Understanding the partitioning of runoff into baseflow and quickflow is crucial for informed decision-making in water resources management, guiding the implementation of flood mitigation strategies, and supporting the development of drought resilience measures. Methods that combine the physically-based Budyko framework with machine learning (ML) have shown promise in estimating global runoff. However, such ‘hybrid’ approaches have not been used for baseflow estimation. Here, we develop a Budyko-constrained ML approach for baseflow estimation by incorporating the Budyko-based baseflow coefficient (BFC) curve as a physical constraint. We estimate the parameters of the original Budyko curve and the newly developed BFC curve based on 13 climatic and physiographic characteristics using boosted regression trees (BRT). BRT models are trained and tested in 1226 catchments worldwide and subsequently applied to the entire global land surface at a 0.25° grid scale. The catchment-trained models exhibit strong performance during the testing phase, with R2 values of 0.96 and 0.88 for runoff and baseflow, respectively. Results reveal that, on average, 30.3% (spatial standard deviation std=26.5%) of the continental precipitation is partitioned into runoff, of which 20.6% (std=22.1%) is baseflow and 9.7% (std=10.3%) is quickflow. Among the 13 climatic and physiographic characteristics, topography and soil-related characteristics generally emerge as the most important drivers, although significant regional variability is observed. Comparisons with previous datasets suggest that global runoff partitioning is still highly uncertain and warrants further research.

Groundwater is an important water source for evaporation, especially during dry conditions. Despite this recognition, plant access to groundwater is often neglected in global evaporation models. This study proposes a new, conceptual approach to incorporate plant access to groundwater in existing global evaporation models. To this end, the Global Land Evaporation Amsterdam Model (GLEAM) is used, and the resulting influence of groundwater on global evaporation is assessed. The new GLEAM-Hydro model relies on the linear reservoir assumption for modelling groundwater flow, and introduces a transpiration partitioning approach to estimate groundwater contributions. Model estimates are validated globally against field observations of evaporation, soil moisture, discharge and groundwater level for the time period 2015-2021, and compared to a regional groundwater model. Results indicate only mild improvements in evaporation estimates, as most eddy-covariance stations are located in energy-limited regions or regions with no plant access to groundwater. The temporal dynamics of the simulated evaporation improves across 75% of the stations where groundwater is a relevant water source. The skill of the model for variables such as soil moisture and runoff remains similar to GLEAM v3. Representing groundwater access influences evaporation in 22% of the continental surface, and it increases evaporation globally by 2.5 mm year-1 (0.5% of terrestrial evaporation). The proposed approach enables a more realistic process representation of evaporation under water-limited conditions in satellite-data driven models such as GLEAM, and sets the ground to assimilate satellite gravimetry data in the future.