Sold by: The Weather Company
Open data
|
Deployed on AWS
A zarr-formatted dataset of 1836 reforecast cases (approx. 5 years) from The Weather Company GRAF (Global high-Resolution Atmospheric Forecasting) model, a version of the National Center for Atmospheric Research (NCAR) Model for Predictions Across Scales (MPAS). GRAF is global, but the configuration for this reforecast had a mesh refinement to approx. 4 km over the US, Caribbean Basin, and Europe, and 15 km elsewhere. This model was designed to run much of its computation on graphical processing units, with this development assisted by NVIDIA. The 1836 cases (approx. 5 years) were generated from ECMWF reanalyses (ERA5) for initial condition dates spanning more than 20 years, 2004-2024. These dates of the chosen initial conditions mostly selected based on high-impact weather in the contiguous US (CONUS) and Caribbean. Sampling in this way spanned a wider range of interesting, high-impact weather scenarios than were there five contiguous years of data. GRAF reforecasts were mostly r[...]
Overview
A zarr-formatted dataset of 1836 reforecast cases (approx. 5 years) from The Weather Company GRAF (Global high-Resolution Atmospheric Forecasting) model, a version of the National Center for Atmospheric Research (NCAR) Model for Predictions Across Scales (MPAS). GRAF is global, but the configuration for this reforecast had a mesh refinement to approx. 4 km over the US, Caribbean Basin, and Europe, and 15 km elsewhere. This model was designed to run much of its computation on graphical processing units, with this development assisted by NVIDIA. The 1836 cases (approx. 5 years) were generated from ECMWF reanalyses (ERA5) for initial condition dates spanning more than 20 years, 2004-2024. These dates of the chosen initial conditions mostly selected based on high-impact weather in the contiguous US (CONUS) and Caribbean. Sampling in this way spanned a wider range of interesting, high-impact weather scenarios than were there five contiguous years of data. GRAF reforecasts were mostly run to +27 h lead time, assuming a 3-h for spin up followed by a full diurnal cycle. Data were saved in zarr format on the native model vertical coordinate. Most fields were saved at 15-min intervals, though several precipitation variables were saved at 5-min cadence.
Features and programs
Open Data Sponsorship Program
This dataset is part of the Open Data Sponsorship Program, an AWS program that covers the cost of storage for publicly available high-value cloud-optimized datasets.
Pricing
This is a publicly available data set. No subscription is required.
Legal
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
AWS Data Exchange (ADX)
AWS Data Exchange is a service that helps AWS easily share and manage data entitlements from other organizations at scale.
Open data resources
Available with or without an AWS account.
- How to use
- To access these resources, reference the Amazon Resource Name (ARN) using the AWS Command Line Interface (CLI). Learn more
- Description
- GRAF Reforecast dataset
- Resource type
- S3 bucket
- Amazon Resource Name (ARN)
- arn:aws:s3:::twc-graf-reforecast
- AWS region
- us-west-2
- AWS CLI access (No AWS account required)
- aws s3 ls --no-sign-request s3://twc-graf-reforecast/
Resources
Vendor resources
Support
Contact
Managed By
How to cite
GRAF Reforecast was accessed on DATE from https://registry.opendata.aws/graf-reforecast .
License
Similar products
Deep Learning based solution which predicts positive, negative and neutral sentiments from text.
The solution identifies items bought together frequently in a retail shopping cart.
Lexicon based NLP solution for predicting big 5 (OCEAN) personality traits and assigning trait scores to users.
This solution assesses a corpus of text to predict the following emotion classes: Anger, Fear, Joy, and Sadness.