 62-77. https://doi.org/10.38088/jise.1375510.

EndNote

Bor A, Okan M (June 1, 2025) Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting. Journal of Innovative Science and Engineering 9 1 62–77.

IEEE

[1]A. Bor and M. Okan, “Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting”, JISE, vol. 9, no. 1, pp. 62–77, June 2025, doi: 10.38088/jise.1375510.

ISNAD

Bor, Asli - Okan, Merve. “Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting”. Journal of Innovative Science and Engineering 9/1 (June 1, 2025): 62-77. https://doi.org/10.38088/jise.1375510.

JAMA

1.Bor A, Okan M. Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting. JISE. 2025;9:62–77.

MLA

Bor, Asli, and Merve Okan. “Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting”. Journal of Innovative Science and Engineering, vol. 9, no. 1, June 2025, pp. 62-77, doi:10.38088/jise.1375510.

Vancouver

1.Asli Bor, Merve Okan. Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting. JISE. 2025 Jun. 1;9(1):62-77. doi:10.38088/jise.1375510

Öz

Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting

Abstract

Keywords

Thanks

References

Details

Primary Language

Subjects

Journal Section

Authors

Early Pub Date

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite