Groundwater level reconstruction using long-term climate reanalysis data and deep neural networks

Study focus: Assessing long-term changes in groundwater is crucial for understanding the impacts of climate change on aquifers and for managing water resources.However, long-term groundwater level (GWL) records are often scarce, limiting the understanding of historical trends and variability. In this paper, we present a deep learning approach to reconstruct GWLs up to several decades back in time using recurrent-based neural networks with wavelet pre-processing and climate reanalysis data as inputs. GWLs are reconstructed using two different reanalysis datasets with distinct spatial resolutions (ERA5: 0.25 degrees x 0.25 degrees & ERA20C: 1 degrees x 1 degrees) and monthly time resolution, and the performance of the simulations were evaluated. New insights: Long term GWL timeseries are now available for northern France, corresponding to extended versions of observational timeseries back to early 20th century. All three types of piezometric behaviours could be reconstructed reliably and consistently capture the multidecadal variability even at coarser resolutions, which is crucial for understanding long-term hydroclimatic trends and cycles. GWLs'multidecadal variability was consistent with the Atlantic multidecadal oscillation. From a synthetic experiment involving a modified long-term observational time series, we highlighted the need for longer training datasets for some lowfrequency signals. Nevertheless, our study demonstrated the potential of using DL models together with reanalysis data to extend GWL observations and improve our understanding of groundwater variability and climate interactions.