Abstract. Excessive sediment discharge in karstic regions can be highly disruptive to water treatment plants. It is essential for catchment stakeholders and drinking water suppliers to limit the impact of high sediment loads on potable water supply, but their strategic choices must be based on simulations integrating surface and groundwater transfers and taking into account possible changes in land use. Karstic environments are particularly challenging as they face a lack of accurate physical descriptions for the modelling process, and they can be particularly complex to predict due to the non-linearity of the processes generating sediment discharge. The aim of the study was to assess the sediment discharge variability at a water treatment plant according to multiple realistic land use scenarios. To reach that goal, we developed a new cascade modelling approach with an erosion-runoff geographic information system (GIS) model (WaterSed) and a deep neural network. The model was used in the Radicatel hydrogeological catchment (106 km2 in Normandy, France), where karstic spring water is extracted to a water treatment plant. The sediment discharge was simulated for five design storms under current land use and compared to four land use scenarios (baseline, ploughing up of grassland, eco-engineering, best farming practices, and coupling of eco-engineering/best farming practices). Daily rainfall time series and WaterSed modelling outputs extracted at connected sinkholes (positive dye tracing) were used as input data for the deep neural network model. The model structure was found by a classical trial-and-error procedure, and the model was trained on 2 significant hydrologic years. Evaluation on a test set showed a good performance of the model (NSE = 0.82), and the application of a monthly backward-chaining nested cross-validation revealed that the model is able to generalize on new datasets. Simulations made for the four land use scenarios suggested that ploughing up 33 % of grasslands would increase sediment discharge at the water treatment plant by 5 % on average. By contrast, eco-engineering and best farming practices will significantly reduce sediment discharge at the water treatment plant (respectively in the ranges of 10 %–44 % and 24 %–61 %). The coupling of these two strategies is the most efficient since it affects the hydro-sedimentary production and transfer processes (decreasing sediment discharge from 40 % to 80 %). The cascade modelling approach developed in this study offers interesting opportunities for sediment discharge prediction at karstic springs or water treatment plants under multiple land use scenarios. It also provides robust decision-making tools for land use planning and drinking water suppliers.

No abstract

No abstract

Laignel (2021) Analyse coût-bénéfice du programme d'actions visant à réduire les impacts du ruissellement et de l'érosion en Haute-Normandie : évaluation des actions passées et projections futures sur le bassin versant

<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 km² 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 ‘Generalized Extreme Value’ (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 (R² = 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>