Social Media Helps Detect Nuclear Agreement Violations
A new computational model combines disparate data sets.
Researchers at North Carolina (NC) State University have developed a new computational model that draws on normally incompatible data sets, such as satellite imagery and social media posts, to answer questions about what is happening in targeted locations. The model identifies violations of nuclear nonproliferation agreements.
The data can include traditional sources, such as Geiger counter readings or multispectral data from satellite imagery, but many may be nontraditional and diverse, including Flickr and Twitter posts. The variety of data often are not normally compatible, Hamid Krim, co-author of a paper on the work, explains in a university announcement. Krim also is a professor of electrical and computer engineering at NC State University and director of the VISSTA Laboratory. “By making these different inputs compatible with each other, we are able to accept a broader range of data inputs and use that data in a meaningful way that, ultimately, can help authorities reach more reliable conclusions,” Krim says.
The paper, “Fusing Heterogeneous Data: A Case for Remote Sensing and Social Media,” is published online in the journal IEEE Transactions on Geoscience and Remote Sensing. First author on the paper is Han Wang, a former postdoctoral researcher at NC State who is now a postdoctoral researcher at the University of Texas at San Antonio. Other co-authors were Erik Skau, a former Ph.D. student at NC State who is a now a postdoctoral researcher at Los Alamos National Laboratory, and Guido Cervone of Penn State .
The work was supported by the Department of Energy National Nuclear Security Administration’s Office of Defense Nuclear Nonproliferation Research and Development through the Consortium for Nonproliferation Enabling Capabilities at NC State University.