Satellite Based Detection of Rocket Emission​

A Brief Synopsis

Analyzed Sentinel-5P satellite data to track atmospheric gas concentrations over Cape Canaveral Island during a launch period. Engineered features from atmospheric indicators—including trace gases, aerosols, and water vapor—to construct an informative classification set. Developed a Random Forest classifier to predict the occurrence of a rocket launch based on temporal trends in atmospheric features and got 56 % accuracy on the testing set. The corresponding jupyter notebooks can be found here.