A new deep learning system can detect natural disasters using images posted on social media. The international group of researchers applied computer vision tools that, once trained using 1.7 million photographs, proved capable of analyzing, filtering, and detecting real disasters, writes the Universitat Oberta de Catalunya (UOC) in a press release. Previous research focused on analyzing text posts, but this research, published in Transactions on Pattern Analysis and Machine Intelligence, went further. During a stay at the MIT Computer Science and Artificial Intelligence Laboratory, Lapedriza contributed to developing a taxonomy of incidents and the database used to train deep learning models and performed experiments to validate the technology. The researchers created a list with 43 categories of incidents, including natural disasters (avalanches, sandstorms, earthquakes, volcanic eruptions, droughts, etc.) and accidents involving some element of human intervention (plane crashes, construction accidents, etc.). This list, together with 49 place categories, enabled the researchers to label the images used to train the system. The authors created a database named Incidents1M, with 1,787,154 images that were then used to train the incident detection model. From among these images, 977,088 had at least one positive label linking them to one of the incident classifications, while 810,066 had class-negative labels. Meanwhile, for the place categories, 764,124 images had class-positive labels, and 1,023,030 were class-negative. Using real data, the authors demonstrated the potential of a tool based on deep learning for obtaining information from social media about natural disasters and incidents requiring humanitarian aid. “This will help humanitarian aid organizations to find out what’s happening during disasters more effectively and improve the way humanitarian aid is managed when needed,” she said.
