Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Samudra 2 scales autoregressive neural ocean emulators to finer resolutions with architectural tweaks and dynamic loss, raising upper-ocean temperature R² from 0.56 to 0.87 at 1° and recovering mesoscale features.
A single data-driven model for atmosphere and ocean achieves roughly one day better forecast skill for marine variables at medium range than traditional physics-based models.
citing papers explorer
-
Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators
Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
-
Samudra 2: Scaling Ocean Emulators across Resolutions
Samudra 2 scales autoregressive neural ocean emulators to finer resolutions with architectural tweaks and dynamic loss, raising upper-ocean temperature R² from 0.56 to 0.87 at 1° and recovering mesoscale features.
-
Representing the Surface Ocean in ECMWF's data-driven forecasting system AIFS
A single data-driven model for atmosphere and ocean achieves roughly one day better forecast skill for marine variables at medium range than traditional physics-based models.