Ensemble model to enhance robustness of flash flood forecasting using an Artificial Neural Network: case-study on the Gardon Basin (south-eastern France)

Abstract : During the last few decades neural networks have been increasingly used in hydrological modelling for their fundamental property of parsimony and of universal approximation of non-linear functions. For the purpose of flash flood forecasting, feed-forward and recurrent multi-layer perceptrons appear to be efficient tools. Nevertheless, their forecasting performances are sensitive to the initialization of the network parameters. We have studied the cross-validation efficiency to select initialization providing the best forecasts in real time situation. Sensitivity to initialization of feed-forward and recurrent models is compared for one-hour lead-time forecasts. This study shows that cross-validation is unable to select the best initialization. A more robust model has been designed using the median of several models outputs; in this context, this paper analyses the design of the ensemble model for both recurrent and feed-forward models.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

https://hal.umontpellier.fr/hal-02128571
Contributeur : Pascale Roussel <>
Soumis le : mardi 14 mai 2019 - 13:44:22
Dernière modification le : mardi 28 mai 2019 - 13:48:10

Identifiants

  • HAL Id : hal-02128571, version 1

Citation

T. Darras, A. Johannet, B. Vayssade, L. Kong-A-Siou, S. Pistre. Ensemble model to enhance robustness of flash flood forecasting using an Artificial Neural Network: case-study on the Gardon Basin (south-eastern France). ITISE 2016 (International work-conference on Time Series), Jun 2016, Grenade, Spain. ⟨hal-02128571⟩

Partager

Métriques

Consultations de la notice

17