Hydrological Forecasts Modeling Using Artificial Intelligence and Conceptual Models of KébirRhumel Watershed, Algeria

• Autorzy: Ramzi Khaldi , Nadir Marouf , Tewfik Bouziane Mohamed , Hakim Djafer Khodja

Identyfikatory

DOI

10.12912/27197050/190235

• Języki publikacji: EN

Abstrakty

EN

This study models the rainfall-runoff relationship in the Kebir-Rhumel River watershed in the Constantine Highlands, Algeria, using data from three concomitant rainfall and hydrometric stations. Statistical tests confirmed the absence of breaks in the series. We applied four conceptual models (GR4J, IHAC6, MORDOR, TOPMO8) and neural network models (RNN, NARX, LSTM) over three- and ten-year periods. Among the conceptual models, GR4J provided the best fit, highlighting the non-stationary nature of the relationship. The PMC neural network model performed well over three years but was less effective over ten years due to low flow influence. Notably, the NARX-RNN and RNN-LSTM models showed excellent predictive accuracy, with NARX-RNN perfectlycapturing flow dynamics and RNN-LSTM achieving minimal RMSE and high correlation coefficients. This study lies the comparative analysis of conceptual and neural network models, specifically the NARX-RNN and RNN-LSTM models, which have not been extensively applied in this context. This research fills the gap in understanding the effectiveness of neural network models in modelling non-stationary rainfall-runoff relationships in the region.

Słowa kluczowe

EN

rainfall-runoff; prevision; Kalman filter; artificial neuron networks; nonlinear autoregressive exogenous model; long short term memory

• Wydawca: Lubelski Oddział Polskiego Towarzystwo Inżynierii Ekologicznej ; Lublin University of Technology ; WNGB Wydawnictwo Naukowe
• Czasopismo: Ecological Engineering & Environmental Technology
• Rocznik: 2024
• Tom: Vol. 25, iss. 9
• Strony: 68--80
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Ramzi Khaldi

• Department of Hydraulic, Faculty of Technology, University of Mohamed Khider, Biskra, 7000, Algeria
• Laboratory of Ecology and Environment, University of Larbi Ben M’hidi, Oum El Bouaghi, 4000, Algeria

• https://orcid.org/0009-0007-4089-3025

autor

Nadir Marouf

• Laboratory of Ecology and Environment, University of Larbi Ben M’hidi, Oum El Bouaghi, 4000, Algeria

• https://orcid.org/0000-0002-9359-0323

autor

Tewfik Bouziane Mohamed

• Department of Hydraulic, Faculty of Technology, University of Mohamed Khider, Biskra, 7000, Algeria

• https://orcid.org/0000-0002-6764-085X

autor

Hakim Djafer Khodja

• Institute of Technology, Water Engineering Department, University of Akli Mohand Oulhadj, Bouira, 10000, Algeria

• https://orcid.org/0000-0001-5661-1116

Bibliografia

• 1. Amireche M., Abdelmalek B., Djamel B. 2018. Modélisation de la relation pluie-débit a différents pas de temps par les modèles conceptuels, neuro-flous et par le filtre de kalman.PhD Thesis.
• 2. Aoulmi Y., Marouf N., Mohamed A. 2020. The assessment of artificial neural network rainfall-runoff models under different input meteorological parameters. Case study: Seybouse basin, Northeast Algeria. Journal of Water and Land Development, 50 (VI–IX), 38–47.
• 3. Aoulmi Y., Marouf N., Rasouli K., Panahi M. 2023. Runoff predictions in a semiarid watershed by convolutional neural networks improved with metaheuristic algorithms and forced with reanalysis and climate data. Journal of Hydrologic Engineering, 28(7), 04023018.
• 4. Batout S., Houichi L., Marouf N. 2022. Influence of the envelope curve on the estimate of probable maximum precipitation (PMP) in the coastal region of Algeria. Modeling Earth Systems and Environment, 8(2), 2083–2093.
• 5. Coron L. 2013. Les modèles hydrologiques conceptuels sont-ils robustes face à un climat en évolution? Diagnostic sur un échantillon de bassins versants français et australiens Doctorat Hydrologie, Institut des Sciences et Industries du Vivant.
• 6. Coron L., Thirel G., Delaigue O., Perrin C., Andréassian, V. 2017. The suite of lumped GR hydrological models in an R package. Environmental modelling & software, 94, 166–171.
• 7. Duc L., Yohei S. 2023. A signal-processing-based interpretation of the Nash–Sutcliffe efficiency. Hydrology and Earth System Sciences, 27(9), 1827–1839.
• 8. Fartas F., Marouf, N., Remini, B. 2017. Quantification du transport solide en suspension dans le barrage de Foum El Gherza–Biskra. Algerie. Journal of Water and Environmental Sciences, 1, 198–218.
• 9. Geron A. 2022. Hands-on machine learning with ScikitLearn, Keras, and TensorFlow. O’Reilly Media, Inc.
• 10. Karim F., Majumdar S., Darabi H., Chen S. 2017. LSTM fully convolutional networks for time series classification. IEEE access, 6, 1662–1669.
• 11. Li P., Zhang J., Krebs P. 2022. Prediction of flow based on a CNN-LSTM combined deep learning approach. Water, 14(6), 993.
• 12. Marouf N., Remini B. 2019. Impact study of BeniHaroun dam on the environmental and socio-economic elements in Kébir-Rhumel basin, Algeria. Journal of Water and Land Development, 43 (X–XII), 120–132.
• 13. Pauwels V.R., De Lannoy G.J., Hendricks Franssen H.-J., Vereecken H. 2013. Simultaneous estimation of model state variables and observation and forecast biases using a two-stage hybrid Kalman filter. Hydrology and earth system sciences, 17(9), 3499–3521.
• 14. Shao Y., Zhao J., Xu J., Fu A., Li, M. 2022. Application of rainfall-runoff simulation based on the NARX dynamic neural network model. Water, 14(13), 2082.
• 15. Sherstinsky A. 2020. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 404, 132306.
• 16. Sun Q., Jankovic M.V., Bally L., Mougiakakou S.G. 2018. Predicting blood glucose with an lstm and bilstm based deep neural network. 14th symposium on neural networks and applications (NEUREL).
• 17. Tamrabet Z., Marouf N., Remini B. 2019. Quantification of suspended solid transport in Endja watercourse [Dehamecha basin-Algeria]. GeoScience Engineering, 65(4), 71–91.
• 18. Vanhoucke V., Senior A., Mao, M.Z. 2011. Improving the speed of neural networks on CPUs.
• 19. Xu Y., Hu C., Wu Q., Jian S., Li Z., Chen Y., Zhang G., Zhang Z., Wang S. 2022. Research on particle swarm optimization in LSTM neural networks for rainfallrunoff simulation. Journal of Hydrology, 608, 127553.
• 20. Yunpeng L., Di H., Junpeng B., Yong Q. 2017. Multi-step ahead time series forecasting for different data patterns based on LSTM recurrent neural network. 14th Web Information Systems and Applications Conference (WISA).
• 21. Zeyneb T., Nadir M., Boualem R. 2022. Modeling of suspended sediment concentrations by artificial neural network and adaptive neuro fuzzy interference system method–study of five largest basins in Eastern Algeria. Water Practice & Technology, 17(5), 1058–1081.
• 22. Zheng Y., Zhang W., Xie J., Liu Q. 2022. A water consumption forecasting model by using a nonlinear autoregressive network with exogenous inputs based on rough attributes. Water, 14(3), 329.