Using Game Engines and Machine Learning to Create Synthetic Satellite Imagery for a Tabletop Verification Exercise
This work addresses the challenge of evaluating citizen-based monitoring potential for nuclear verification, though it is incremental as it applies existing methods to a specific domain.
The authors tackled the problem of limited availability and accessibility of high-resolution satellite imagery for citizen-based monitoring of nuclear activities by using game engines and machine learning to generate synthetic imagery with customizable parameters like time of day and resolution. They demonstrated its application in tabletop exercises to assess verification capabilities from new satellite constellations.
Satellite imagery is regarded as a great opportunity for citizen-based monitoring of activities of interest. Relevant imagery may however not be available at sufficiently high resolution, quality, or cadence -- let alone be uniformly accessible to open-source analysts. This limits an assessment of the true long-term potential of citizen-based monitoring of nuclear activities using publicly available satellite imagery. In this article, we demonstrate how modern game engines combined with advanced machine-learning techniques can be used to generate synthetic imagery of sites of interest with the ability to choose relevant parameters upon request; these include time of day, cloud cover, season, or level of activity onsite. At the same time, resolution and off-nadir angle can be adjusted to simulate different characteristics of the satellite. While there are several possible use-cases for synthetic imagery, here we focus on its usefulness to support tabletop exercises in which simple monitoring scenarios can be examined to better understand verification capabilities enabled by new satellite constellations and very short revisit times.