Flood: how HazardNet classifies and scores it
Riverine and monsoon flooding, scored from how much rain falls and how hard it falls.
How the model arrives at this class
The classifier labels each district forecast trajectory from the same meteorological drivers (rainfall, temperature, wind, humidity, radiation, evapotranspiration). Its class and its severity index are separate outputs: the class says which hazard the drivers most resemble, the severity says how strong the resemblance is.
The published confidence is the model's own softmax over the eight classes and is reported as `uncalibrated_model_softmax`. It is not a probability of flooding and it is not derived from the physics cross-check.
Advisory levels follow the published alert policy and the escalation boundaries of the responsible authorities; nothing here overrides them.
The independent physics cross-check
Both terms are required and must be different quantities. The pipeline this project inherited passed the horizon total twice, which made a wet fortnight indistinguishable from a three-day burst.
Drivers: precipitation accumulated over the horizon (P_total) · wettest 24 hours in that horizon (P_peak).
- Expression: 0.5*clip(P_total/300) + 0.5*clip(P_peak/100)
- That expression is executed against the pipeline’s own implementation by the content tests in CI: this page cannot silently describe a formula the pipeline no longer runs.
What the current run says about Flood
In the run this deployment ships (prediction date 2026-11-02), 4 district trajectories are classified as Flood across the continuous 15-day window (Days 1 to 15).
Highest model severity: Jhalokati (0.30, Days 1 to 15), Natore (0.30, Days 1 to 15), Noakhali (0.30, Days 1 to 15), Rangamati (0.30, Days 1 to 15).
These are classifications from the current run, not a forecast of impact. Advisory levels follow the published escalation gate alongside official Bangladesh authorities.
Season and geography
Typical season: June–September (monsoon); peak in July–August. This describes when the hazard is climatologically plausible, not when this run flags it.
What this class cannot tell you
- No hydrology: river levels, upstream release, embankment state and soil moisture are not inputs, so a high score means 'this much rain on this district', not 'this river will breach'.
- The two rainfall classes (Flood and Flash Flood) share one physics proxy: distinguishing them needs drainage and terrain data the pipeline does not carry.
- The soil-moisture channels in the current tensor are the fabricated constants this repository already flagged (`soil_channels_fabricated` on the snapshot); until a real ERA5-Land soil layer is wired in at the forecast timestep, the class is weaker than the rainfall alone would suggest.
- Confidence is published as an uncalibrated model score; no calibration accuracy is claimed.
Inputs behind it
Published assessments and official bulletins are the record; this site reports what they name.
- published forecast records
Questions and answers
Is a high Flood severity a prediction of damage?
No. The severity index is the model's continuous score for how strongly the drivers resemble this class, on a 0.00–1.00 scale. It is not a probability, not a percentage, and it does not model exposure. The physics cross-check is a second, independent estimate; where the two diverge, both numbers are shown rather than averaged.
Why is the confidence not a probability of Flood?
The published confidence is the model's own confidence over its eight classes, labelled uncalibrated_model_confidence in the data. It says how certain the classifier is about the class it picked, not how often that class actually materialises. No calibration has been fitted yet, which is also why nothing above the WATCH level can be published automatically.
Which districts does this page cover?
The district pages cover all 64 districts. This page summarises the districts the current run covers: a run can be partial, and the coverage stamp on the snapshot says exactly how partial, which the status page reports.
HazardNet is not an official warning service. Official warnings come from BMD and FFWC. In an emergency call 999.
Loading the interactive HazardNet application…