Simulating sediment discharge at water treatment plants under different land use scenarios using cascade modelling with an expert-based erosion-runoff model and a deep neural network

Abstract

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.

Lessons learnt on the impact of an unprecedented soil decontamination program in Fukushima on contaminant fluxes

“…The WaterSed model was used to model runoff, erosion, and associated 137 Cs fluxes. It is an event-based distributed model that simulates runoff and soil erosion from the plot to the catchment scale during a sequence of rainfall events ( 34 – 37 ). It is a raster-based model that describes runoff, erosion, and sediment transport based on hydrological and sediment balances.…”

“…The WaterSed model ( 37 ) is a nondynamic distributed model that simulates runoff and soil erosion from the plot to the catchment scale during a sequence of rainfall events ( 34 – 36 )—see SI Appendix for more details. In this work, runoff and erosion processes were calculated for a grid with a spatial resolution corresponding to that of the DTM (i.e., 5 m).…”

An Improved Gray Neural Network Method to Optimize Spatial and Temporal Characteristics Analysis of Land-Use Change

“…It has been commonly used in land, water, space, mapping, transportation, meteorology, etc. Artificial intelligence (AI) technology has been integrated into various fields of socioeconomic development, and AI technology makes it possible to automatically identify and capture implicit, disordered, and many data features [ 2 ]. As a significant branch of artificial neural network algorithm, Self-organizing Feature Mapping (SOFM) neural network is self-organizing clustering of the target dataset with its internal mutual learning and competition mechanism.…”