Skip to main content

An overview of the Embeddings Based Analysis toolset

The Embeddings Based Analysis toolset contains tools for generating, updating, and analyzing embeddings derived from location-based features or raster data.

The toolset supports generating embeddings, using those embeddings to find similar features, and merging embeddings to create representations at different administrative levels, such as aggregating embeddings from zip codes to counties. By representing raw data as embeddings, it helps uncover meaningful patterns, relationships, and insights that are not easily visible in the original data.

Tools in the Embeddings Based Analysis toolset

Tool

Description

Extract Embeddings To Fields

Extracts vector embeddings stored as binary large object (BLOB) fields into individual numeric fields in a new output feature class.

Find Similar Features Using Embeddings

Performs large-scale similarity search on location and image data by comparing their embedding representations.

Generate Embeddings Using AI Models

Generates semantic embeddings for geospatial data using foundation models.

Merge Embeddings

Merges embeddings from an input embeddings feature class into target polygons based on the area of overlap.