Improved Weather Forecasting Using Neural Network Emulation for Radiation Parameterization
Problem
Radiation parameterization is computationally expensive in operational weather forecasting models, slowing forecasts.
Why it matters
It runs in the operational forecasting model of the Korea Meteorological Administration.
What the AI did
A neural network emulator, trained on large-scale datasets across 96 categories, replaced the radiation parameterization and was evaluated against infrequent use of the original scheme.
Results
60-fold radiation speedup; 87.26% decrease in total computation time; mean errors reduced 22-34% vs infrequent method; up to 36-fold additional speedup
Impact
Made operational radiation computation roughly 60 times faster while reducing errors versus the equal-cost alternative.
Record
| Venue | Journal of Advances in Modeling Earth Systems |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Hwan‐Jin Song, Soonyoung Roh |
| Citations | 44 (OpenAlex, at import time) |
| References | 61 |
| Model or method | Neural network emulator (96 categories: longwave-shortwave, months, land-ocean, clear-cloud) |
| Organization | Korea Meteorological Administration |
| Primary source | https://doi.org/10.1029/2021ms002609 |
| Open access | gold |
| Keywords | neural network emulator, radiation parameterization, weather forecasting, speedup, operational model |
Importance rating
significant — thousands to millions affected
Abstract states the emulator runs in the Korea Meteorological Administration's operational forecasting model, a national-scale service; large speedups with maintained forecast accuracy.
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
|