Improving Precipitation Forecasts with Convolutional Neural Networks
importance 6/10
partially solved
Meteorological Phenomena and Simulations weather forecasting stage: research
Problem
Dynamical model (West-WRF) daily precipitation forecasts over the US west coast contain systematic biases.
Why it matters
Accurate precipitation forecasts inform water supply and flood planning in the western US.
What the AI did
A modified U-Net CNN combining classification and dual regression was trained on 34 years of West-WRF reforecasts to identify and reduce forecast biases.
Results
On 4 unseen water years: 12.9-15.9% RMSE reduction and 2.7-3.4% Pearson correlation improvement.
Impact
CNN post-processing measurably improved precipitation forecasts on independent test years.
Record
| Venue | Weather and Forecasting |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Anirudhan Badrinath, Luca Delle Monache, Negin Hayatbini, Will Chapman, Forest Cannon, Marty Ralph |
| Citations | 26 (OpenAlex, at import time) |
| Model or method | modified U-Net convolutional neural network |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1175/waf-d-22-0002.1 |
| Open access | closed |
| Keywords | CNN, U-Net, precipitation forecast, bias correction, post-processing, machine learning |
Importance rating
6
significant — thousands to millions affected
Precipitation forecasts inform water supply and flood planning for the US west coast; abstract shows bias reduction but no quantified beneficiary scale.
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
|