Dynamic Selection of Ensemble Members in Multi-model Hydrometeorological Ensemble Forecasting
| Autor: | Sergey V. Kovalchuk, Alexey V. Krikunov |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Forecast error
Computer science Forecast skill computer.software_genre Machine learning Hydrometeorology Root-mean-square deviation Physics::Atmospheric and Oceanic Physics Selection (genetic algorithm) General Environmental Science Ensemble forecasting business.industry ensemble Forecast verification Ensemble learning Water level dynamic ensemble selection ComputingMilieux_GENERAL multi-Model Ensemble Forecasting classification General Earth and Planetary Sciences Data mining Artificial intelligence Consensus forecast business computer |
| Zdroj: | Procedia Computer Science. 66:220-227 |
| ISSN: | 1877-0509 |
| DOI: | 10.1016/j.procs.2015.11.026 |
| Popis: | Multi-model prediction ensembles show significant ability to improve forecasts. Nevertheless, the set of models in an ensemble is not always optimal. This work proposes a procedure that allows to select dynamically ensemble members for each forecast. Proposed procedure was evaluated for the task of the water level forecasting in the Baltic See. The regression-based estimation of ensemble forecasts errors was used to implement the selection procedure. Improvement of the forecast quality in terms of mean forecast RMS error and mean forecast skill score are demonstrated. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|