paper
2023
Explainability, uncertainty & physics
Global medium-range NWP New model or method
RNN / LSTM / ConvLSTMPhysics-informed / physics-constrainedNOAA (incl. GFDL, PSL, GSL, NCEP/EMC) Journal
2023-10-01
047
Oct 2023
Jason A. Platt, Stephen Gregory Penny, Timothy A. Smith et al.
Chaos An Interdisciplinary Journal of Nonlinear Science
NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)
Reservoir computers trained to enforce dynamical invariants gain longer, more stable forecasts with limited data on Lorenz 96 and a quasi-geostrophic atmosphere model.
Explainability, uncertainty & physics
Constraining chaos: Enforcing dynamical invariants in the training of reservoir computers
In one sentence. Reservoir computers trained to enforce dynamical invariants gain longer, more stable forecasts with limited data on Lorenz 96 and a quasi-geostrophic atmosphere model.
Labels
- Topic
- Explainability, uncertainty & physics, Global medium-range NWP
- Type
- New model or method
- Method
- RNN / LSTM / ConvLSTM, Physics-informed / physics-constrained
- Domain
- Global
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1063/5.0156999 OpenAlex:W4387299563
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.