In this paper, we help NASA solve three Exploration Mission-1 (EM-1) challenges: data storage, computation time, and visualization of complex data. NASA is studying one year of trajectory data to determine available launch opportunities (about 90TBs of data). We improve data storage by introducing a cloud-based solution that provides elasticity and server upgrades. This migration will save $120k in infrastructure costs every four years, and potentially avoid schedule slips. Additionally, it increases computational efficiency by 125%. We further enhance computation via machine learning techniques that use the classic orbital elements to predict valid trajectories. Our machine learning model decreases trajectory creation from hours/days to minutes/seconds with an overall accuracy of 98%. Finally, we create an interactive, calendar-based Tableau visualization for EM-1 that summarizes trajectory data and considers multiple constraints on mission availability. The use of Tableau allows for sharing of visualization dashboards and would eventually be automatically updated upon generation of a new set of trajectory data. Therefore, we conclude that cloud technologies, machine learning, and big data visualization will benefit NASA’s engineering team. Successful implementation will further ensure mission success for the Exploration Program with a team of 20 people accomplishing what Apollo did with a team of 1000.
Garza, Antonio P. III; Quinonez, Jose; Santana, Misael; and Lohia, Nibhrat
"Visualization and Machine Learning Techniques for NASA’s EM-1 Big Data Problem,"
SMU Data Science Review: Vol. 2:
1, Article 11.
Available at: https://scholar.smu.edu/datasciencereview/vol2/iss1/11
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Applied Statistics Commons, Astrodynamics Commons, Databases and Information Systems Commons, Numerical Analysis and Scientific Computing Commons, Programming Languages and Compilers Commons, Statistical Methodology Commons, Statistical Models Commons, Systems Architecture Commons