paper
2023
Hybrid physics-ML & parameterization
New model or method
GAN or VAEPhysics-informed / physics-constrainedClimate projections / centennialNASA Journal
2023-10-10
051
Oct 2023
Donifan Barahona, Katherine H. Breen, Heike Kalesse‐Los et al.
Artificial Intelligence for the Earth Systems
NASA
An adversarially trained deep learning parameterization of subgrid vertical wind variability reproduces observed statistics and can run online in large-scale atmospheric models.
Hybrid physics-ML & parameterization
Deep Learning Parameterization of Vertical Wind Velocity Variability via Constrained Adversarial Training
In one sentence. An adversarially trained deep learning parameterization of subgrid vertical wind variability reproduces observed statistics and can run online in large-scale atmospheric models.
Labels
- Topic
- Hybrid physics-ML & parameterization
- Type
- New model or method
- Method
- GAN or VAE, Physics-informed / physics-constrained
- Time scale
- Climate projections / centennial
- Domain
- Global
- Data
- km-scale or high-res simulation, ERA5 / reanalysis, Satellite
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-23-0025.1 OpenAlex:W4387502517
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.