Abstract
Karst catchments frequently exhibit complex exchanges between surface and subterranean flow. While the swing between surface flood and underground flood is complex, the ability to predict such behavior would be of great interest for flood forecasting and water recharge assessment. To this end an innovative methodology is proposed to visualize internal variables of a neural network model. It proves to be efficient to extract internal variables highly correlated to measured signals previously identified as proxy of the karst-river exchanges. The study focuses on a small Mediterranean catchment where karst/river interactions control the dynamic and genesis of surface floods. But the methodology is generic and can be applied to any catchment provided the availability of a sufficient database.