Toward Data‐Driven Weather and Climate Forecasting: Approximating a Simple General Circulation Model With Deep Learning
Problem
Whether deep learning can emulate the dynamics of weather and climate general circulation models to enable data-driven forecasting.
Why it matters
Learning-based forecasting could eventually make weather and climate prediction faster and cheaper than physical simulation.
What the AI did
A deep neural network trained on a simple general circulation model predicts complete model states several steps ahead and generates stable climate runs via feedback.
Results
Network predicts complete model state several time steps ahead; climate run has similar statistics to the GCM with no long-term drift
Impact
Proof of concept in a model world only; real-world forecasting not demonstrated.
Record
| Venue | Geophysical Research Letters |
|---|---|
| Published | 2018 |
| Work type | article |
| Authors | Sebastian Scher |
| Citations | 303 (OpenAlex, at import time) |
| References | 23 |
| Model or method | Deep neural network (not further specified) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1029/2018gl080704 |
| Open access | hybrid |
| Keywords | weather forecasting, climate modeling, deep learning, neural network emulation, general circulation model |
Importance rating
real but narrower advance
Proof of concept emulating a simple general circulation model in a model world only; potential future speed/cost benefits for forecasting suggested but no real-world demonstration or scale stated.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|