ERA5 data preprocessing steps

If we fetch data directly from copernicus climate data store using cdsapi than what are preprocessing steps are used before loading this weather data with model. Right now its not matching with model and sample data available on google cloud strorage are compatible and valid. So whats the actual difference in it.

Compare data fetched through cdsapi with the sample data stored in Google Cloud Storage, then trace the preprocessing used before the model loads each dataset. Document the actual transformations and the differences that explain why the CDS data does not match; no specific files or tests are named in the issue.

Written by the indexing model from the issue text.