Geospatial Foundation Models

An extension for accessing open source Geospatial Foundation Models: large-scale AI models trained on diverse geospatial data like satellite imagery, topographical maps, and other location-specific datasets, that encapsulate spatial information and relationships into dense representations in a multi-dimensional space (embeddings).

Google PDFM County Embeddings

Description

This component loads Google's PDFM Embeddings at the county level.

This component loads Google's Population Dynamics Foundation Model (PDFM) Embeddings at the county level. Google's (PDFM) Embeddings are condensed vector representations designed to encapsulate the complex, multidimensional interactions among human behaviors, environmental factors, and local contexts at specific locations.

These embeddings capture patterns in aggregated data such as search trends, busyness trends, and environmental conditions (maps, air quality, temperature), providing a rich, location-specific snapshot of how populations engage with their surroundings.

Output

• Output table: This component generates an output table with the PDFM embeddings at the county level.

Google PDFM ZCTA Embeddings

Description

This component loads Google's Population Dynamics Foundation Model (PDFM) Embeddings at the ZIP Code Tabulation Area (ZCTA) level. Google's (PDFM) Embeddings are condensed vector representations designed to encapsulate the complex, multidimensional interactions among human behaviors, environmental factors, and local contexts at specific locations.

These embeddings capture patterns in aggregated data such as search trends, busyness trends, and environmental conditions (maps, air quality, temperature), providing a rich, location-specific snapshot of how populations engage with their surroundings.

Output

• Output table: This component generates an output table with the PDFM embeddings at the ZCTA level.

Google Earth Engine Satellite Embeddings

This component loads Google Earth Engine's Satellite Embeddings summarized for input geometries.

The Satellite Embeddings dataset provides global, analysis-ready 64-dimensional vectors for each 10-meter land pixel, capturing annual temporal patterns of surface conditions using data from multiple Earth observation sources. Unlike traditional spectral bands, these vectors summarize complex, multi-source relationships in a more abstract but powerful format.

Input

• Input table: This component expects an input table with a geography column

Settings

• Geography column: A column that contains the geography data.

• From: The starting year of data to extract.

• To: The end year of data to extract.

• Reducer function: Function to summarize the raster data over each polygon (e.g., mean, min, max).

• Scale in meters: The scale of the source data in meters.

Output

• Output table: This component generates an output table with the Satellite Embeddings.