Probability where it counts.
Give your team a probability heatmap of where a missing person is most likely to be, built from their behavioural profile, the terrain, and current weather.
Where this comes in.
Drawing search rings on paper costs daylight.
By the time the planning cell has a usable map, the most likely area has already changed. predict gives the on-call coordinator a probability surface in the response format their search planner already knows.
Commercial GIS assumes you've got a search planner on duty.
Most prediction tooling expects ArcGIS familiarity and a desktop session. Footstep is a single API call from any laptop, tablet, or commercial CAD platform. The heatmap comes back ready to render.
Existing tools don't model subject or conditions.
Lost-person behaviour is profile-shaped. A wandering dementia patient does not move like a lost hiker. predict conditions on profile, terrain, and live weather so the surface reflects who you're looking for, not an average.
Predict access and use
Restricted access. Predict is not part of the standard plan. Access is granted by application only, to organisations with appropriate operational expertise. Apply for access.
Decision support only, never a replacement. Predict outputs are probability priors. They must never replace expert human judgment, established response protocols, or any duty-of-care obligation. Outputs may be incorrect, incomplete, or unsuitable for a given scenario. Final decisions sit with qualified human operators.
Footstep's predict API generates a probability surface across an H3 hex grid, scored on where a missing person is most likely to be found at a given time. It uses behavioural profiles (dementia, despondent, hiker, child, more on the way), local terrain, and current weather as conditioning inputs. Pass a last-seen point or a search area, get back a ranked grid.
Output renders directly in the tools your team already uses, like QGIS, ArcGIS, deck.gl, and kepler.gl, without a transformation step. Pair predict with get_isochrone to model reach. Pair parse_address, reverse_geocode, and search_places to anchor incoming radio reports.
Decision support only, never a replacement for expert human judgement.
What you can count on.
- Behavioural profiles for dementia, despondent, hiker, child. More in the pipeline.
- Terrain-aware: slopes, water, land use, footpath density baked into the surface.
- Weather-aware: conditions fetched automatically from the timestamp, or override manually.
- Deterministic and reproducible. The same inputs give the same output, suitable for incident reports and reviews.
- Fair-use pricing tier for volunteer teams. Talk to us if your unit needs predictable annual cost.
The tools that fit.
Where to look first.
A probability heatmap of where a missing person is most likely to be found, built from their behavioural profile, the terrain, and current weather.
Where can you reach in 30 minutes?
Reachability polygons by time or distance from any starting point. Walking, cycling, or driving.
What's at this location?
Given a coordinate, return the address or place label. Useful for labelling pins and incident reports.
What's near here?
Points of interest near a location, by category or by venue name. Sorted by distance.
Clean up a messy address.
Free-text in, structured out. Fixes typos, expands abbreviations, infers missing fields, and scores confidence.
Driving, walking, and cycling directions.
Point-to-point or multi-stop routes with terrain analytics. Answer 'is this walkable?' without a second call.
Altitude for any point or path.
Heights in metres above sea level, with summary statistics for total ascent and descent.