NTRS - NASA Technical Reports Server

Back to Results
Integrating Machine Learning into a Crowdsourced Model for Earthquake-Induced Damage AssessmentOn January 12th, 2010, a catastrophic 7.0M earthquake devastated the country of Haiti. In the aftermath of an earthquake, it is important to rapidly assess damaged areas in order to mobilize the appropriate resources. The Haiti damage assessment effort introduced a promising model that uses crowdsourcing to map damaged areas in freely available remotely-sensed data. This paper proposes the application of machine learning methods to improve this model. Specifically, we apply work on learning from multiple, imperfect experts to the assessment of volunteer reliability, and propose the use of image segmentation to automate the detection of damaged areas. We wrap both tasks in an active learning framework in order to shift volunteer effort from mapping a full catalog of images to the generation of high-quality training data. We hypothesize that the integration of machine learning into this model improves its reliability, maintains the speed of damage assessment, and allows the model to scale to higher data volumes.

Document ID
Document Type
Conference Paper
External Source(s)
Rebbapragada, Umaa (Jet Propulsion Lab., California Inst. of Tech. Pasadena, CA, United States)
Oommen, Thomas (Michigan Technological Univ. Houghton, MI, United States)
Date Acquired
April 29, 2015
Publication Date
June 28, 2011
Subject Category
Earth Resources and Remote Sensing
Meeting Information
International Conference on Machine Learning Workshop(Bellevue, WA)
Distribution Limits
damage assessment
machine learning
remote sensing