Climate change may cause profound changes in the regional water cycle causing negative impacts in many sectors, such as agriculture or water resources. In this study, projected changes of the terrestrial water cycle are investigated based on the simulations from 47 regional climate model ensemble members of the COordinated Regional Downscaling EXperiment (CORDEX) project’s EURO-CORDEX initiative, which downscale different global climate models of the CMIP5 experiment over a 12km resolution pan-European model domain. We analyze climate change impacts on the terrestrial water budget through changes in the long-term annual and seasonal cycles of precipitation, evapotranspiration, and runoff over 20 major European river catchments (Guadalquivir, Guadiana, Tagus, Douro, Ebro, Garonne, Rhone, Po, Seine, Rhine, Loire, Maas, Weser, Elbe, Oder, Vistuala, Danube, Dniester, Dnieper, and Neman) for near (2021-2050) and far future (2070-2099) time spans with reference to a historical period (1971-2000) for three Representative Concentration Pathways (RCPs), RCP2.6, RCP4.5, and RCP8.5. The analysis shows substantial differences between the projected changes in precipitation, evapotranspiration, and runoff for the twenty European catchments. For the near future RCP8.5 scenario, the long-term average of the annual sum precipitation increases over most of Europe by up to 10% in the ensemble mean over central European catchments; but also decreases up to 10 % are found, e.g. over the Iberian Peninsula. For the far future, the long-term average ensemble means of the annual precipitation sum increases from 30% for eastern, 15% for central to 7% for western European catchments, and further decreases up to 25% over the Iberian Peninsula, which will likely cause water stress situations. These first order changes in precipitation lead to ensuing changes in evapotranspiration and runoff, that cause altered hydrological regimes and feedback processes in the water cycle in the catchments.

Long Short-Term Memory (LSTM) networks are a deep learning technology to exploit long-term dependencies in the input-output relationship, which has been observed in the response of groundwater dynamics to atmospheric and land surface processes. We introduced an indirect method based on LSTM networks to estimate monthly water table depth anomalies (wtd_a) across Europe from monthly precipitation anomalies (pr_a). The network has further been optimized by including supplementary hydrometeorological variables, which are routinely measured and available at large scales. The data were obtained from daily integrated hydraulic simulation results over Europe from 1996 to 2016, with a spatial resolution of 0.11° (Furusho-Percot et al., 2019), and separated into a training set, a validation set and a test set at individual pixels. We compared test performances of the LSTM networks locally at selected pixels in eight PRUDENCE regions with random combinations of monthly pr_a, evapotranspiration anomaly, and soil moisture anomaly (θ_a) as input variables. The optimal combination of input variables was pr_a and θ_a, and the networks with this combination achieved average test R^2 between 47.88% and 91.62% in areas with simulated wtd ≤ 3 m. Moreover, we found that introducing θ_a improved the ability of the trained networks to handle new data, indicating the substantial contribution of θ_a to explain groundwater state variation. Therefore, including information about θ_a is beneficial, for instance in the estimation of groundwater drought, and the proposed optimized method may be transferred to a real-time monitoring of groundwater drought at the continental scale using remotely sensed soil moisture observations. Furusho-Percot, C., Goergen, K., Hartick, C., Kulkarni, K., Keune, J. and Kollet, S.: Pan-European groundwater to atmosphere terrestrial systems climatology from a physically consistent simulation, Sci. data, 6(1), 320, doi:10.1038/s41597-019-0328-7, 2019.