A hybrid ML physics model, NeuralGCM, with persisted SST and sea ice anomalies, yields skillful seasonal forecasts of tropical cyclone frequency in the North Atlantic and East Pacific (r around 0.7 over 1990-2023).
The July-November means of the 500-hPa geopotential height of the NeuralGCM and the ERA5 show consistent climate patterns
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ao-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Advancing Seasonal Prediction of Tropical Cyclone Activity with a Hybrid AI-Physics Climate Model
A hybrid ML physics model, NeuralGCM, with persisted SST and sea ice anomalies, yields skillful seasonal forecasts of tropical cyclone frequency in the North Atlantic and East Pacific (r around 0.7 over 1990-2023).