Machine-learning-based downscaling of modelled climate change impacts on groundwater table depth

Abstract

Abstract. There is an urgent demand for assessments of climate change impacts on the hydrological cycle at high spatial resolutions. In particular, the impacts on shallow groundwater levels, which can lead to both flooding and drought, have major implications for agriculture, adaptation, and urban planning. Predicting such hydrological impacts is typically performed using physically based hydrological models (HMs). However, such models are computationally expensive, especially at high spatial resolutions. This study is based on the Danish national groundwater model, set up as a distributed, integrated surface–subsurface model at a 500 m horizontal resolution. Recently, a version at a higher resolution of 100 m was created, amongst others, to better represent the uppermost groundwater table and to meet end-user demands for water management and climate adaptation. However, the increase in resolution of the hydrological model also increases computational bottleneck. To evaluate climate change impacts, a large ensemble of climate models was run with the 500 m hydrological model, while performing the same ensemble run with the 100 m resolution nationwide model was deemed infeasible. The desired outputs at the 100 m resolution were produced by developing a novel, hybrid downscaling method based on machine learning (ML). Hydrological models for five subcatchments, covering around 9 % of Denmark and selected to represent a range of hydrogeological settings, were run at 100 m resolutions with forcings from a reduced ensemble of climate models. Random forest (RF) algorithms were established using the simulated climate change impacts (future – present) on water table depth at 100 m resolution from those submodels as training data. The trained downscaling algorithms were then applied to create nationwide maps of climate-change-induced impacts on the shallow groundwater table at 100 m resolutions. These downscaled maps were successfully validated against results from a validation submodel at a 100 m resolution excluded from training the algorithms, and compared to the impact signals from the 500 m HM across Denmark. The suggested downscaling algorithm also opens for the spatial downscaling of other model outputs. It has the potential for further applications where, for example, computational limitations inhibit running distributed HMs at fine resolutions.