The eight hazard classes, and what each one actually measures
HazardNet classifies every district across its continuous 15-day daily trajectory into one of eight classes and scores it. These pages state what each class means, how its independent physics cross-check is computed, what it cannot tell you, and what the current run says.
Pick a hazard
Each page below is generated from the same artifacts this deployment ships, so the numbers in them match the map.
Current run at a glance
Prediction date 2026-11-02; 64 district trajectories classified across 64 districts (Days 1 to 15).
- Riverine and monsoon flooding, scored from how much rain falls and how hard it falls. Current run: 4 district trajectories classified as Flood.
- Short-duration, high-intensity flooding: the burst case of the rainfall proxy. Current run: 50 district trajectories classified as Flash Flood.
- Wind-driven coastal hazard: sustained wind above 50 km/h, with the rain it carries. Current run: 8 district trajectories classified as Tropical Cyclone.
- Heat load against the rainfall expected across the 15-day forecast window. Current run: 0 district trajectories classified as Drought.
- Exceedance above 30 °C, plus persistence. Current run: 0 district trajectories classified as Heat Wave.
- How far the minimum falls below 16 °C, plus persistence. Current run: 0 district trajectories classified as Cold Wave.
- Vegetation and burn risk from heat, wind and drying. Current run: 2 district trajectories classified as Fire.
- Squall wind plus a convective downpour. Current run: 0 district trajectories classified as Severe Local Storm.
Shared rules across every class
- Every alert uses the same four-level vocabulary, NORMAL, WATCH, WARNING, EMERGENCY, across all eight classes.
- Confidence is published as an uncalibrated model score; no calibration accuracy is claimed.
- Advisory levels follow the published alert policy and the escalation boundaries of the responsible authorities; nothing here overrides them.
Questions and answers
Why only eight classes?
Eight is the model's output vocabulary, fixed by the training data and enforced on ingest. A hazard outside that list is not mapped onto a nearest neighbour: the event loader rejects and reports the label instead, and the forecast ingest refuses the row.
Which class is most likely in the current run?
The current-run counts are listed above, and each hazard page repeats them. What the counts do not tell you is which is likely: they describe one model run, not a climatology.
HazardNet is not an official warning service. Official warnings come from BMD and FFWC. In an emergency call 999.
Loading the interactive HazardNet application…