Drought: how HazardNet classifies and scores it
Heat load against the rainfall expected across the 15-day forecast window.
How the model arrives at this class
Classified from the same drivers.This hazard's inputs are research-private.
Uncalibrated softmax. The confidence does not account for irrigation, which is what actually determines whether a dry fortnight damages a crop.
Advisory levels follow the published alert policy and the escalation boundaries of the responsible authorities; nothing here overrides them.
The independent physics cross-check
The rainfall term is inverted: less rain scores higher. 200 mm is the reference total at which the rainfall component reaches zero.
Drivers: maximum temperature in the horizon (T_max, °C) · precipitation accumulated over the horizon (P_total, mm).
- Expression: 0.6*clip((T_max-25)/20) + 0.4*clip((200-P_total)/200)
- 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 Drought
The run this deployment ships (prediction date 2026-11-02) classifies no district trajectory as Drought across Days 1 to 15. An absence of drought in one run is not a statement that the hazard cannot occur this season.
Season and geography
Typical season: November–April (dry season), most acute in the Barind and the south-west. This describes when the hazard is climatologically plausible, not when this run flags it.
What this class cannot tell you
- No soil moisture, no irrigation, no crop calendar: this is meteorological dryness, not agricultural drought.
- A dry horizon in the monsoon is a different event from a dry horizon in March; the proxy does not encode season.
- MODIS NDVI/EVI and land-surface temperature exist in the ETL for the archive path but are not live inputs to the forecast.
- 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 Drought 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 Drought?
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…