← Use casesResearch Preview

Spatial probability for missing-person response

Score where a missing person is most likely to be found. Direct ground teams to the highest-density hexes first.

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.

Predict returns a probability surface across an H3 hex grid, conditioned on behavioural profile, terrain, and weather. Use it to direct ground teams, prioritise patrols, or front-load the highest-density area before searchers arrive.

Inputs: a behavioural profile (despondent, dementia_alzheimers, others), an area (circle, polygon, path), age, datetime, and weather. Output: an H3 grid scored by likelihood. Render in deck.gl, kepler.gl, or QGIS. Pair with get_isochrone for evacuation reach. Pair with reverse_geocode to anchor incident inputs.

Predict carries a Research Preview label because we keep refining the behavioural priors. The model is real, callable, and stable to depend on.

Patterns

What this looks like in practice

Common shapes mapped to the tools you'd reach for.

Trailhead probability surface

Given a despondent profile, a 5km radius from the trailhead, and current conditions, generate the top 50 most likely H3 hexes ranked by score. Direct ground teams to the highest-density area first.

Evacuation reachability

Compute walking isochrones from at-risk locations to model who can get to safety inside 15, 30, or 60 minutes. Combine with predict outputs to prioritise outreach.

Incident-to-coordinates parsing

Run incoming radio reports through parse_address, anchor the result with geocode, and feed the coordinates straight into predict. The agent flow handles 'last seen near the Crown pub on Bridge St' end to end.

Other use cases

Logistics and autonomous fleets

Multi-stop optimisation, OD matrices, and corridor search for the agents and backends that move things.

Read →

Environmental and field operations

Terrain profiles, reachability polygons, and GPS map matching for ESG reporting, conservation, and field research.

Read →

Real estate and property

Geocode listings, model commute reach, score nearby amenities, and overlay terrain risk. The toolkit behind agent-led property search.

Read →

Travel and itinerary planning

Find places, route between them, fit them into a time budget, and surface what's on the way. The geospatial layer behind agentic trip planners.

Read →

Customer-input cleanup

Fix typos, expand abbreviations, validate before geocoding. The reliable pre-step for agents handling user-typed addresses.

Read →

Field service and dispatch

Optimise visit order, score reachable jobs from each tech, clean GPS into proof-of-visit records.

Read →

Insurance and risk underwriting

Anchor addresses, layer terrain and elevation, assess access from emergency services. Bulk-process portfolios in one call.

Read →

Healthcare access and equity

Compute drive-time and walk-time access to facilities, model coverage gaps, place ambulances with travel-time matrices.

Read →

Sales and territory planning

Build OD matrices between reps and accounts, draw catchments around offices, normalise lead addresses at scale.

Read →

Outdoor and fitness apps

Plan walking, hiking, and cycling routes with explicit difficulty. Snap noisy GPS into clean traces with surface and grade per edge.

Read →

Public-sector planning

Model who can reach what, where the gaps are, how transit changes the answer. Reachability and matrix tools for civic planning.

Read →