Trill Science Ministry| Chasers of the Lost Data
Project Details
The Challenge | Chasers of the Lost Data
Help find ways to improve the performance of machine learning and predictive models by filling in gaps in the datasets prior to model training. This entails finding methods to computationally recover or approximate data that is missing due to sensor issues or signal noise that compromises experimental data collection. This work is inspired by data collection during additive manufacturing (AM) processes where sensors capture build characteristics in-situ, but it has applications across many NASA domains.
Fireball Data Recovery
Our project uses Random Forest Linear Regression to determine likely velocity data of fireballs, shooting stars that are particularly bright.
Using data to predict missing data through Machine Learning.
We attempted different methods of graphing the data to understand it intuitively before trying to pour ML algorithms into the problem. We understood for example that the velocity column is always positive because it is a magnitude.
The algorithm we chose was Linear Regression through Random Forest Generation from Sci-Learn's library. The results report 97.67% accuracy.
Presentation is here.
Our Code is found here.
Members:
Ran, Nick, Sarah, and Krishnana