Mapping the Nepal Floods
Posted by Kshitij Sharma • Sept. 16, 2026
- < 24 HRS Flood to first mapping project
- 338 Experienced volunteer mappers engaged
- 799 Volunteer validators in MapSwipe
- 20,100 Buildings added to OpenStreetMap
Activation record
- 26 August — Flash floods and mudslides hit the Lhende Khola Valley
- 27 Aug — HOT launched the mapping campaign on Tasking Manager. Humanitarian datasets were published on HDX, and Vantor agreed to release imagery.
- 28 Aug — AI-assisted damage assessment was published on HDX.
- 29–31 Aug — Mapping expanded to the lower river corridor at the request of Nepal’s disaster authority (NDRRMA).
- 1 Sep — The first four projects were 100% mapped and validated.
- 2–7 Sep — Four MapSwipe projects opened to validate the AI damage results.
How it worked
Volunteers mapped from satellite imagery. fAIr models learned from that mapping: one found the buildings, the other scored the damage level per building. Volunteers then validated the the AI results.
Imagery released — Vantor before and after images. Mappers traced mostly on Esri World Imagery in Tasking Manager.
Volunteers map — Tasking Manager projects: buildings, roads, residential areas.
Validators check — Mappers with more than 250 changesets, in vetted teams like HOT Global Validators.
fAIr trains — Buildings mapped by volunteers in OpenStreetMap become training data for the AI models.
Models predict — One model finds the buildings. A second scores the damage level for each mapped building.
MapSwipe validates — Volunteers validate the 1,053 buildings in the first AI release, one at a time.
Human mapping and validation — fAIr model — Open data and imagery. Mapped features go into OpenStreetMap. HOT rebuilds those layers on HDX every day.
How damage is recorded in OpenStreetMap. Mappers keep the outline of a destroyed building, change building=yes to destroyed: building=yes, and add damage:event=2026 Nepal Flood. The building stays in the data as a record of the loss, and the HDX layers mark it Destroyed.
Two local models
Each model was trained on buildings mapped by hand during the response. Try both at dev.ai.hotosm.org/try-fair.
01 Buildings
Before flood imagery
- BASE — DINOv3 (Meta) building model, the same base model available in fAIr
- TRAINED ON — Buildings mapped by volunteers in OpenStreetMap, once the first Tasking Manager project was complete
- PREDICTED — Buildings across the whole northern priority area
- RELEASED AS — Building layer on HDX, archived once manual mapping was done
02 Damage
Before and after imagery
- BASE — DINOv3 (Meta) siamese damage model, pretrained on xView and Venezuela earthquake damage data
- TRAINED ON — 272 buildings labelled by expert mappers for the first release: 183 destroyed, 89 intact
- PREDICTED — 28 Aug: 1,053 buildings in the first after-flood images. 12 Sep: 8,421 buildings across the 26-image after-flood composite, 2,276 destroyed, 594 major, 1,049 minor, the rest no visible damage
- RELEASED AS — Nepal Flood 2026: fAIr Damage Assessment on HDX, first release 28 Aug, updated 12 Sep
Cloud and mud made damage hard to read. In the worst-hit settlements buildings were buried in mud, and only 5 of 27 after-flood images were clear over the river. The AI results went out as predictions, 799 MapSwipe volunteers checked them, and the September update was measured against 3,896 buildings tagged by hand.
What exists, and where
At HOT's request, Vantor agreed on 27 August to release before and after images under CC BY-NC 4.0. Features traced into OpenStreetMap fall under the ODbL licence.
Imagery over the 90 km² high-risk area
55 km² covered after the flood, 45 km² Covered before the flood
5 of 27 images clear over the river, 35–72 cm/px published on OpenAerialMap
Published datasets and services
Flood-affected area, OSM and Overture
Full river corridor
fAIr damage assessment
Imagery viewer
Tasking Manager projects
MapSwipe validation
Contribution statistics
Activation Wiki
Share
