Dan Karcz supported NASA’s Deep Space mining data to help predict signal loss with NASA spacecraft so lost signals can be more easily diagnosed in the future. If machine-learning can diagnose the origin of signal loss, work to reestablish the signal can begin immediately. Analyzed past signal loss anomalies and correlated with weather conditions to establish patterns and build an algorithm. The Deep Space Network operates 12 antennae, all of different sizes, on three separate continents, making this a massive data-mining project. Each location has its own weather pattern, adding to the scope of the data-mining project.