Skip to main content
Wherobots is a cloud-native platform purpose-built for creating data products from spatial data. Built by the creators of Apache Sedona, Wherobots brings together spatial analytics, AI, and data management into a single, serverless platform.
Ready to get started? Create a free Community Edition account and run your first notebook in minutes.

​
Core products

Wherobots has the following core products, which when used together provide a comprehensive platform for spatial data processing, analytics, and AI:

WherobotsDB

Spatial analytics engineCloud-native, serverless engine for querying and processing geospatial data. Supports Spatial SQL, Python, and Scala with 300+ vector and raster functions. Apache Sedona-compatible.
  • Process vector and raster data at planetary scale
  • Up to 20x faster than alternatives
  • Open formats: Parquet, GeoParquet, GeoTIFF

GeoStats & Map Matching

Spatial algorithmsDetect spatial patterns with statistical algorithms and match GPS traces to road networks.

  • GeoStats: DBSCAN, Getis-Ord Gi*, Local Outlier Factor
  • Map Matching: GPS-to-road-network alignment

RasterFlow

Raster processing & inference engine Private PreviewEnd-to-end pipeline for large-scale raster workflows. Build mosaics from satellite imagery, run ML model inference, and vectorize results.

  • Pre-configured models for land cover, roads, canopy height
  • Bring your own data and models
  • Simple, high-level API

Havasu

Spatial table formatBuilt on Apache Iceberg, Havasu adds native support for geometry and raster data types. ACID transactions, schema evolution, time travel, and partition pruning for spatial workloads.
  • Geometry and raster column types
  • Spatial filter push-down
  • Iceberg-compatible tooling

​
WherobotsDB in depth

WherobotsDB is a cloud-native, serverless analytics engine optimized for geospatial workloads.
  • Modern, performant, and affordable: Run small to planetary-scale geospatial queries up to 20x faster, at a fraction of the cost. Only pay for what you use.
  • Unified vector and raster: Derive insights through spatial relationships between vector and raster data types in a single engine.
  • Apache Sedona compatible: Lift-and-shift Sedona workloads with confidence.
  • Popular languages: Spatial SQL, Python, and Scala. No esoteric tools required.
  • No vendor lock-in: Open formats (Parquet, GeoParquet), Apache Iceberg, and your own cloud storage.
  • Feature complete: 300+ vector and raster functions, notebooks for Exploratory Data Analysis (EDA), production-ready job runs, and a geospatial dataset catalog.
  • Serverless and secure: No infrastructure management. 99.5% runtime SLA with isolation by default for Enterprise Edition Organizations.
  • Automating spatial data processing: Schedule and automate ETL with Job Runs. Orchestrate pipelines with the Wherobots Airflow Provider.
  • Modernizing Spark + Sedona workloads: Eliminate cluster management, performance tuning, and indexing overhead. Lift-and-shift existing Sedona-on-Spark workloads.
  • Extracting insights from aerial imagery: RasterFlow integrates with WherobotsDB for end-to-end raster processing, ML inference, and analysis workflows.
The fastest way to start is to run an example notebook:
  1. Create a free Community Edition account.
  2. Start a runtime and open examples/Getting_Started/Part_1_Loading_Data.ipynb.
This notebook introduces the Wherobots Data Catalogs, Spatial SQL, and geospatial visualization.Already have existing workloads? Use WherobotsRunOperator to run them as Job Runs from Airflow.

​
GeoStats and Map Matching in depth

GeoStats and Map Matching make it easy to extract insights from geospatial data without needing to be a geospatial or infrastructure expert.
Distributed ML clustering algorithms for detecting hotspots, density patterns, and local outliers in vector data.Use cases: pedestrian activity hotspots, public health outbreak detection, strategic retail placement.Algorithms: DBSCAN, Getis-Ord Gi*, Local Outlier Factor.
sedona = SedonaContext.create(config)
clusters_df = dbscan(df, 0.3, 10, include_outliers=True)
GeoStats is available in all Organization Editions, including Community (free).
Offline distributed map matching — precisely align GPS or location-tracking coordinates to digital road networks.Use cases: traffic pattern analysis, optimized routing.
sedona = SedonaContext.create(config)
df_edge = matcher.load_osm("data/osm.xml", "[car]")
result_df = matcher.match(df_edge, df_paths, "geometry", "geometry")
Map Matching is available in all Organization Editions. Community Edition may experience latency with large datasets.
CapabilityCommunityProfessionalEnterprise
GeoStats (DBSCAN, LOF, Gi*)YesYesYes
Map MatchingYesYesYes
RasterFlowNoYes
Private Preview		Yes
Private Preview
Example notebooks:
CapabilityNotebook Path
DBSCANexamples/Analyzing_Data/Clustering_DBSCAN.ipynb
Local Outlier Factorexamples/Analyzing_Data/Local_Outlier_Factor.ipynb
Getis-Ord Gi*examples/Analyzing_Data/Getis_Ord_Gi*.ipynb
Map Matchingexamples/Analyzing_Data/GPS_Map_Matching.ipynb

​
How the products work together

Wherobots products can be used independently but are most effective when combined. Here are some common patterns for how customers use them together to build spatial data products:
WherobotsDB + Havasu + AirflowIngest raw spatial data from S3 or public sources, transform with Spatial SQL, and store in Havasu tables for efficient querying. Automate your ETL with the Wherobots Airflow Provider.Typical flow: Data Source → WherobotsDB (transform) → Havasu (store) → Downstream consumers
RasterFlow + WherobotsDBUse RasterFlow to build mosaics from satellite imagery, run ML inference (classification, segmentation, object detection) with pre-configured or custom models, and vectorize the results. Then analyze and enrich the output with WherobotsDB.Typical flow: Satellite imagery → RasterFlow (mosaic + infer + vectorize) → WherobotsDB (analyze vectors) → Visualization
WherobotsDB + GeoStatsLoad point-of-interest or movement data, enrich with spatial joins, and detect clusters, hotspots, or anomalies using GeoStats algorithms.Typical flow: Vector data → WherobotsDB (join + enrich) → GeoStats (cluster) → Insights
WherobotsDB + Map MatchingLoad GPS traces, match them to road network geometries, and analyze traffic patterns, congestion, or optimal routes.Typical flow: GPS data + road network → Map Matching → WherobotsDB (analyze) → Routing decisions

​
Key security properties

Wherobots is designed with security as a top priority. Wherobots has the SOC 2 Type 2 attestation. For the full details, see the Security Guide and Wherobots Trust Center.

​
Workload types

Wherobots has the following workload types, each optimized for different use cases:

Notebooks

Interactive Jupyter notebooks for exploratory data analysis, prototyping, and visualization

Job Runs

Scheduled or ad-hoc batch jobs for production ETL, analytics, and Machine Learning workloads

SQL Sessions

Submit Spatial SQL queries programmatically to run ad-hoc analyses or power applications with a spatial SQL backend

MCP Server

Natural language interface for exploring spatial data in VS Code Copilot. MCP Server query executions are logged as SQL Sessions.

​
Data connectivity

Wherobots connects to your data wherever it lives.

Managed Storage

Built-in storage included with every organization

Amazon S3

Bring your own S3 buckets with cross-account IAM roles

Unity Catalog

Access Databricks Unity Catalog Delta tables directly

​
Supported languages & formats

CategorySupported
LanguagesSpatial SQL, Python, Scala
Vector formatsParquet, GeoParquet, GeoJSON, Shapefile, GeoPackage, CSV
Raster formatsGeoTIFF, COG, NetCDF, Zarr
Table formatsApache Iceberg (Havasu), Delta Lake (via Unity Catalog)
Tile formatsPMTiles (vector tiles)
APIsSTAC, REST

​
Organization editions

Wherobots offers three tiers to match your needs:
FeatureCommunity (Free)ProfessionalEnterprise
WherobotsDBYesYesYes
GeoStatsYesYesYes
RasterFlow-Yes
Private Preview		Yes
Private Preview
GPU runtimes-YesYes
SSO / SAML--Yes
Dedicated support--Yes
For full details, see Organization Editions and Wherobots Pricing.

​
Next steps

Create an Account

Get started with a free Community Edition organization

Run a Notebook

Launch your first spatial analytics notebook

Explore Tutorials

Hands-on guides for every Wherobots capability