Intelligent Decision Support for Target Tracking Analysis and Characterization

While automation has been increasingly used to process high volumes of satellite remote sensing data, deriving accurate and actionable information from these data streams still requires human analysts. Machine learning algorithms are critical for processing large datasets, whereas well-trained operators are especially effective at synthesizing information from diverse sources and recognizing unique situations that may require different interpretations of the data. Therefore, combining algorithmic strengths with improved operator awareness is critical for reliable and robust data analysis. This research contributes a suite of algorithms that support the visualization, analysis, and characterization of infrared satellite data. The key components of our Collaborative Analyst-Machine Perception system include a probabilistic classifier, a false data filter, a historical track comparison tool, and an online data recommendation system. These components are integrated into an interactive dashboard and trained on synthetic satellite information that emulates operational challenges. We evaluated our application with six United States Space Force satellite operators in a live scenario with simulated real-time data acquisition. We found that the operators rated our application as more usable than current operational systems and that the combined human–machine team was capable of more accurate data characterization than machine learning algorithms alone.