AIFS -- ECMWF's data-driven forecasting system
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910558586929152 |
|---|---|
| author | Lang, Simon Alexe, Mihai Chantry, Matthew Dramsch, Jesper Pinault, Florian Raoult, Baudouin Clare, Mariana C. A. Lessig, Christian Maier-Gerber, Michael Magnusson, Linus Bouallègue, Zied Ben Nemesio, Ana Prieto Dueben, Peter D. Brown, Andrew Pappenberger, Florian Rabier, Florence |
| author_facet | Lang, Simon Alexe, Mihai Chantry, Matthew Dramsch, Jesper Pinault, Florian Raoult, Baudouin Clare, Mariana C. A. Lessig, Christian Maier-Gerber, Michael Magnusson, Linus Bouallègue, Zied Ben Nemesio, Ana Prieto Dueben, Peter D. Brown, Andrew Pappenberger, Florian Rabier, Florence |
| contents | Machine learning-based weather forecasting models have quickly emerged as a promising methodology for accurate medium-range global weather forecasting. Here, we introduce the Artificial Intelligence Forecasting System (AIFS), a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS is based on a graph neural network (GNN) encoder and decoder, and a sliding window transformer processor, and is trained on ECMWF's ERA5 re-analysis and ECMWF's operational numerical weather prediction (NWP) analyses. It has a flexible and modular design and supports several levels of parallelism to enable training on high-resolution input data. AIFS forecast skill is assessed by comparing its forecasts to NWP analyses and direct observational data. We show that AIFS produces highly skilled forecasts for upper-air variables, surface weather parameters and tropical cyclone tracks. AIFS is run four times daily alongside ECMWF's physics-based NWP model and forecasts are available to the public under ECMWF's open data policy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01465 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AIFS -- ECMWF's data-driven forecasting system Lang, Simon Alexe, Mihai Chantry, Matthew Dramsch, Jesper Pinault, Florian Raoult, Baudouin Clare, Mariana C. A. Lessig, Christian Maier-Gerber, Michael Magnusson, Linus Bouallègue, Zied Ben Nemesio, Ana Prieto Dueben, Peter D. Brown, Andrew Pappenberger, Florian Rabier, Florence Atmospheric and Oceanic Physics Machine learning-based weather forecasting models have quickly emerged as a promising methodology for accurate medium-range global weather forecasting. Here, we introduce the Artificial Intelligence Forecasting System (AIFS), a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS is based on a graph neural network (GNN) encoder and decoder, and a sliding window transformer processor, and is trained on ECMWF's ERA5 re-analysis and ECMWF's operational numerical weather prediction (NWP) analyses. It has a flexible and modular design and supports several levels of parallelism to enable training on high-resolution input data. AIFS forecast skill is assessed by comparing its forecasts to NWP analyses and direct observational data. We show that AIFS produces highly skilled forecasts for upper-air variables, surface weather parameters and tropical cyclone tracks. AIFS is run four times daily alongside ECMWF's physics-based NWP model and forecasts are available to the public under ECMWF's open data policy. |
| title | AIFS -- ECMWF's data-driven forecasting system |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2406.01465 |