Probabilistic Forecasting of El Niño Using Neural Network Models
Problem
Statistical models predicting the El Niño–Southern Oscillation lacked direct estimation of predictive uncertainty for each forecast.
Why it matters
El Niño forecasts inform disaster preparedness, agriculture, and climate-sensitive decisions worldwide.
What the AI did
Gaussian density and quantile regression neural network ensembles produced probabilistic ENSO forecasts, directly predicting forecast uncertainty.
Results
Correlation skill r=0.5 at 12-month lead time (1963–2017); Gaussian density NN estimated predictive uncertainty better than a standard method (1982–2017).
Impact
Provided novel probabilistic ENSO forecasts with quantified uncertainty at long lead times.
Record
| Venue | Geophysical Research Letters |
|---|---|
| Published | 2020 |
| Work type | article |
| Authors | Paul Petersik, Henk A. Dijkstra |
| Citations | 52 (OpenAlex, at import time) |
| References | 43 |
| Model or method | Gaussian density neural network; quantile regression neural network |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1029/2019gl086423 |
| Open access | bronze |
| Keywords | El Niño, ENSO, probabilistic forecasting, neural networks, uncertainty estimation |
Importance rating
significant — thousands to millions affected
Probabilistic ENSO forecasts with quantified uncertainty at 12-month lead (r=0.5) add a genuinely new capability; ENSO informs global decisions, but abstract states no impact 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
|