Complexity selection of a neural network model for karst flood forecasting: The case of the Lez Basin (southern France)

Line Kong a Siou (1, 2) , Anne Johannet (2) , Valérie Borrell (1) , Séverin Pistre (1)

1 HSM - Hydrosciences Montpellier
2 CMGD - Centre des Matériaux de Grande Diffusion

A neural network model is applied to simulate the rainfall-runoff relation of a karst spring. The input selection for such a model becomes a major issue when deriving a parsimonious and efficient model. The present study is focused on these input selection methods; it begins by proposing two such methods and combines them in a subsequent step. The methods introduced are assessed for both simulation and forecasting purposes. Since rainfall is very difficult to forecast, especially in the study area, we have chosen a forecasting mode that does not require any rainfall forecast assumptions. This application has been implemented on the Lez karst aquifer, a highly complex basin due to its structure and operating conditions. Our models yield very good results, and the forecasted discharge values at the Lez spring are acceptable up to a 1-day forecasting horizon. The combined input selection method ultimately proves to be promising, by reducing input selection time while taking into account: i) the model's ability to accommodate nonlinearity, and ii) the forecasting horizon.

Mots clés: Flash Flood; modeling; Neural networks; karst aquifer

Domaines: Machine Learning [stat.ML]; Hydrologie; Milieux et Changements globaux

Line Kong a Siou, Anne Johannet, Valérie Borrell, Séverin Pistre. Complexity selection of a neural network model for karst flood forecasting: The case of the Lez Basin (southern France). Journal of Hydrology, 2011, 403 (3-4), pp.367-380. ⟨10.1016/j.jhydrol.2011.04.015⟩. ⟨hal-00656598⟩