paper
2020
Hybrid physics-ML & parameterization
New model or method
OtherOak Ridge National Laboratory Journal
2020-04-23
022
Apr 2020
Anikesh Pal
Geophysical Research Letters
Oak Ridge National Laboratory
Deep neural networks emulate subgrid viscosity and diffusivity for turbulent stratified shear flows, giving a 2-2.5x simulation speedup while preserving kinetic and density variance budgets.
Hybrid physics-ML & parameterization
Deep Learning Emulation of Subgrid‐Scale Processes in Turbulent Shear Flows
In one sentence. Deep neural networks emulate subgrid viscosity and diffusivity for turbulent stratified shear flows, giving a 2-2.5x simulation speedup while preserving kinetic and density variance budgets.
Labels
- Topic
- Hybrid physics-ML & parameterization
- Type
- New model or method
- Method
- Other
- Data
- km-scale or high-res simulation
- Status
- Research
- Identifiers
- DOI:10.1029/2020gl087005 OpenAlex:W3017476219
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.