Referenz für das Kernschema

Field Name	Type	Mode	Description	Example
geo_id	STRING	NULLABLE	The primary identifier for the region. For S2 cell datasets, this is the S2 cell token represented as a hexadecimal string. Use this as your primary join key.	80ead45
geo_name	STRING	NULLABLE	The human-readable name for the region. Note: For S2 grid datasets, mathematical cells don't have standard names, so this column will contain the exact same token as geo_id.	80ead45
administrative_area_level_1_id	STRING	NULLABLE	The unique Google Maps Place ID for the top-level administrative boundary (for instance, State or Province).	ChIJPV4oX_65j4ARVW8IJ6IJUYs
administrative_area_level_1_name	STRING	NULLABLE	The human-readable name for the top-level boundary (for instance, 'California').	California
administrative_area_level_2_id	STRING	NULLABLE	The unique Google Maps Place ID for the secondary administrative boundary (for instance, County or District).	ChIJ1_-qb3ovlYAR5-g1FwCi4EQ
administrative_area_level_2_name	STRING	NULLABLE	The human-readable name for the secondary boundary (for instance, 'Tulare County').	Tulare County
features	FLOAT	REPEATED	The core 330-dimensional embedding vector, stored natively as an ARRAY<FLOAT64>. Each section corresponds to specific aggregated data signals.	[0.1042, -0.0345, 0.8841, ...]