See Not Just Where — But Why
Causal AI applied to geospatial data. Domain experts define causal hypotheses; the platform estimates effects and maps them.
What it shows
From hypothesis to mapped effect
- 1A domain expert draws their causal hypothesis visually.
- 2The platform runs DoWhy-based inference on spatial data.
- 3Results are mapped with confidence indicators.
Causal graph
Estimated effect
Capabilities
What the demo illustrates
Visual Causal Graph Editor
Draw and edit the causal structure your domain experts believe holds.
Multi-layer GIS Integration
Combine spatial layers — boundaries, points, rasters — into one model.
Causal Effect Estimation
DoWhy-based identification and estimation on spatial data.
What-if Scenario Modelling
Compare interventions and read off estimated effects before acting.
Explainable Output Reports
Auditable results stakeholders and committees can actually read.
Flexible Data Ingestion
GeoJSON, Shapefile, CSV, and API sources.
By industry
Where it applies
- Estimate how campus facility placement causally affects student outcomes.
- Separate catchment effects from genuine programme impact across districts.
- Model how infrastructure changes propagate effects across a spatial network.
- Quantify the causal contribution of design choices to measured performance.
- Trace how site and environmental conditions causally drive delays by location.
- Prioritise mitigations by estimated effect, not just where issues cluster.
- Estimate counterfactual traffic and demand under district-level interventions.
- Map where a policy actually causes change versus where it merely correlates.
- Quantify how interventions causally shift environmental outcomes over space.
- Attribute measured change to policy rather than confounded spatial trends.
Under the hood
Technical stack — no black boxes
Every causal model is specified by your experts. Here is what runs underneath.
Related work
Projects using Causal GIS
District Congestion Intervention Modelling
Estimating how district-level roadworks and signal changes cause shifts in traffic across the network.
Counterfactual traffic estimate per intervention
Infrastructure Reliability Drivers
Estimating how design and process changes cause shifts in asset reliability and lifecycle cost.
Projected: ranked reliability drivers
Air Quality Policy Impact
Quantifying how environmental policies cause measurable changes in air quality over space and time.
Counterfactual air-quality estimate per policy
Request Early Access
Early access partners help shape this demo's development. Tell us about your spatial causal question and we'll be in touch.