(Subscribe to Science For All, our weekly newsletter, where we aim to take the jargon out of science and put the fun in. Click here.)
Every year a stunning and colourful image of India does the rounds on Diwali, with claims that it was taken from space. In reality, the image is a composite of several satellite photos, created in 2003 by the National Oceanic and Atmospheric Administration (NOAA) to highlight population growth in the country.
So how do we know if a satellite image is fake or even if it has been used for misinformation? A new study says that there is a lot of this ‘deepfake geography’ happening in recent times and with new and more sophisticated artificial intelligence technologies available today, the problem could grow.
To the untrained eye it may be difficult to detect the differences between real and fake images, the researchers point out. To try to identify a “fake,” researchers employed many technical aspects of image processing, such as colour histograms and spatial domains.
Bo Zhao, assistant professor of geography at the University of Washington and lead author of the study said in a release that the study’s goal was not to show that geospatial data can be falsified, rather it was to learn how to detect fake images so that geographers can begin to develop the data literacy tools, similar to today’s fact-checking services, for public benefit.