Climate foundation models restricted to historical-only training exhibit an accuracy-stability trade-off under no-analog forcing shifts, with the ClimaX model showing the lowest absolute errors but up to 8.44% relative increase in precipitation errors under extreme scenarios.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Flow matching produces better spatial structure than diffusion models for convective precipitation downscaling but underestimates heavy rainfall amounts.
citing papers explorer
-
Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts
Climate foundation models restricted to historical-only training exhibit an accuracy-stability trade-off under no-analog forcing shifts, with the ClimaX model showing the lowest absolute errors but up to 8.44% relative increase in precipitation errors under extreme scenarios.
-
Flow Matching for Convective-Scale Precipitation Downscaling
Flow matching produces better spatial structure than diffusion models for convective precipitation downscaling but underestimates heavy rainfall amounts.