Starting Date: June 2023
Prerequisites: notion of data analysis and machine learning, python
Will results be assigned to University: No
Billions of exoplanets are orbiting around their stars outside our solar system [1]. But are they similar enough to our Earth so that life may have developed there? Often you can answer this question if you know the planet’s mass, radius, and orbiting period. Given the astronomic distances between us and the planets, however, you need to estimate these quantities indirectly through a mathematical model and a series of sky observations.
In this project, you will use data from the Kepler mission [2], Neural Networks, and Conformal Predictors to estimate various exoplanet parameters and classify them. Compared to the commonly used Bayesian approach, e.g. [3], Neural Networks and Conformal Prediction produce finite-sample prediction intervals faster and more accurately.
[1] https://exoplanets.nasa.gov/, [2]https://exoplanetarchive.ipac.caltech.edu/docs/KeplerMission.html, [3]https://iopscience.iop.org/article/10.1086/432594/pdf, [4]https://www.jmlr.org/papers/volume9/shafer08a/shafer08a.pdf