paper
2022
Hybrid physics-ML & parameterization
New model or method
OtherClimate projections / centennialNASANew York University (M2LInES)Stanford University Journal
★ Highlight 2022-04-12
059
Apr 2022
Zachary I. Espinosa, Aditi Sheshadri, Gerald R. Cain et al.
Geophysical Research Letters
NASA, New York University (M2LInES), Stanford University
Neural networks emulate a non-orographic gravity wave drag scheme and generalize to reproduce the QBO and the climate response to increased CO2 when coupled online.
1
Hybrid physics-ML & parameterization★ Highlight
Machine Learning Gravity Wave Parameterization Generalizes to Capture the QBO and Response to Increased CO2
Why it matters. Shows NN gravity wave drag emulator generalizes online to reproduce QBO and CO2 response, a key test for climate-robust ML parameterizations.
In one sentence. Neural networks emulate a non-orographic gravity wave drag scheme and generalize to reproduce the QBO and the climate response to increased CO2 when coupled online.
Labels
- Topic
- Hybrid physics-ML & parameterization
- Type
- New model or method
- Method
- Other
- Time scale
- Climate projections / centennial
- Domain
- Global
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1029/2022gl098174 OpenAlex:W4223593636
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.