IAHS2022-379
https://doi.org/10.5194/iahs2022-379
IAHS-AISH Scientific Assembly 2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Towards a flash flood forecasting model for local crisis managers

Salma Sadkou, Guillaume Artigue, Pierre-Alain Ayral, Séverin Pistre, Sophie Sauvagnargues, and Anne Johannet
Salma Sadkou et al.
  • HydroSciences Montpellier, Univ. Montpellier, IMT Mines Ales, IRD, CNRS, 30100 Ales, France, France (salma.sadkou@mines-ales.fr)

Southern France is frequently hit with severe flash floods. These events have caused numerous casualties as well as considerable economic losses. In France, crisis inducing floods are managed at a local scale by municipalities. Current forecasting models are rarely used by these crisis managers. This is due to the fact that these models often fail to convey relevant information in an appropriate form. This work aims to determine the adequate output variable in a crisis management context with a special focus on the needs and vision of local crisis managers.

The study area is the 545 sq. km. sized Gardon in Anduze in the Cévennes range, France, which is often subject to important flash floods. A feed-forward multilayer perceptron, a type of neural networks where one of the inputs is the measured output, is used to forecast water discharge. Neural networks are good candidates to model nonlinear phenomenon. Both the properties of parsimony - they provide relevant results while requiring a limited number of parameters – and of universal approximation are very helpful in hydrology. Various rainfall and discharge measurements are considered as inputs. The output variable for this model is water flow. Data ranges from 2002 to 2019 at a 30 minutes’ time step. Events are extracted from this database to compose a training set, a test set and an early stopping set. Complexity and variable selection is made using cross-validation, allowing to select the most robust model. To make the model easier to understand by end users, discharges are replaced by water levels. Both these results are compared, especially regarding their ability to reach crisis management plans levels without delay. Secondly, ensemble models based on different initializations of the parameters of the neural model during the training step are developed. They give an uncertainty margin, often desired by end users.

The results are enriched through the collection of background information (end users’ opinions and habits) in order to enhance the assessment of performance. Further analysis is carried to determine the pros and cons of each approach (discharge or levels to crisis management plans levels and uncertainties representation and communication).

How to cite: Sadkou, S., Artigue, G., Ayral, P.-A., Pistre, S., Sauvagnargues, S., and Johannet, A.: Towards a flash flood forecasting model for local crisis managers, IAHS-AISH Scientific Assembly 2022, Montpellier, France, 29 May–3 Jun 2022, IAHS2022-379, https://doi.org/10.5194/iahs2022-379, 2022.