Comparison between NARX-NN and HEC-HMS models to simulate Wadi Seghir catchment runoff events in Algerian northern

ABSTRACT

This paper presents a comparison between the black box Nonlinear Auto-Regressive with eXogenous inputs-Neural Network (NARX-NN) and the conceptual Hydrologic Engineering Centre-Hydrologic Modelling System (HEC-HMS) Rainfall-Runoff models. The two models were applied on a small urban watershed to assess its response to fourteen hourly real storm events. The differences between the steps engaged in each model to reach the hydrograph were presented in detail. The estimation of the best parameters is carried out using a weighted average function during the calibration phase. A statistical evaluation was conducted to assess the model’s performance thereafter; a critical comparison was made to illustrate the differences and discuss the steps involved. The results indicate that both models successfully reflect the urban basin runoff. However, the NARX-NN outperforms in the testing phase owing to their strength generalization feature. The NARX-NN model has more strength to produce the shape bending of the hydrograph. Consequently, this model is better to highlight the curvatures resulting from the local peaks of rainfall.

KEYWORDS:

• Rainfall-runoff
• modelling
• NARX-NN
• HEC-HMS
• urban watershed
• single hourly events
• calibration
• hydrograph

Acknowledgment

We would like to thank the Laboratory of Civil Engineering and Hydraulics (LGCH) of the University of 8 Mai 1945 Guelma, Algeria, for their great support. Special thanks are also to be addressed to the National Office of Sanitation (NOS) for providing the data, without forgetting Dr Ali BOUAMRANE from the laboratory of Civil and Hydraulic Engineering, Faculty of Applied Sciences, University of Kasdi Merbah, Ouargla, Algeria, for his permanent support and encouragement.

Author contributions

All authors of this manuscript have directly participated in the planning, execution, and analysis of this study. I. KADRI worked on data collection, analytical part, mapping. A. AIEB worked on the statistical part concerning data representation, comparison, and performance studies of each used model. R. MANSOURI participated in validation results, as well as the methodology followed in this study. Finally, it is essential to point out that all authors read and approved the manuscript's final version.

Data availability statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Suggestion for future research

Our future work aims to give a new approach to explain the best choice of rainfall-runoff models to single events in an ungauged watershed; this next proposition will take into consideration the climatic characteristic of the area. In addition, several models will be applied by using different times scales. We want to choose a study area, Algerian northern, because of climate diversity, which characterizes this area. The final approach will be obtained according to the statistical comparison between different results.