A global analysis of the influence of shallow and deep groundwater tables on relationships between environmental parameters and heatwaves

Heatwaves increasingly impact ecosystems, human health, and economic activities worldwide. As their frequency and intensity rise, understanding the mechanisms driving heatwave dynamics and interactions with land surface processes becomes crucial. While numerous studies have examined atmospheric and land surface variables, the role of groundwater, through its effects on soil moisture and surface evaporative fluxes, remains less understood. Although modeling approaches at various scales have enhanced our understanding of groundwater-atmosphere coupling, machine learning (ML) enables capturing complex, nonlinear interactions and evaluating the relative importance of key drivers globally. We developed pixel-based ML models to estimate global summer heatwave frequency over the past 21 years. For each pixel, we considered data within a 1.5° radius (149 neighboring pixels), identified as the optimal scale through a saturation radius analysis. We used feature importance metrics to identify the dominant drivers among surface fluxes, land characteristics, atmospheric and hydrological variables, and interpreted these results in relation to contrasting groundwater depths (<10 m and >100 m). We ensured robustness using 10-fold cross-validation and confirmed that results were not driven by randomness with two additional validation runs on a subset of the data, with shuffled targets and randomized covariates. Our findings suggest that geopotential height showed the highest relative importance among predictors in regions with deep groundwater tables, while in areas with shallow groundwater, surface fluxes emerge as the key contributor. Incorporating groundwater-related processes may therefore improve understanding of land-atmosphere interactions and support more robust assessments of future heatwave risks.