Using Artificial Neural Networks for Generating Probabilistic Subseasonal Precipitation Forecasts over California
Problem
NWP models have limited skill for subseasonal 7-day precipitation accumulations over California, and low signal-to-noise ratio makes reliable probabilistic forecasts hard.
Why it matters
Reliable subseasonal precipitation probabilities matter for planning in California.
What the AI did
An artificial neural network postprocessing framework links NWP ensemble forecasts to gridded observed precipitation to adjust category probabilities; a CNN extension takes images of large-scale predictors.
Results
not stated in source
Impact
Peer-reviewed framework proposed for probabilistic subseasonal precipitation forecasts.
Record
| Venue | Monthly Weather Review |
|---|---|
| Published | 2020 |
| Work type | article |
| Authors | Michael Scheuerer, Matthew Blaise Switanek, Rochelle Pauline Worsnop, Thomas M. Hamill |
| Citations | 82 (OpenAlex, at import time) |
| References | 60 |
| Model or method | ANN; CNN |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1175/mwr-d-20-0096.1 |
| Open access | bronze |
| Keywords | neural networks, precipitation forecasting, postprocessing, subseasonal, California, probabilistic |
Importance rating
real but narrower advance
Reliable subseasonal precipitation probabilities aid California planning, but abstract covers one region and notes low skill at weeks 3-4; narrower regional advance.
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
|