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
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
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.