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>
The debiasing model applies to:
The debiasing solution is a hybrid approach depending on the proximity of the location to a weather station. If the location is within 1 km of a good station, then the station-specific model uses a quantile-mapping approach and applies a different bias adjustment depending on the daily temperature (warm vs cold day). Otherwise, the debiasing uses the generalized model that uses training data to learn the complex relationship between ERA5 and local environment to calculate a bias correction factor.