Integrating Deep Learning to GIS Modelling: An Efficient Approach to Predict Sediment Discharge at Karstic Springs Under Different Land-Use Scenarios
<p>Sediment Discharge (SD) at karstic springs refers to a black-box due to the non-linearity of the processes generating SD, and the lack of accurate physical description of karstic environments. Recent research in hydrology emphasized the use of data-driven techniques for black-box models, such as Deep Learning (DL), considering their good predictive power rather than their explanatory abilities. Indeed, their integration into traditional hydrology-related workflows can be particularly promising. In this study, a deep neural network was built and coupled to an erosion-runoff GIS model (<em>WATERSED</em>, Landemaine et al., 2015) to predict SD at a karstic spring. The study site is located in the Radicatel catchment (88 km&#178; in Normandy, France) where spring water is extracted to a Water Treatment Plant (WTP). SD was predicted for several Designed Storm Project (DSP<sub>0.5-2-10-50-100</sub>) under different land-use scenarios by 2050 (baseline, ploughing up 33% of grassland, eco-engineering (181 fascines + 13ha of grass strips), best farming practices (+20% infiltration)). Rainfall time series retrieved from French <em>SAFRAN</em> database and <em>WATERSED</em> modelling outputs extracted at connected sinkholes were used as input data for the DL model. The model structure was found by a classical trial and error procedure, and the model was trained on two significant hydrologic years (n<sub>events</sub> = 731). Evaluation on a test set suggested good performance of the model (NSE = 0.82). Additional evaluation was performed comparing the &#8216;Generalized Extreme Value&#8217; (GEV) distribution for the five DSP under the baseline scenario. The SD predicted by the DL model was in perfect agreement with the GEV distribution (R&#178; = 0.99). Application of the model on the other scenarios suggests that ploughing up 33% of grasslands will increase SD at the WTP to an average 5%. Eco-engineering and best farming practices will reduce SD in the range of 10-44% and 63-80% respectively. This novel approach offers good opportunities for SD prediction at karstic springs or WTP under multiple land use scenarios. It also provide robust decision making tools for land-use planning and drinking water suppliers.</p>