Havasu Catalog. The knowledge lake for the physical world. Havasu streamlines discovery, access, and semantic understanding of physical-world data, models, jobs, and apps. Start from what Wherobots publishes in the open to what you and your team build in your own data lake. Explore the catalog Start for free The history of HavasuRead the story → From GeoSpark to the Havasu catalog GeoSparkApache SedonaHavasu formatIceberg GEOToday AI coding toolsSet up → Query Havasu from Claude, Cursor, or VS Code The Wherobots MCP server connects your AI coding tool to the catalog. Ask for a dataset and the agent writes and runs the spatial SQL. Open data and RasterFlow output on one map Parker Valley fields Lake Havasu City NAIP imagery 0.3 m, USDA Field boundaries RasterFlow · Fields of the World Labels field area, hectares NAIP imagery 0.3 m, USDA Buildings Overture Maps Roads Overture Maps Places Overture Maps 229 fields detected by RasterFlow on NAIP imagery, 25 km south of Lake Havasu 1,072 buildings, 956 roads and 682 places from Overture over NAIP NAIP · June 2023 The open catalog Datasets42 Models6 Solution notebooks9 Demo apps6 All providers All notebook topics Any format Vector Raster Tabular 63 results Open geospatial datasets 42 USDA NAIPRaster USDA NAIP aerial imagery High-resolution aerial imagery (30 cm to 1 m) of the continental United States from the USDA National Agriculture Imagery Program, flown state by state on a two-year cycle. Wherobots manages it as a RasterFlow built-in dataset: build red, green, blue, and near-infrared mosaics for any area of interest without staging imagery yourself. RasterFlow built-in dataset What is Earth observation data? → ESA Copernicus Sentinel-2Raster Sentinel-2 seasonal mosaics Cloud-filtered median composites of Sentinel-2 L2A imagery at 10 m, built on demand for any area of interest. Wherobots manages it as a RasterFlow built-in dataset: pick a planting season, harvest season, or custom date window, and RasterFlow selects scenes, masks clouds and shadows, and writes an analysis-ready mosaic without staging imagery yourself. RasterFlow built-in dataset What is change detection in satellite imagery? → CopernicusRaster Copernicus DEM GLO-30 Global 30 m digital surface model from the Copernicus programme, stored as raster tiles with footprints. wherobots_open_data.copernicus_dem.glo_30m 6 columnsApache Iceberg What is a digital elevation model? → ESA Copernicus Sentinel-2Imagery index Sentinel-2 L2A scene index STAC items for Sentinel-2 Level-2A scenes with footprints, acquisition times, cloud cover, and links to Cloud Optimized GeoTIFF bands. wherobots_open_data.sentinel2.l2a_source_items 20 columnsApache Iceberg What is a GeoTIFF? → OpenStreetMapVector OpenStreetMap nodes OpenStreetMap node features with tags. wherobots_pro_data.osm.nodes 9 columnsApache Iceberg OpenStreetMapVector OpenStreetMap ways OpenStreetMap way features such as roads, rivers, and building outlines, with tags. wherobots_pro_data.osm.ways 8 columnsApache Iceberg Overture Maps FoundationVector Overture buildings Global building footprints with height, floor count, and class where available. wherobots_open_data.overture_maps_foundation.buildings_building 24 columnsApache Iceberg What is a flood risk map? → Overture Maps FoundationVector Overture division areas Polygons for administrative divisions such as countries, regions, and localities. wherobots_open_data.overture_maps_foundation.divisions_division_area 14 columnsApache Iceberg Overture Maps FoundationVector Overture infrastructure Infrastructure features such as towers, bridges, and power lines from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_infrastructure 13 columnsApache Iceberg Data center site selection criteria → Overture Maps FoundationVector Overture transportation segments Road, rail, and water transportation segments with class, speed limits, and access rules. wherobots_open_data.overture_maps_foundation.transportation_segment 21 columnsApache Iceberg US Census BureauVector TIGER counties US county boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_county 19 columnsApache Iceberg Allen Institute for AI (Satlas)Raster Satlas offshore infrastructure Sentinel-2 image tiles from Allen AI's Satlas project over coastal and offshore areas used to map wind turbines and platforms, stored as multiband rasters with footprints. wherobots_pro_data.satlas.offshore_satlas 4 columnsApache Iceberg What is geospatial AI? → Allen Institute for AI (Satlas)Raster Satlas solar farms Sentinel-2 image tiles from Allen AI's Satlas project over solar farm areas in Arizona and southern Nevada, stored as multiband rasters with footprints. wherobots_pro_data.satlas.solar_satlas 4 columnsApache Iceberg What is geospatial AI? → Google and MicrosoftVector Google and Microsoft Open Buildings Combined building footprints from the Google Open Buildings and Microsoft Building Footprints datasets. wherobots_pro_data.google_microsoft.open_buildings 6 columnsApache Iceberg What is catastrophe modeling? → NASA and METIRaster ASTER Global DEM v3 (30 m) Global digital elevation model at 30 m resolution, stored as raster tiles with a footprint for each tile. wherobots_open_data.aster_gdem.v3_30m 6 columnsApache Iceberg What is a digital elevation model? → Meta and WRIRaster Meta Global Canopy Height v2 Global tree canopy height map (CHMv2) from Meta and the World Resources Institute, made with machine learning on high-resolution satellite imagery and stored as raster tiles with a footprint for each tile. wherobots_open_data.meta_canopy_height.global_v2 6 columnsApache Iceberg NOAA National Weather ServiceVector NWS watches and warnings National Weather Service watch and warning polygons with event type, severity, and effective times. wherobots_open_data.noaa.nws_watch_warnings 26 columnsApache Iceberg What is the HRRR model? → NYC Taxi and Limousine CommissionVector NYC yellow taxi trips 2009 to 2010 New York City yellow taxi trip records with pickup and dropoff points, times, and fares. wherobots_pro_data.nyc_taxi.yellow_2009_2010 20 columnsApache Iceberg OpenStreetMapVector OpenStreetMap postal codes Postal code areas from OpenStreetMap. wherobots_pro_data.osm.postal_codes 3 columnsApache Iceberg Overture Maps FoundationVector Overture addresses Address points from the Overture Maps addresses theme. wherobots_open_data.overture_maps_foundation.addresses_address 12 columnsApache Iceberg Overture Maps FoundationVector Overture bathymetry Ocean depth polygons from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_bathymetry 7 columnsApache Iceberg Overture Maps FoundationVector Overture building parts Parts of buildings with their own height and shape, linked to a parent building. wherobots_open_data.overture_maps_foundation.buildings_building_part 22 columnsApache Iceberg Overture Maps FoundationVector Overture division boundaries Boundary lines between administrative divisions. wherobots_open_data.overture_maps_foundation.divisions_division_boundary 15 columnsApache Iceberg Overture Maps FoundationVector Overture divisions Administrative and named places from countries to neighborhoods, as points with hierarchy. wherobots_open_data.overture_maps_foundation.divisions_division 21 columnsApache Iceberg Overture Maps FoundationVector Overture geocodes Geocoding table built by Wherobots from Overture Maps addresses and places. wherobots_open_data.overture_maps_foundation.geocodes 4 columnsApache Iceberg Overture Maps FoundationVector Overture land Land features such as islands, peaks, and cliffs from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_land 13 columnsApache Iceberg Overture Maps FoundationVector Overture land cover Global land cover polygons from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_land_cover 7 columnsApache Iceberg What is land cover classification? → Overture Maps FoundationVector Overture land use Land use polygons such as residential, agricultural, and protected areas from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_land_use 13 columnsApache Iceberg Land cover vs land use → Overture Maps FoundationVector Overture places Global points of interest with names, categories, and confidence scores. wherobots_open_data.overture_maps_foundation.places_place 16 columnsApache Iceberg What is POI data? → Overture Maps FoundationVector Overture places with drive-time isochrones Overture places with 5, 10, 15, and 20 minute isochrone polygons computed by Wherobots. wherobots_pro_data.overture_maps_foundation.overture_places_with_isochrones 18 columnsApache Iceberg What is POI data? → Overture Maps FoundationVector Overture road network graph Routable road network edge list built by Wherobots from Overture transportation data. wherobots_pro_data.overture_maps_foundation.road_network 8 columnsApache Iceberg Overture Maps FoundationVector Overture transportation connectors Points where transportation segments join, for building routable networks. wherobots_open_data.overture_maps_foundation.transportation_connector 5 columnsApache Iceberg Overture Maps FoundationVector Overture water Oceans, lakes, rivers, and other water features from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_water 13 columnsApache Iceberg US Census BureauTabular ACS 5-year estimates American Community Survey 5-year estimates by geography and variable. wherobots_open_data.us_census.acs_5yr_estimates 7 columnsApache Iceberg US Census BureauTabular ACS 5-year variables Variable definitions for the American Community Survey 5-year estimates. wherobots_open_data.us_census.acs_5yr_variables 4 columnsApache Iceberg US Census BureauVector TIGER block groups US Census block group boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_blockgroup 14 columnsApache Iceberg US Census BureauVector TIGER census tracts US census tract boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_tract 14 columnsApache Iceberg US Census BureauVector TIGER states US state boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_state 16 columnsApache Iceberg US Census BureauVector TIGER ZIP Code Tabulation Areas US ZIP Code Tabulation Area boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_zcta 11 columnsApache Iceberg US weather recordsVector US weather events Weather event records by airport weather station. wherobots_pro_data.weather.weather_events 15 columnsApache Iceberg What is the HRRR model? → US weather recordsVector US wildfires US wildfire records with discovery dates, causes, sizes, and locations. wherobots_pro_data.weather.wild_fires 39 columnsApache Iceberg What is catastrophe modeling? → USGS LandsatRaster Landsat surface temperature Landsat 8 and 9 Collection 2 surface temperature scenes, tiled at 1024 x 1024 pixels for fast spatial filtering. wherobots_pro_data.landsat.landsat_surface_temperature_1024x1024_outdb 11 columnsApache Iceberg What is Landsat? → RasterFlow models 6 Wherobots RasterFlowModel Fields of the World Detect agricultural field boundaries from Sentinel-2 imagery and segment crop fields across counties and regions, then convert predictions to vector geometries. Agricultural field boundary segmentationOutput table What is satellite imagery analysis? → Wherobots RasterFlowModel Tile2Net Identify sidewalks, crosswalks, and pedestrian pathways from high-resolution aerial imagery for urban planning and accessibility analysis. Sidewalk and crosswalk segmentationOutput table What is satellite imagery analysis? → Wherobots RasterFlowModel Meta CHM v1 (canopy height) Predict tree canopy heights from aerial imagery to monitor forest health and vegetation structure and support conservation and urban forestry. Tree canopy height estimationOutput table What is LiDAR data? → Wherobots RasterFlowModel ChesapeakeRSC Identify roads, especially in rural environments, to map road networks and detect changes that keep maps current. Road segmentation, including roads under tree coverOutput table What is satellite imagery analysis? → Wherobots RasterFlowModel SAM3 (text-prompted detection) Detect objects from a text prompt with Meta's Segment Anything Model 3 and return georeferenced geometries, with no separate vectorization step. Object detection from a natural language promptOutput table What is satellite imagery analysis? → Wherobots RasterFlowModel Bring your own model Export a custom PyTorch model to a RasterFlow-compatible format, register it, and run it as an inference task over large mosaics alongside the built-in models. Run a custom PyTorch model at scale Solution notebooks 9 WherobotsNotebook Detecting field boundaries with RasterFlow Detect agricultural field boundaries from satellite imagery with RasterFlow and the Fields of the World model, then vectorize the results for your area of interest. Analyzing Data WherobotsNotebook Detecting roads with RasterFlow Detect roads from aerial imagery with RasterFlow and the ChesapeakeRSC model, then vectorize the results for your area of interest. Analyzing Data WherobotsNotebook Detecting sidewalks with RasterFlow Detect sidewalks from aerial imagery with RasterFlow and the Tile2Net model, then vectorize the results for your area of interest. Analyzing Data WherobotsNotebook Estimating canopy height with RasterFlow Estimate canopy height from aerial imagery with RasterFlow and the Meta and World Resources Institute Canopy Height model (Meta CHM v1). Analyzing Data WherobotsNotebook Part 1: Loading Data Getting started, part 1: hands-on geospatial analysis in Wherobots, combining SQL, Python, and cloud-native data integration. Getting Started WherobotsNotebook Part 2: Reading Spatial Files Getting started, part 2: load raster and vector data in a variety of formats from cloud storage and Wherobots managed storage. Getting Started WherobotsNotebook Part 3: Accelerating Geospatial Datasets Getting started, part 3: manage, cluster, and export large geospatial datasets for high-performance analysis and downstream use. Getting Started WherobotsNotebook Part 4: Spatial Joins Getting started, part 4: combine datasets by their spatial relationships with spatial joins, using Python and the DataFrame API. Getting Started WherobotsNotebook Reading STAC data Load SpatioTemporal Asset Catalog (STAC) collections into WherobotsDB with the STAC reader and API. Reading and Writing Data Demo apps 6 Demo built with AI coding toolsDemo app Texas drone-delivery nest siting Shortlists candidate drone-delivery nest sites across Texas by weighing the people each site reaches within 10 km against FAA LAANC airspace ceilings and obstacles. Live demo Demo built with AI coding toolsDemo app Colorado property risk explorer Property-and-casualty exposure to five perils across every building and parcel in Colorado, from statewide hexes down to individual buildings. Live demo What is probable maximum loss? → Demo built with AI coding toolsDemo app California signal quality explorer Statewide map of California mobile signal quality that separates capacity-limited areas from coverage gaps, with population and income lenses. Live demo Demo built with AI coding toolsDemo app Pacific Northwest corridor resilience A gorge-fire scenario played out on real Pacific Northwest road and rail geometry, showing which freight corridors degrade and which communities lose every way in. Work in progress Community demoDemo app Australia AI data center siting A national suitability screen for AI data center siting across Australia, with a ranked shortlist of candidate sites and a what-if weighting sandbox. Live demo Demo built with AI coding toolsDemo app California grid wildfire exposure Transmission spans in the PG&E area scored 0 to 9 for environmental wildfire exposure from fuels, vegetation vigor, canopy, slope, and nearby structures. Work in progress Nothing matches. Clear the search or filters. The history of HavasuFrom GeoSpark and Apache Sedona to the Havasu catalog Arizona State UniversityGeoSparkResearch by Jia Yu and Mo Sarwat on distributed spatial processing for Apache Spark. Apache Software FoundationApache SedonaGeoSpark becomes Apache Sedona, now a top-level Apache project. 2023Havasu table formatWherobots extends Apache Iceberg with geometry and raster types, spatial statistics, and filter push-down. 2024Iceberg GEOSpatial types become part of the Apache Iceberg spec, with contributors from Wherobots, CARTO, Planet, Apple, Databricks, Snowflake, and others. TodayHavasu knowledge lakeThe name returns as the knowledge lake for the physical world: one catalog for the data, models, jobs, and apps that Wherobots and its customers build. × Havasu Catalog FAQ The Havasu Catalog What is the Havasu Catalog? The Havasu Catalog is an open data catalog of geospatial datasets, RasterFlow models, solution notebooks, and demo apps from Wherobots. Each dataset lists its schema and sample SQL, so a team can query it in Wherobots right away. Learn more about the Havasu Catalog. What is geospatial data? Geospatial data records where things are on Earth. Vector data covers features such as buildings, roads, and boundaries, and raster data covers grids such as satellite and aerial imagery. The Havasu Catalog holds both. Read the introduction to spatial data. Which geospatial data sources does the catalog include? The Havasu Catalog holds 63 entries, including 42 geospatial datasets. Sources include the Overture Maps Foundation, the US Census Bureau, OpenStreetMap, ESA Copernicus Sentinel-2, USDA NAIP aerial imagery, and USGS Landsat. Do I need to download data to use the catalog? No. Every Open Data table in Havasu is queryable in place with spatial SQL in WherobotsDB, so a first analysis starts without a download. Can my own tables sit next to the open datasets? Yes. Your own spatial tables and the open geospatial datasets share one catalog, connected through Unity Catalog, AWS Glue, or any Apache Iceberg catalog. What is Apache Iceberg, and how does Havasu relate to it? Apache Iceberg is an open table format for large analytic tables in cloud object storage. Havasu began in 2023 as the Wherobots spatial table format that extended Iceberg with geometry and raster types, and Iceberg v3 now includes native geometry and geography types. Read about Iceberg geospatial types. How is Havasu related to Apache Sedona? Wherobots was founded by the original creators of Apache Sedona, which began as GeoSpark research at Arizona State University. The Havasu Catalog continues that lineage for data, models, and apps. Read the history of the Havasu Catalog. How do I start using the Havasu Catalog? Start a Wherobots free trial at login.cloud.wherobots.com and query any Open Data table in Havasu. Continued access after the trial requires the Professional tier or above. The solution notebooks in the catalog and the Wherobots developer docs give worked starting points. Datasets in the Havasu Catalog What is Overture Maps? Overture Maps is open map data published by the Overture Maps Foundation, a Linux Foundation project founded by Amazon Web Services, Meta, Microsoft, and TomTom. It covers buildings, places, transportation, addresses, administrative divisions, and base layers such as land and water. The Havasu Catalog lists each Overture theme as its own table, from buildings and places to the road network graph. What is NAIP imagery? NAIP is the National Agriculture Imagery Program, run by the USDA Farm Service Agency. It captures aerial imagery of the continental United States during the agricultural growing season, typically at 60 cm to 1 m resolution with red, green, blue, and near-infrared bands. In the Havasu Catalog, NAIP is a RasterFlow managed dataset that models such as Fields of the World run on. What is Sentinel-2, and what is its resolution? Sentinel-2 is the European Space Agency Copernicus mission for multispectral Earth imagery. It records 13 spectral bands at 10 m, 20 m, and 60 m resolution and revisits each location about every five days. The Havasu Catalog includes Sentinel-2 seasonal mosaics and an index of Level-2A surface reflectance scenes. What is OpenStreetMap? OpenStreetMap is a free, editable map of the world built by volunteer contributors and published under the Open Database License. The Havasu Catalog includes OpenStreetMap nodes, ways, and postal codes as tables. What is a census tract? A census tract is a small statistical subdivision of a US county, defined by the Census Bureau and usually home to 1,200 to 8,000 people. The Havasu Catalog includes TIGER boundaries for states, counties, census tracts, block groups, and ZIP Code Tabulation Areas. What is the American Community Survey? The American Community Survey (ACS) is an ongoing US Census Bureau survey of population, housing, income, and commuting. Its 5-year estimates cover every census tract and block group. The Havasu Catalog includes ACS 5-year estimates with a variables table that explains each column. What is a digital elevation model (DEM)? A digital elevation model is a raster grid in which each cell stores the height of the Earth surface. The Havasu Catalog includes two global DEMs at 30 m resolution: Copernicus DEM GLO-30 and NASA and METI ASTER Global DEM v3. What are Google and Microsoft Open Buildings? Google Open Buildings and Microsoft Global ML Building Footprints are building outlines detected from satellite imagery with machine learning. The Havasu Catalog combines both into one building footprint table. What is Landsat? Landsat is the joint NASA and USGS Earth observation program, which has imaged the planet since 1972. The Havasu Catalog includes Landsat surface temperature, derived from the thermal infrared bands. RasterFlow and models What is RasterFlow? RasterFlow is the Wherobots image preparation and inference engine for large-scale raster processing and geospatial machine learning. It builds mosaics from satellite and aerial imagery, runs computer vision models over them for semantic segmentation, regression, and change detection, and vectorizes the results. RasterFlow is in Public Preview for Professional, Innovation, and Enterprise organizations. Get started with RasterFlow. Which models does RasterFlow include? RasterFlow includes five pre-trained, open-source models: SAM3 for text-prompted object detection, Fields of the World for agricultural field boundaries from Sentinel-2, Tile2Net for sidewalks and crosswalks, Meta CHM v1 for tree canopy height, and ChesapeakeRSC for rural roads. Each model in the Havasu Catalog links to a sample output table. See the RasterFlow models. What is SAM3, and how does RasterFlow use it? SAM3 is Meta’s Segment Anything Model 3, which detects and segments objects from a text prompt such as “roofs”. RasterFlow runs SAM3 over aerial imagery such as 30 cm NAIP and returns georeferenced polygons or bounding boxes with confidence scores, with no separate vectorization step. Read how SAM3 maps building footprints. Can I run my own PyTorch model in RasterFlow? Yes. Export the model with torch.export to a PT2 file, register it, and RasterFlow runs it as an inference task over a mosaic at scale, alongside the built-in models. Follow the bring-your-own-model notebook. What is a PT2 file? A PT2 file is a PyTorch 2 archive created with torch.export. One file holds the exported model, and it can also carry configuration, hyperparameters, and preprocessing transforms. RasterFlow loads PT2 models from Amazon S3 or Hugging Face, and the built-in models are published as PT2 files in the Wherobots Hugging Face collection. Why does RasterFlow use the PT2 model format? A PT2 archive can be exported on a CPU and loaded onto a GPU at runtime. It can be compiled for faster execution on CUDA, AMD, or Intel GPUs, and it stores the model metadata and transforms in a standard place, so one file moves from training to large-scale inference. Can I use my own imagery with RasterFlow? Yes. RasterFlow builds mosaics from your own Cloud Optimized GeoTIFFs through a GDAL Raster Tile Index, including imagery found through a STAC catalog, in addition to the built-in NAIP and Sentinel-2 datasets. Follow the bring-your-own-rasters notebook. What formats does RasterFlow output? RasterFlow writes mosaics and model predictions as Zarr stores and writes vectorized results as GeoParquet, which joins with vector data in WherobotsDB. Wherobots-GL shows mosaics, prediction stores, and vectorized results on one map in Wherobots Cloud or a notebook. How is RasterFlow priced? RasterFlow bills four tasks, mosaicking, inference, building multiscales, and vectorization, in RasterFlow Spatial Units. Mosaicking and inference apply a complexity factor that varies by dataset and by model. See Wherobots pricing. Start in minutes Run your first spatial query. Start a free trial and query every Open Data table in Havasu, with nothing to download. Continued access after the trial is included in the Professional tier and above. Start for free Talk to our team
USDA NAIPRaster USDA NAIP aerial imagery High-resolution aerial imagery (30 cm to 1 m) of the continental United States from the USDA National Agriculture Imagery Program, flown state by state on a two-year cycle. Wherobots manages it as a RasterFlow built-in dataset: build red, green, blue, and near-infrared mosaics for any area of interest without staging imagery yourself. RasterFlow built-in dataset What is Earth observation data? →
ESA Copernicus Sentinel-2Raster Sentinel-2 seasonal mosaics Cloud-filtered median composites of Sentinel-2 L2A imagery at 10 m, built on demand for any area of interest. Wherobots manages it as a RasterFlow built-in dataset: pick a planting season, harvest season, or custom date window, and RasterFlow selects scenes, masks clouds and shadows, and writes an analysis-ready mosaic without staging imagery yourself. RasterFlow built-in dataset What is change detection in satellite imagery? →
CopernicusRaster Copernicus DEM GLO-30 Global 30 m digital surface model from the Copernicus programme, stored as raster tiles with footprints. wherobots_open_data.copernicus_dem.glo_30m 6 columnsApache Iceberg What is a digital elevation model? →
ESA Copernicus Sentinel-2Imagery index Sentinel-2 L2A scene index STAC items for Sentinel-2 Level-2A scenes with footprints, acquisition times, cloud cover, and links to Cloud Optimized GeoTIFF bands. wherobots_open_data.sentinel2.l2a_source_items 20 columnsApache Iceberg What is a GeoTIFF? →
OpenStreetMapVector OpenStreetMap nodes OpenStreetMap node features with tags. wherobots_pro_data.osm.nodes 9 columnsApache Iceberg
OpenStreetMapVector OpenStreetMap ways OpenStreetMap way features such as roads, rivers, and building outlines, with tags. wherobots_pro_data.osm.ways 8 columnsApache Iceberg
Overture Maps FoundationVector Overture buildings Global building footprints with height, floor count, and class where available. wherobots_open_data.overture_maps_foundation.buildings_building 24 columnsApache Iceberg What is a flood risk map? →
Overture Maps FoundationVector Overture division areas Polygons for administrative divisions such as countries, regions, and localities. wherobots_open_data.overture_maps_foundation.divisions_division_area 14 columnsApache Iceberg
Overture Maps FoundationVector Overture infrastructure Infrastructure features such as towers, bridges, and power lines from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_infrastructure 13 columnsApache Iceberg Data center site selection criteria →
Overture Maps FoundationVector Overture transportation segments Road, rail, and water transportation segments with class, speed limits, and access rules. wherobots_open_data.overture_maps_foundation.transportation_segment 21 columnsApache Iceberg
US Census BureauVector TIGER counties US county boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_county 19 columnsApache Iceberg
Allen Institute for AI (Satlas)Raster Satlas offshore infrastructure Sentinel-2 image tiles from Allen AI's Satlas project over coastal and offshore areas used to map wind turbines and platforms, stored as multiband rasters with footprints. wherobots_pro_data.satlas.offshore_satlas 4 columnsApache Iceberg What is geospatial AI? →
Allen Institute for AI (Satlas)Raster Satlas solar farms Sentinel-2 image tiles from Allen AI's Satlas project over solar farm areas in Arizona and southern Nevada, stored as multiband rasters with footprints. wherobots_pro_data.satlas.solar_satlas 4 columnsApache Iceberg What is geospatial AI? →
Google and MicrosoftVector Google and Microsoft Open Buildings Combined building footprints from the Google Open Buildings and Microsoft Building Footprints datasets. wherobots_pro_data.google_microsoft.open_buildings 6 columnsApache Iceberg What is catastrophe modeling? →
NASA and METIRaster ASTER Global DEM v3 (30 m) Global digital elevation model at 30 m resolution, stored as raster tiles with a footprint for each tile. wherobots_open_data.aster_gdem.v3_30m 6 columnsApache Iceberg What is a digital elevation model? →
Meta and WRIRaster Meta Global Canopy Height v2 Global tree canopy height map (CHMv2) from Meta and the World Resources Institute, made with machine learning on high-resolution satellite imagery and stored as raster tiles with a footprint for each tile. wherobots_open_data.meta_canopy_height.global_v2 6 columnsApache Iceberg
NOAA National Weather ServiceVector NWS watches and warnings National Weather Service watch and warning polygons with event type, severity, and effective times. wherobots_open_data.noaa.nws_watch_warnings 26 columnsApache Iceberg What is the HRRR model? →
NYC Taxi and Limousine CommissionVector NYC yellow taxi trips 2009 to 2010 New York City yellow taxi trip records with pickup and dropoff points, times, and fares. wherobots_pro_data.nyc_taxi.yellow_2009_2010 20 columnsApache Iceberg
OpenStreetMapVector OpenStreetMap postal codes Postal code areas from OpenStreetMap. wherobots_pro_data.osm.postal_codes 3 columnsApache Iceberg
Overture Maps FoundationVector Overture addresses Address points from the Overture Maps addresses theme. wherobots_open_data.overture_maps_foundation.addresses_address 12 columnsApache Iceberg
Overture Maps FoundationVector Overture bathymetry Ocean depth polygons from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_bathymetry 7 columnsApache Iceberg
Overture Maps FoundationVector Overture building parts Parts of buildings with their own height and shape, linked to a parent building. wherobots_open_data.overture_maps_foundation.buildings_building_part 22 columnsApache Iceberg
Overture Maps FoundationVector Overture division boundaries Boundary lines between administrative divisions. wherobots_open_data.overture_maps_foundation.divisions_division_boundary 15 columnsApache Iceberg
Overture Maps FoundationVector Overture divisions Administrative and named places from countries to neighborhoods, as points with hierarchy. wherobots_open_data.overture_maps_foundation.divisions_division 21 columnsApache Iceberg
Overture Maps FoundationVector Overture geocodes Geocoding table built by Wherobots from Overture Maps addresses and places. wherobots_open_data.overture_maps_foundation.geocodes 4 columnsApache Iceberg
Overture Maps FoundationVector Overture land Land features such as islands, peaks, and cliffs from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_land 13 columnsApache Iceberg
Overture Maps FoundationVector Overture land cover Global land cover polygons from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_land_cover 7 columnsApache Iceberg What is land cover classification? →
Overture Maps FoundationVector Overture land use Land use polygons such as residential, agricultural, and protected areas from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_land_use 13 columnsApache Iceberg Land cover vs land use →
Overture Maps FoundationVector Overture places Global points of interest with names, categories, and confidence scores. wherobots_open_data.overture_maps_foundation.places_place 16 columnsApache Iceberg What is POI data? →
Overture Maps FoundationVector Overture places with drive-time isochrones Overture places with 5, 10, 15, and 20 minute isochrone polygons computed by Wherobots. wherobots_pro_data.overture_maps_foundation.overture_places_with_isochrones 18 columnsApache Iceberg What is POI data? →
Overture Maps FoundationVector Overture road network graph Routable road network edge list built by Wherobots from Overture transportation data. wherobots_pro_data.overture_maps_foundation.road_network 8 columnsApache Iceberg
Overture Maps FoundationVector Overture transportation connectors Points where transportation segments join, for building routable networks. wherobots_open_data.overture_maps_foundation.transportation_connector 5 columnsApache Iceberg
Overture Maps FoundationVector Overture water Oceans, lakes, rivers, and other water features from the Overture Maps base theme. wherobots_open_data.overture_maps_foundation.base_water 13 columnsApache Iceberg
US Census BureauTabular ACS 5-year estimates American Community Survey 5-year estimates by geography and variable. wherobots_open_data.us_census.acs_5yr_estimates 7 columnsApache Iceberg
US Census BureauTabular ACS 5-year variables Variable definitions for the American Community Survey 5-year estimates. wherobots_open_data.us_census.acs_5yr_variables 4 columnsApache Iceberg
US Census BureauVector TIGER block groups US Census block group boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_blockgroup 14 columnsApache Iceberg
US Census BureauVector TIGER census tracts US census tract boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_tract 14 columnsApache Iceberg
US Census BureauVector TIGER states US state boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_state 16 columnsApache Iceberg
US Census BureauVector TIGER ZIP Code Tabulation Areas US ZIP Code Tabulation Area boundaries from TIGER/Line. wherobots_open_data.us_census.tiger_zcta 11 columnsApache Iceberg
US weather recordsVector US weather events Weather event records by airport weather station. wherobots_pro_data.weather.weather_events 15 columnsApache Iceberg What is the HRRR model? →
US weather recordsVector US wildfires US wildfire records with discovery dates, causes, sizes, and locations. wherobots_pro_data.weather.wild_fires 39 columnsApache Iceberg What is catastrophe modeling? →
USGS LandsatRaster Landsat surface temperature Landsat 8 and 9 Collection 2 surface temperature scenes, tiled at 1024 x 1024 pixels for fast spatial filtering. wherobots_pro_data.landsat.landsat_surface_temperature_1024x1024_outdb 11 columnsApache Iceberg What is Landsat? →
Wherobots RasterFlowModel Fields of the World Detect agricultural field boundaries from Sentinel-2 imagery and segment crop fields across counties and regions, then convert predictions to vector geometries. Agricultural field boundary segmentationOutput table What is satellite imagery analysis? →
Wherobots RasterFlowModel Tile2Net Identify sidewalks, crosswalks, and pedestrian pathways from high-resolution aerial imagery for urban planning and accessibility analysis. Sidewalk and crosswalk segmentationOutput table What is satellite imagery analysis? →
Wherobots RasterFlowModel Meta CHM v1 (canopy height) Predict tree canopy heights from aerial imagery to monitor forest health and vegetation structure and support conservation and urban forestry. Tree canopy height estimationOutput table What is LiDAR data? →
Wherobots RasterFlowModel ChesapeakeRSC Identify roads, especially in rural environments, to map road networks and detect changes that keep maps current. Road segmentation, including roads under tree coverOutput table What is satellite imagery analysis? →
Wherobots RasterFlowModel SAM3 (text-prompted detection) Detect objects from a text prompt with Meta's Segment Anything Model 3 and return georeferenced geometries, with no separate vectorization step. Object detection from a natural language promptOutput table What is satellite imagery analysis? →
Wherobots RasterFlowModel Bring your own model Export a custom PyTorch model to a RasterFlow-compatible format, register it, and run it as an inference task over large mosaics alongside the built-in models. Run a custom PyTorch model at scale
WherobotsNotebook Detecting field boundaries with RasterFlow Detect agricultural field boundaries from satellite imagery with RasterFlow and the Fields of the World model, then vectorize the results for your area of interest. Analyzing Data
WherobotsNotebook Detecting roads with RasterFlow Detect roads from aerial imagery with RasterFlow and the ChesapeakeRSC model, then vectorize the results for your area of interest. Analyzing Data
WherobotsNotebook Detecting sidewalks with RasterFlow Detect sidewalks from aerial imagery with RasterFlow and the Tile2Net model, then vectorize the results for your area of interest. Analyzing Data
WherobotsNotebook Estimating canopy height with RasterFlow Estimate canopy height from aerial imagery with RasterFlow and the Meta and World Resources Institute Canopy Height model (Meta CHM v1). Analyzing Data
WherobotsNotebook Part 1: Loading Data Getting started, part 1: hands-on geospatial analysis in Wherobots, combining SQL, Python, and cloud-native data integration. Getting Started
WherobotsNotebook Part 2: Reading Spatial Files Getting started, part 2: load raster and vector data in a variety of formats from cloud storage and Wherobots managed storage. Getting Started
WherobotsNotebook Part 3: Accelerating Geospatial Datasets Getting started, part 3: manage, cluster, and export large geospatial datasets for high-performance analysis and downstream use. Getting Started
WherobotsNotebook Part 4: Spatial Joins Getting started, part 4: combine datasets by their spatial relationships with spatial joins, using Python and the DataFrame API. Getting Started
WherobotsNotebook Reading STAC data Load SpatioTemporal Asset Catalog (STAC) collections into WherobotsDB with the STAC reader and API. Reading and Writing Data
Demo built with AI coding toolsDemo app Texas drone-delivery nest siting Shortlists candidate drone-delivery nest sites across Texas by weighing the people each site reaches within 10 km against FAA LAANC airspace ceilings and obstacles. Live demo
Demo built with AI coding toolsDemo app Colorado property risk explorer Property-and-casualty exposure to five perils across every building and parcel in Colorado, from statewide hexes down to individual buildings. Live demo What is probable maximum loss? →
Demo built with AI coding toolsDemo app California signal quality explorer Statewide map of California mobile signal quality that separates capacity-limited areas from coverage gaps, with population and income lenses. Live demo
Demo built with AI coding toolsDemo app Pacific Northwest corridor resilience A gorge-fire scenario played out on real Pacific Northwest road and rail geometry, showing which freight corridors degrade and which communities lose every way in. Work in progress
Community demoDemo app Australia AI data center siting A national suitability screen for AI data center siting across Australia, with a ranked shortlist of candidate sites and a what-if weighting sandbox. Live demo
Demo built with AI coding toolsDemo app California grid wildfire exposure Transmission spans in the PG&E area scored 0 to 9 for environmental wildfire exposure from fuels, vegetation vigor, canopy, slope, and nearby structures. Work in progress
