Kilometer-Scale AI Downscaling of Atlantic Hurricanes with Generative Ensembles
Yingkai Sha, Talea L. Mayo, Ethan D. Gutmann, Lulin Xue, Andrew Newman
Abstract
This study presents an AI-based dynamical downscaling system for Tropical Cyclones (TCs). The system incorporates an AI-based limited-area model that downscales 3-hourly low-resolution boundary forcings into hourly high-resolution fields autoregressively, and a diffusion model that converts the outputs into ensembles of hazard-relevant variables. The system is trained on the regridded CONUS404 data with ERA5 forcings, and is evaluated on 20 TCs in 2020--2024. Verification shows stable downscaling performance across Atlantic hurricane seasons, with energy spectra closely matching the CONUS404 reference. The system is also verified to produce skillful TC-relevant weather extremes, largely improved over a deterministic AI baseline. The system performs well with forcing data from other models (GDAS/FNL) and can produce detailed eyewall, rainband, and landfall structures in TC case studies. The study provides a good example of how AI-based dynamical downscaling systems can be designed to resolve small-scale extreme weather events.
Create a lesson
Related papers
Did recent sea surface temperature warming reinforce the extreme East Asian summer monsoon precipitation in 2020?
Taeho Mun, Haerin Park, Dong-Hyun Cha et al.
Baseline Climatology of Tornadoes and Waterspouts in the Philippine Archipelago
Generich H. Capuli
A Sensor-Adaptive Incremental Learning Framework for Artifact Detection in Satellite Precipitation Data
Andres F. Monsalve, Hernan A. Moreno, Christian D. Kummerow
A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling
Filippo Dainelli, Amirpasha Mozaffari, Marina Castaño et al.
Universal ordinary differential equations and the parameterization of warm-rain processes
Axel Seifert
Reconciling the Lack of a Robust Anvil Cloud Amount Response to Warming
Zachary McGraw, Blaž Gasparini, Wouter Mol et al.