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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bailly-Comte V, Jourde H, Roesch A, Pistre S (2008) Mediterranean flash flood transfer through karstic area. Environ Geol 54:605–614
Bailly-Comte V, Jourde H, Pistre S (2009) Conceptualization and classification of groundwater-surface water hydrodynamic interaction in karst watersheds: case of the karst watershed of the Coulazou River (Southern France). J Hydrol 376:456–462
Bailly-Comte V, Borrell V, Jourde H, Pistre S (2012) A conceptual semidistributed model of the Coulazou River as a tool for assessing surface water–karst groundwater interactions during flood in Mediterranean ephemeral rivers. Water Resour Res 48(W09534):14
Dreyfus G (2005) Neural networks methodology and applications, 1st edn. Springer, Berlin
Jain A, Kumar S (2009) Dissection of trained neural network hydrologic models for knowledge extraction. Water Resour Res 45
Johannet A, Mangin A, D’Hulst D (1994) Subterranean water infiltration modelling by neural networks : use of water source flow. Int Conf Artif Neural Netw ICANN 94(2):1033–1036
Johannet A, Vayssade B, Bertin D (2008) Neural networks: from black box towards transparent box application to evapotranspiration modeling. Int J Comput Intell 4
Jourde H, Roesch A, Guinot V, Bailly-Comte V (2007) Dynamics and contribution of karst groundwater to surface flow during Mediterranean flood. Environ Geol 51(5):725–730
Jourde H, Lafare A, Mazzilli N, Belaud G, Neppel L, Dörfliger N, Cernesson F (2014) Flash flood mitigation as a positive consequence of anthropogenic forcing on the groundwater resource in a karst catchment. Environ Earth Sci 71(2):573–583
Kong-A-Siou L, Cros K, Johannet A, Borrell-Estupina V, Pistre S (2013) KnoX method, or knowledge extraction from neural network model. Case study on the Lez karst aquifer (southern France). J Hydrol 507:19–32
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kong-A-Siou, L., Jourde, H., Johannet, A. (2015). Neural Networks Model as Transparent Box: Toward Extraction of Proxies to Better Assess Karst/River Interactions (Coulazou Catchment, South of France). In: Andreo, B., Carrasco, F., Durán, J., Jiménez, P., LaMoreaux, J. (eds) Hydrogeological and Environmental Investigations in Karst Systems. Environmental Earth Sciences, vol 1. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17435-3_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-17435-3_40
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17434-6
Online ISBN: 978-3-642-17435-3
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)