Conformalized graph neural network emulation of regional climate extremes: an artificial intelligence evaluation of coverage guarantees under emissions-scenario shift

Conformal prediction offers distribution-free coverage guarantees for machine-learning emulators of climate extremes, but the guarantee is only as good as the exchangeability assumption that underwrites it. Using NASA POWER monthly reanalysis for Kampala, Uganda (0.35°N, 32.58°E) over 2000–2023 (312 observations, mean 22.443 °C, linear trend −0.1564 °C per decade), the study specifies a graph construction, a split-conformal calibration protocol, and a coverage-degradation bound expressed as a function of a scenario-shift divergence. The analysis derives a finite-sample coverage gap under covariate shift, proposes a weighted conformal score that restores approximate validity, and identifies the conditions under which GNN emulators of regional extremes can be certified for out-of-distribution emissions scenarios. The contribution is a formal account of when conformal coverage survives scenario shift and a diagnostic that practitioners can compute before deploying an emulator.