Generative climate downscaling enables high-resolution compound risk assessment by preserving multivariate dependencies

ArXi:2605.11531v1 Announce Type: cross Physics-based climate projections using general circulation models are essential for assessing future risks, but their coarse resolution limits regional decision-making. Statistical downscaling can efficiently add detail, yet many methods treat variables independently, degrading inter-variable relationships that govern compound hazards such as heat stress, drought, and wildfire.