US: Researchers at the Michigan Technological University are using crowdsourcing to analyse earthquake-induced damages in remotely sensed imagery. They have successfully demonstrated that this technology can estimate the damages at least two or three times faster than the conventional methods. Their project is going to be funded by a $325,000 grant from the National Science Foundation (NSF).
Thomas Oommen, assistant professor in the Department of Geological and Mining Engineering and Sciences, and his team use remote-sensing images that possess three components of high resolution—spatial (measure of the smallest object that can be identified), spectral (the specific wavelengths that a sensor can record) and temporal (how often a sensor can obtain imagery. They have been testing this crowd-based rapid damage assessment solution called BACKBOnE ( Building a Crowdsourced Knowledge Base of Extreme Events) in Haiti, New Zealand, and China. The researchers appreciate the fact that detailed ground assessment has highlighted the limitation of their approach but they have a plan to solve the issue. They propose automating key tasks using state-of-the-art machine learning and image processing and replacing manual image interpretation with supervised automated tasks for mapping and classifying damage.