Global hydrological models are important decision support tools for policy making in today’s water-scarce world as their process-based nature allows for worldwide water resources assessments under various climate-change and socio-economic scenarios. Although efforts are continuously being made to improve water resource assessments, global hydrological model computational demands have dramatically increased and calibrating them has proven to be difficult. To address these issues, deep-learning approaches have gained prominence in the hydrological community, in particular the development of deep-learning surrogates. Nevertheless, the development of deep-learning global hydrological model surrogates remains constrained, as previous surrogate frameworks only focus on land-surface fluxes for a single spatial resolution. Therefore, we introduce a global hydrological model surrogate framework that includes integrated spatially-distributed runoff routing, human impacts on water resources and the ability to scale across spatial resolutions. To test our framework we develop a deep-learning surrogate for the PCRaster Global Water Balance (PCR-GLOBWB) global hydrological model. Our surrogate performed well when compared to the model outputs, with a median Kling-Gupta Efficiency (KGE) of 0.45, while predictions were at least an order of magnitude faster. Moreover, the multi-resolution surrogate performed similarly to several single-resolution surrogates, indicating limited trade-offs between the surrogate’s broad spatial applicability and its performance. Model surrogates are a promising tool for the global hydrological modeling community, given their potential benefits in reducing computational demands and enhancing calibration. Accordingly, our framework provides an excellent foundation for the community to create their own multi-scale deep-learning global hydrological model surrogates.

Climate change threatens the sustainable use of groundwater resources worldwide by affecting future recharge rates. However, assessments of global warming’s impact on groundwater recharge at local scales are lacking. This study provides a continental-scale assessment of groundwater recharge changes in Europe, past, present, and future, at a (5 x 5) km2 resolution under different global warming levels (1.5 K, 2.0 K, and 3.0 K). Utilizing multi-model ensemble simulations from four hydrologic and land-surface models (HMs), our analysis incorporates E-OBS observational forcing data (1970-2015) and five bias-corrected and downscale climate model (GCMs) datasets covering the near-past to future climate conditions (1970-2100). Results reveal a north-south polarization in projected groundwater recharge change: declines over 25-50% in the Mediterranean and increases over 25% in North Scandinavia at high warming levels (2.0-3.0 K). Central Europe shows minimal changes (±5%) with larger uncertainty at lower warming levels. The southeastern Balkan and Mediterranean region exhibited high sensitivity to warming, with changes nearly doubling between 1.5 K and 3.0 K. We identify greater uncertainty from differences among GCMs, though significant uncertainties due to HMs exist in regions like the Mediterranean, Nordic, and Balkan areas. The findings highlight the importance of using multi-model ensembles to assess future groundwater recharge changes in Europe and emphasize the need to mitigate impacts in higher warming scenarios.

Changes in groundwater recharge in areas where irrigated agriculture has increased despite low precipitation and surface water allocation are a big concern. The increasing water demand has raised global drought intensities by 10-500%, worsening hydrological drought. Agriculture accounts for 69% of total groundwater abstraction worldwide, and South America expects to face unprecedented hydrological drought conditions within the next 30 years with uncertain impacts (UNESCO 2022, Wada 2016, Wanders & Wada 2015, Siebert et al. 2015). This study compares coupled and non-coupled versions of PCR-GLOBWB2.0 with MODFLOW regarding model selection and scenario comparison. Natural and human scenarios are presented to understand the effects of groundwater depletion and drought recovery. The scenario comparison evaluation of groundwater fluxes, drought characteristics, and recovery reveals changes in the water cycle due to anthropogenic impacts. This is valuable for identifying drought vulnerability in regions where water management is critical for human consumption and ecosystems.