Tarn Taran Punjab

9,604 candidate unseen burns covering 16,012 ha in 603 villages, in the 30 days of passes up to 12 Nov 2026. 752 harvested fields in 224 villages 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 14 Oct – 12 Nov 2026

Candidate unseen burns9,604upper bound

Their area16,012 haupper bound

Villages with them603newest pass 12 Nov

Harvested fields10,066straw still lying, 12,169 ha

In the top tenth752 fieldsin 224 villages

Villages with candidate unseen burns

Largest candidate unseen area first. A village’s map link and case file open its largest burn.

Villages as CSVEnglish हिन्दी ਪੰਜਾਬੀ

Villages of Tarn Taran with candidate unseen burns, the 30 days of passes up to 12 Nov 2026
Position	Village	Sub-district	Burns	Hectares	Newest pass	Location	Largest burn
1	Gandiwind	Tarn Taran	95 burns	169.6 ha	newest pass 7 Nov	Map: Gandiwind in Google Maps, opens a new tab31.22173, 74.97186	Case 1953424
2	Punian	Patti

Watchlist: harvested fields, the burn-risk run’s top tenth first

Harvested fields whose straw was still lying on the latest clear pass, grouped by village and ordered by the burn-risk run of 13 Nov, 17:23 IST.

Modest ranking

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 Tarn Taran: 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: 224 villages have fields among the run’s highest-ranked tenth
1	Manochahal	Tarn Taran	55 fields	54.1 ha	16 in the top tenth	best rank 11,820	Map

How to read this brief

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 30 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.

Open on the live map Ask the investigator

Sources and freshness

Brief built: 13 Nov 2026, 20:15 IST
Newest Sentinel-2 pass: 12 Nov 2026, 11:21 IST
Burn-risk run: 13 Nov 2026, 17:23 IST, risk-v3, 2,61,123 fields ranked

Element 84 Earth Search STACfetched 13 Nov, 19:29 IST · fetch 63541earth-search.aws.element84.com/v1/collections/sentinel-2-c1-l2a…
Sentinel-2 L2A pixels (Earth Search COGs on AWS)fetched 13 Nov, 17:22 IST · fetch 62842earth-search.aws.element84.com/v1/collections/sentinel-2-c1-l2a…
ESA WorldCoverfetched 13 Nov, 17:22 IST · fetch 62841planetarycomputer.microsoft.com/api/stac/v1/search
NASA FIRMS active fires (VIIRS 375 m, MODIS 1 km; NRT)fetched 13 Nov, 19:47 IST · fetch 63558blindspot-relay.vercel.app/api/firms
Survey of India states + LGD/Bharatmaps districts (DataMeet / ramSeraph mirror)fetched 9 Nov, 08:47 IST · fetch 44144github.com/ramSeraph/indian_admin_boundaries/releases/download/…

Printed from the BlindSpot field brief for Tarn Taran, built 13 Nov 2026, 20:15 IST. Every village of the window, with its map link, is in the CSV: https://blindspot-api-azure.vercel.app/api/brief/Tarn%20Taran/csv?days=30&lang=en

Tarn Taran Punjab

9,604 candidate unseen burns covering 16,012 ha in 603 villages, in the 30 days of passes up to 12 Nov 2026. 752 harvested fields in 224 villages 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.

Villages of Tarn Taran with candidate unseen burns, the 30 days of passes up to 12 Nov 2026
Position	Village	Sub-district	Burns	Hectares		Newest pass	Location	Largest burn
1	Gandiwind	Tarn Taran	95 burns	169.6 ha		newest pass 7 Nov	Map: Gandiwind in Google Maps, opens a new tab31.22173, 74.97186	Case 1953424
2	Punian	Patti

Village

Sub-district

Burns

Hectares

Newest pass

Location

Largest burn

Gandiwind

Tarn Taran

95 burns

169.6 ha

newest pass 7 Nov

Map31.22173, 74.97186

Case 1953424

Punian

Patti

Watchlist of Tarn Taran: 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: 224 villages have fields among the run’s highest-ranked tenth
1	Manochahal	Tarn Taran	55 fields	54.1 ha	16 in the top tenth	best rank 11,820	Map

Village

Sub-district

Harvested fields

Hectares

Fields in the top tenth

Best rankof 2,61,123

Location

In the top tenth: 224 villages have fields among the run’s highest-ranked tenth

Manochahal

Tarn Taran

55 fields

54.1 ha

16 in the top tenth

best rank 11,820

Map

How to read this brief

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 30 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.