4,198 candidate unseen burns covering 7,320 ha in 481 villages, in the 14 days of passes up to 12 Nov 2026. 2 harvested fields in 1 village rank in the top tenth for the next burn.
Candidate unseen burns are not confirmed fires: their audit precision 87% (95% CI 68–96%, n = 23), so every count and area of them here is an upper bound.
The top tenth comes from a burn-risk ranking that is modest in its backtest (AUC 0.640, 95% CI 0.595–0.693; 0.5 is chance): a rank says where to look first, not the chance that a field will burn.
Sentinel-2 passes 30 Oct – 12 Nov 2026
Candidate unseen burns4,198upper bound
Their area7,320 haupper bound
Villages with them481newest pass 11 Nov
Harvested fields5,561straw still lying, 9,283 ha
In the top tenth2 fieldsin 1 village
Villages with candidate unseen burns
Largest candidate unseen area first. A village’s map link and case file open its largest burn.
In this season's backtest, fields in the top tenth of their pass burnt by the next clear pass 1.61 times as often as the average field (95% CI 1.28-2.04): 20.1% against 12.5%. The backtest could order past fields only by burning nearby and last season's fires: the time since harvest and the rain cannot be reconstructed for past passes. Checked over all 387 pass pairs, the ranking is modest (AUC 0.640, 95% CI 0.595-0.693; 0.5 is chance). A rank says where to look first; it is not the chance that a field will burn.
Watchlist of Karnal: villages with harvested fields, ordered by the burn-risk ranking
#Position
Village
Sub-district
Harvested fields
Hectares
Fields in the top tenth
Best rankof 2,61,123
Location
In the top tenth: 1 village has fields among the run’s highest-ranked tenth
Candidate unseen burns are Sentinel-2 burn scars that no NASA FIRMS fire detection explains. They are candidates, not confirmed fires: in a hand audit of 23 of them, 87% were real burns (95% CI 68%-96%), so every count and area of them here is an upper bound.
The window is the 14 days of Sentinel-2 passes up to the newest one in the data (2026-11-12), not up to today: Sentinel-2 sees a field only every few days, and its passes are processed once a day.
Each village's point is its largest candidate unseen burn, so its map link leads to the burnt field itself. Village names are the nearest census village within 3 km of a scar; scars with no village that close are listed by sub-district, without a name.
The watchlist orders harvested fields whose straw was still lying on the latest clear pass by the burn-risk run of 2026-11-13 17:23 IST: villages with fields in the run's top tenth first, then the others by their best-ranked field, so a district with no field in the top tenth still gets a list. In this season's backtest, fields in the top tenth of their pass burnt by the next clear pass 1.61 times as often as the average field (95% CI 1.28-2.04): 20.1% against 12.5%. The backtest could order past fields only by burning nearby and last season's fires: the time since harvest and the rain cannot be reconstructed for past passes. Checked over all 387 pass pairs, the ranking is modest (AUC 0.640, 95% CI 0.595-0.693; 0.5 is chance). A rank says where to look first; it is not the chance that a field will burn.
These lists say where to look, not who burnt: a satellite flag needs a visit on the ground before any action, and the brief names villages only, never people.
Printed from the BlindSpot field brief for Karnal, built 13 Nov 2026, 20:39 IST. Every village of the window, with its map link, is in the CSV: https://blindspot-api-azure.vercel.app/api/brief/Karnal/csv?days=14&lang=en
Best rank is the rank of the village’s best field among the 2,61,123 fields of the run (1 = the highest). The brief has no scores and no probabilities.