FuXi: a cascade machine learning forecasting system for 15-day global weather forecast
Abstract Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has led to state-of-the-art ML models that have superior performance compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)’s high-resolution forecast (HRES), which is...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | npj Climate and Atmospheric Science |
| Online Access: | https://doi.org/10.1038/s41612-023-00512-1 |
| _version_ | 1827723717856198656 |
|---|---|
| author | Lei Chen Xiaohui Zhong Feng Zhang Yuan Cheng Yinghui Xu Yuan Qi Hao Li |
| author_facet | Lei Chen Xiaohui Zhong Feng Zhang Yuan Cheng Yinghui Xu Yuan Qi Hao Li |
| author_sort | Lei Chen |
| collection | DOAJ |
| description | Abstract Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has led to state-of-the-art ML models that have superior performance compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)’s high-resolution forecast (HRES), which is widely considered as the world’s best physics-based weather forecasting system. Specifically, ML models have outperformed HRES in 10-day forecasts with a spatial resolution of 0.25∘. However, the challenge remains in mitigating the accumulation of forecast errors for longer effective forecasts, such as achieving comparable performance to the ECMWF ensemble in 15-day forecasts. Despite various efforts to reduce accumulation errors, such as implementing autoregressive multi-time step loss, relying on a single model has been found to be insufficient for achieving optimal performance in both short and long lead times. Therefore, we present FuXi, a cascaded ML weather forecasting system that provides 15-day global forecasts at a temporal resolution of 6 hours and a spatial resolution of 0.25∘. FuXi is developed using 39 years of the ECMWF ERA5 reanalysis dataset. The performance evaluation demonstrates that FuXi has forecast performance comparable to ECMWF ensemble mean (EM) in 15-day forecasts. FuXi surpasses the skillful forecast lead time achieved by ECMWF HRES by extending the lead time for Z500 from 9.25 to 10.5 days and for T2M from 10 to 14.5 days. Moreover, the FuXi ensemble is created by perturbing initial conditions and model parameters, enabling it to provide forecast uncertainty and demonstrating promising results when compared to the ECMWF ensemble. |
| first_indexed | 2024-03-10T22:04:45Z |
| format | Article |
| id | doaj.art-c5f2a9cefa464ea88086df20dc6dd84e |
| institution | Directory Open Access Journal |
| issn | 2397-3722 |
| language | English |
| last_indexed | 2024-03-10T22:04:45Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Climate and Atmospheric Science |
| spelling | doaj.art-c5f2a9cefa464ea88086df20dc6dd84e2023-11-19T12:50:47ZengNature Portfolionpj Climate and Atmospheric Science2397-37222023-11-016111110.1038/s41612-023-00512-1FuXi: a cascade machine learning forecasting system for 15-day global weather forecastLei Chen0Xiaohui Zhong1Feng Zhang2Yuan Cheng3Yinghui Xu4Yuan Qi5Hao Li6Artificial Intelligence Innovation and Incubation Institute, Fudan UniversityArtificial Intelligence Innovation and Incubation Institute, Fudan UniversityKey Laboratory of Polar Atmosphere-ocean-ice System for Weather and Climate, Ministry of Education, Department of Atmospheric and Oceanic Sciences, Fudan UniversityArtificial Intelligence Innovation and Incubation Institute, Fudan UniversityArtificial Intelligence Innovation and Incubation Institute, Fudan UniversityArtificial Intelligence Innovation and Incubation Institute, Fudan UniversityArtificial Intelligence Innovation and Incubation Institute, Fudan UniversityAbstract Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has led to state-of-the-art ML models that have superior performance compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)’s high-resolution forecast (HRES), which is widely considered as the world’s best physics-based weather forecasting system. Specifically, ML models have outperformed HRES in 10-day forecasts with a spatial resolution of 0.25∘. However, the challenge remains in mitigating the accumulation of forecast errors for longer effective forecasts, such as achieving comparable performance to the ECMWF ensemble in 15-day forecasts. Despite various efforts to reduce accumulation errors, such as implementing autoregressive multi-time step loss, relying on a single model has been found to be insufficient for achieving optimal performance in both short and long lead times. Therefore, we present FuXi, a cascaded ML weather forecasting system that provides 15-day global forecasts at a temporal resolution of 6 hours and a spatial resolution of 0.25∘. FuXi is developed using 39 years of the ECMWF ERA5 reanalysis dataset. The performance evaluation demonstrates that FuXi has forecast performance comparable to ECMWF ensemble mean (EM) in 15-day forecasts. FuXi surpasses the skillful forecast lead time achieved by ECMWF HRES by extending the lead time for Z500 from 9.25 to 10.5 days and for T2M from 10 to 14.5 days. Moreover, the FuXi ensemble is created by perturbing initial conditions and model parameters, enabling it to provide forecast uncertainty and demonstrating promising results when compared to the ECMWF ensemble.https://doi.org/10.1038/s41612-023-00512-1 |
| spellingShingle | Lei Chen Xiaohui Zhong Feng Zhang Yuan Cheng Yinghui Xu Yuan Qi Hao Li FuXi: a cascade machine learning forecasting system for 15-day global weather forecast npj Climate and Atmospheric Science |
| title | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast |
| title_full | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast |
| title_fullStr | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast |
| title_full_unstemmed | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast |
| title_short | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast |
| title_sort | fuxi a cascade machine learning forecasting system for 15 day global weather forecast |
| url | https://doi.org/10.1038/s41612-023-00512-1 |
| work_keys_str_mv | AT leichen fuxiacascademachinelearningforecastingsystemfor15dayglobalweatherforecast AT xiaohuizhong fuxiacascademachinelearningforecastingsystemfor15dayglobalweatherforecast AT fengzhang fuxiacascademachinelearningforecastingsystemfor15dayglobalweatherforecast AT yuancheng fuxiacascademachinelearningforecastingsystemfor15dayglobalweatherforecast AT yinghuixu fuxiacascademachinelearningforecastingsystemfor15dayglobalweatherforecast AT yuanqi fuxiacascademachinelearningforecastingsystemfor15dayglobalweatherforecast AT haoli fuxiacascademachinelearningforecastingsystemfor15dayglobalweatherforecast |