Spatial debiasing is a post-processing step applied to 0.25deg native forecasts and ERA5. It provides a better estimate for the weather for a specific ****lat/lon
or a list of grid points in a location_file
. Debiasing helps correct inherent biases present in spatial data like ERA5 Reanalysis, a source of training data for Salient’s models. Salient uses two methodologies depending on the timescale via an API debiasing option(debias=True
).
<aside>
📌
Note: Currently, debiased forecasts are not available in Cloudflare.
</aside>
Debiasing Model - Daily Resolution
The debiasing model applies to:
- Salient GEM
- Salient Blend Daily Downscale
- ERA 5 Daily Downscale
The debiasing solution uses a generalized model that uses training data to learn the complex relationship between ERA5 and local environment to calculate a bias correction factor.
- This is a post-processing model that downscales 0.25deg ERA5-style data to a specific location within a grid cell at a granularity of 100m
- Uses properties of the local environment like the land surface attributes and proximity to water, plus other features of the current weather, to debias the forecast
- This has the biggest impact in coastal regions, mountains, and urban areas, and has a bigger gain for daily high temperatures than for low temperatures
- Should only be used when validating against station data rather than gridded reanalysis data, since the outputs are specific to a precise coordinate
Supported Variables
- Temperature
- Miniumum Temperature
- Maximum Temperature
- HDD
- CDD
- Wind Speed 10m (coming in a future release)
- Precipitation (coming to a future release)