Crowdsourcing for post-disaster damage mapping

The project takes aim at rapid damage mapping using crowd-sourced data and satellite imagery to support humanitarian relief efforts and post-disaster recovery.

© Guy J. Sagi | Shutterstock - Road washed out in Raeford North Carolina after Hurricane Matthew

© Guy J. Sagi | Shutterstock - Road washed out in Raeford North Carolina after Hurricane Matthew

According to the Food and Agriculture Organization (FAO), natural disasters triggered by climate change have risen in frequency and severity over the last three decades. Between 2003 and 2013, natural disasters caused a total of US$ 1.5 trillion in damage worldwide. In developing countries alone, they cost about $550 billion in estimated damage and affected the lives of two billion people. Therefore, timely and innovative methods to rapidly assess damage to subsequently aid relief and recovery efforts are critical. In this field of post-disaster damage assessment, several crowdsourcing-based technological tools that engage citizens in carrying out various tasks, including data collection, satellite image analysis and online interactive mapping, have recently been developed. One such tool is Picture Pile, a cross-platform application that is designed as a generic and flexible tool for ingesting satellite imagery for rapid classification by volunteers. Picture Pile, initially developed to crowdsource deforestation mapping using very high resolution satellite imagery, has recently been adapted to support rapid post-disaster damage assessments as part of the Crowd4Sat initiative led by Imperative Space, in partnership with IIASA, Humanitarian OpenStreetMap Team (HOT), and the European Space Agency (ESA). The application provides simple microtasks, where the volunteer is presented with satellite images and is asked a simple yes/no question. A “before” disaster satellite image is displayed next to an “after” disaster image and the volunteer is asked to assess whether there is any visible, detectable damage. The question is formulated precisely to focus the volunteer’s attention on a particular aspect of the damage (i.e damaged buildings). The users can then quickly classify the images by swiping them to the right, left or down to indicate their answer respectively for yes, no or maybe, thereby efficiently completing the microtask. When thousands of microtasks are being completed by the crowd of volunteers over a very short time immediately after a disaster, the aggregated information on damage extent can help rapidly identify affected areas and significantly increase response efficiency on the ground.

Following an initial crowd-powered test phase that uses example satellite imagery from large regions of Haiti affected by Hurricane Matthew in October 2016, the Picture Pile app is expected to be fully operational for rapid post-disaster damage mapping for future natural disasters. The project not only helps to increase citizen awareness of natural disasters, but also provides them with a unique opportunity to contribute directly to relief efforts.

The Picture Pile app is available for IOS, Android and in web browsers. 

For more information:


Picture Pile: Gaming For Science 

Print this page

Last edited: 10 April 2018


Steffen Fritz

EOCS Center Head and Deputy Program Director

Ecosystems Services and Management

T +43(0) 2236 807 353

Inian Moorthy

Research Scholar

Ecosystems Services and Management

T +43(0) 2236 807 465

Dilek Fraisl

Research Scholar

Ecosystems Services and Management

T +43(0) 2236 807 398


September 2016 - April 2017


Fraisl D, Campbell J, See L , Wehn U, Wardlaw J, Gold M, Moorthy I, Arias R, et al. (2020). Mapping citizen science contributions to the UN sustainable development goals. Sustainability Science DOI:10.1007/s11625-020-00833-7. (In Press)

Masson V, Heldens W, Bocher E, Bonhomme M, Bucher B, Burmeister C, de Munck C, Esch T, et al. (2020). City-descriptive input data for urban climate models: Model requirements, data sources and challenges. Urban Climate 31: e100536. DOI:10.1016/j.uclim.2019.100536.

Marshall M, Crommelinck S, Kohli D, Perger C, Yang MY, Ghosh A, Fritz S, Bie K, et al. (2019). Crowd-Driven and Automated Mapping of Field Boundaries in Highly Fragmented Agricultural Landscapes of Ethiopia with Very High Spatial Resolution Imagery. Remote Sensing 11 (18): e2082. DOI:10.3390/rs11182082.

Schepaschenko D , See L , Lesiv M, Bastin J-F, Mollicone D, Tsendbazar N-E, Bastin L, McCallum I, et al. (2019). Recent Advances in Forest Observation with Visual Interpretation of Very High-Resolution Imagery. Surveys in Geophysics 40 (4): 839-862. DOI:10.1007/s10712-019-09533-z.

Bechtel B, Alexander PJ, Beck C, Böhner J, Brousse O, Ching J, Demuzere M, Fonte C, et al. (2019). Generating WUDAPT Level 0 data – Current status of production and evaluation. Urban Climate 27: 24-45. DOI:10.1016/j.uclim.2018.10.001.

International Institute for Applied Systems Analysis (IIASA)
Schlossplatz 1, A-2361 Laxenburg, Austria
Phone: (+43 2236) 807 0 Fax:(+43 2236) 71 313