Planette ECMWF IFS S2S Reforecast Data

The C3S seasonal forecast dataset provides global, daily, probabilistic forecasts of the Earth system, enabling users to assess the likelihood of future climate states. These forecasts are particularly valuable for studying slowly evolving climate patterns such as El Nino, La Nina, and the North Atlantic Oscillation (NAO), which can be predicted with greater skill than the chaotic atmosphere. This dataset is derived from the Copernicus Climate Change Service (C3S) archive and includes SEAS5 hindcasts (1981-2016) and forecasts (2017-present) at 1x1 global resolution. More models from the C3S archive will be updated as they are processed into cloud native format. The planette C3S archive stores this data in cloud native format for easy access and analysis.

The ERA5 archive provides a comprehensive record of global weather and climate from 1940 to present, with multiple temporal aggregations for flexible analysis. This dataset is derived from the ECMWF/Copernicus ERA5 reanalysis and includes daily means, 7-day rolling means, and monthly/seasonal aggregations at 0.25°×0.25° global resolution. The Planette ERA5 archive stores this data in cloud-native format (Zarr with icechunk) for efficient access and analysis. The dataset includes essential atmospheric variables at both surface and pressure levels, enabling a wide range of climate analyses, from daily weather patterns to long-term climate trends. Daily means are computed by averaging hourly ERA5 data, while longer temporal aggregations are derived from these daily means.

The Artificial Intelligence Forecasting System (AIFS) is a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). This is the non-ensemble configuration of AIFS that produces a single forecast trace. AIFS is trained on ECMWF's ERA5 re-analysis and ECMWF's operational numerical weather prediction (NWP) analyses. These datasets have been translated to cloud-optimized Icechunk Zarr format by dynamical.org. ECMWF AIFS Single forecast - Weather forecasts from the ECMWF Artificial Intelligence Forecasting System (AIFS) Single model. ECMWF AIFS Single forecast, virtual - Weather forecasts from the ECMWF Artificial Intelligence Forecasting System (AIFS) Single model.

This is an archive of pure AI-based weather prediction reforecasts produced collaboratively between the Cooperative Institute for Research in the Atmosphere (CIRA) and the NOAA Global Systems Laboratory (NOAA-GSL). Currently, FourCastNetv2-small, Pangu-Weather, and GraphCast are included, with more models to come. Each of these models has been initialized with both NOAA GFS (directories with no extension) and ECMWF IFS initial conditions (directories ending in "_IFS"). The datasets are updated with near-real-time data twice per day (00Z and 12Z initializations). FourCastNetv2-small and Pangu-Weather are availab[...]