Skip to main content
The following notebook examples discuss how Wherobots enables organizations to: track land change over time, model exposure to environmental catastrophe, and check compliance across large and remote footprints.

​
Examples

Baseline & Survey Imagery

Pull satellite and aerial imagery from STAC catalogs to establish a land baseline you can measure every later survey against.

Change Detection

Run a model over satellite imagery of your footprint from two dates with RasterFlow.

Regulatory Compliance

Overlay operational boundaries with protected areas, water bodies, and jurisdictional zones to automate compliance checks through spatial joins.

Severe Weather Exposure

Correlate NOAA Severe Weather Data Inventory records with your operational footprint to model exposure to storms, hail, and tornado activity.

​
Key Capabilities

Use RasterFlow to run change detection models on satellite imagery from two dates. The example notebook shows the two-date workflow with the Fields of the World model, which segments field boundaries rather than detecting change. To measure change, run a change detection model, such as one you export with the Bring Your Own Model notebook.

Change detection with RasterFlow

Run a model over imagery from two dates.
Estimate canopy height from aerial imagery to establish vegetation baselines and measure recovery against them.

Estimating canopy height

Predict tree heights from aerial imagery to baseline vegetation.
Join hazard zones, such as FEMA floodplains, against vector asset inventories with WherobotsDB to quantify what is exposed.

California coastal flood risk

Join hazard zones against parcel and asset records to quantify what is exposed.
Bring your own drone, aerial, or satellite GeoTIFFs into a RasterFlow mosaic and run your own PyTorch model over them to detect site-specific features such as tailings, wellheads, or haul roads.

Bring your own rasters

Mosaic your own GeoTIFFs into analysis-ready imagery.

Bring your own model

Run a custom PyTorch model over that imagery at scale.
Analyze ESA WorldCover land cover across large regions to inform decisions about where to operate and where to avoid.

Exploring ESA WorldCover

Explore global 10 m land cover classes from ESA WorldCover.

Get started with Wherobots

Try Wherobots with your own geospatial data in minutes.