AirSense
Air qualityAirSense v1.0AirSense scores air-quality risk from live pollutant concentrations (WHO-2021-anchored curves for PM2.5, PM10, NO₂ and O₃) plus stagnation and receptor context. Provider AQI indexes appear only as benchmark signals.
Run AirSense
Live mode uses keyless open providers; demo mode is deterministic and offline. Missing data lowers confidence — it never fakes a value.
Score formula
Required inputs
- PM2.5 / PM10 (µg/m³)
- NO₂, O₃, SO₂, CO (µg/m³)
Optional inputs
- dust, aerosol optical depth
- wind speed (km/h), boundary layer height (m)
- provider AQI (European/US) — benchmark only
Missing optional inputs drop their formula term (weights renormalize) and reduce confidence — the engine never crashes or invents data.
Decision modes
Concentrations near WHO guideline levels.
Elevated but generally tolerable for the general population.
Children, elderly, pregnant people and those with heart/lung conditions should reduce exposure.
Everyone may experience effects; limit prolonged outdoor exertion.
Serious effects possible for everyone; avoid outdoor exposure.
Not enough pollutant concentration data to assess air quality.
Limitations
- Model grid concentrations (~11–40 km) can differ substantially from street-level exposure.
- No local emission events (traffic incidents, industrial releases) are modelled.
- The score is health-oriented decision support, not a medical assessment.
- Provider AQI indexes are displayed for comparison only and never drive the score.
AirSense is a self-built TerraSentinel engine: external providers supply live environmental variables; the score, mode, confidence, explanation and actions above are computed by this project’s own documented model. Provider risk indexes are used only as benchmark references and never as the output. API: GET /api/engines/airsense/run?lat=&lon=
TerraSentinel is a decision-support tool and does not replace official emergency services, government warnings, or professional environmental management decisions.