Limits in Using Multiresolution Analysis to Forecast Turbidity by Neural Networks. Case Study on the Yport Basin, Normandie-France
Résumé
Approximately, 25% of the world population drinking water depends on karst aquifers. Nevertheless, due to their poor filtration properties, karst aquifers are very sensitive to pollution and specifically to turbidity. As physical processes involved in transport of solid/suspended particles (advection, diffusion, deposit…) are complicated and badly known in underground conditions, a black-box modeling approach using neural networks is promising. Despite the well-known ability of universal approximation of multilayer perceptron, it appears difficult to efficiently take into account hydrological conditions of the basin. Indeed, these conditions depend both on the initial state of the basin (schematically wet or dry: long timescale component), and on the intensity of rainfall, usually associated to short timescale component. In this context, the present paper addresses the application of the multiresolution analysis to decompose the turbidity on several timescales in order to better consider various phenomena at various timescales (flow in thin or wide fissures for example). Because of “boundary effects”, usually neglected by authors, a specific adaptation was shown as necessary that diminishes the quality of results for real-time forecasting. Decomposing turbidity using multiresolution analysis adds thus questionable improvements.