Journal cover Journal topic
Natural Hazards and Earth System Sciences An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 2.883 IF 2.883
  • IF 5-year value: 3.321 IF 5-year
  • CiteScore value: 3.07 CiteScore
  • SNIP value: 1.336 SNIP 1.336
  • IPP value: 2.80 IPP 2.80
  • SJR value: 1.024 SJR 1.024
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 81 Scimago H
    index 81
  • h5-index value: 43 h5-index 43
Volume 12, issue 11 | Copyright
Nat. Hazards Earth Syst. Sci., 12, 3307-3324, 2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.

Research article 12 Nov 2012

Research article | 12 Nov 2012

Flash flood forecasting in poorly gauged basins using neural networks: case study of the Gardon de Mialet basin (southern France)

G. Artigue1, A. Johannet1, V. Borrell2, and S. Pistre2 G. Artigue et al.
  • 1Ecole des Mines d'Alès, Centre des Matériaux de Grande Diffusion, Alès, France
  • 2Université Montpellier II, Hydrosciences Montpellier, Montpellier, France

Abstract. In southern France, flash flood episodes frequently cause fatalities and severe damage. In order to inform and warn populations, the French flood forecasting service (SCHAPI, Service Central d'Hydrométéorologie et d'Appui à la Prévision des Inondations) initiated the BVNE (Bassin Versant Numérique Expérimental, or Experimental Digital Basin) project in an effort to enhance flash flood predictability. The target area for this study is the Gardon d'Anduze basin, located in the heart of the Cévennes range. In this Mediterranean mountainous setting, rainfall intensity can be very high, resulting in flash flooding. Discharge and rainfall gauges are often exposed to extreme weather conditions, which undermines measurement accuracy and continuity. Moreover, the processes governing rainfall-discharge relations are not well understood for these steeply-sloped and heterogeneous basins. In this context of inadequate information on both the forcing variables and process knowledge, neural networks are investigated due to their universal approximation and parsimony properties. We demonstrate herein that thanks to a rigorous variable and complexity selection, efficient forecasting of up to two-hour durations, without requiring rainfall forecasting as input, can be derived using the measured discharges available from a feedforward model. In the case of discharge gauge malfunction, in degraded mode, forecasting may result using a recurrent neural network model. We also observe that neural network models exhibit low sensitivity to uncertainty in rainfall measurements since producing ensemble forecasting does not significantly affect forecasting quality. In providing good results, this study suggests close consideration of our main purpose: generating forecasting on ungauged basins.

Publications Copernicus