Detecting and Characterizing Exoplanets using AI

Nikolaos Nikolaou

Keywords: Exoplanets, Astronomy, Spectroscopy, AI Competitions, Uncertainty Quantification, Explainable AI, AI for Science

Abstract:

The last decade has witnessed a rapid growth of the field of exoplanet discovery and characterization - i.e. regarding the chemical species comprising its atmosphere, important for better understanding their formation and evolution and identifying potential biosignatures. However, several big challenges remain, many of which could be addressed using machine learning methodology. For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots. The current practice in the literature is identifying the effects of spots visually and correcting them manually or discarding the affected data. This paper explores a first step towards fully automating the efficient and precise derivation of transit depths from transit light curves in the presence of stellar spots. The primary focus of the paper is to present in detail a diverse arsenal of methods for doing so. The methods and results we present were obtained in the context of the 1st Machine Learning Challenge organized for the European Space Agency’s upcoming Ariel mission. We first present the problem, the simulated Ariel-like data and outline the Challenge while identifying best practices for organizing similar challenges in the future. Finally, we present the solutions obtained by the top five winning teams, provide their code, and discuss their implications. Successful solutions either construct highly non-linear (w.r.t. the raw data) models with minimal pre-processing – deep neural networks and ensemble methods – or amount to obtaining meaningful statistics from the light curves, constructing linear models on which yields comparably good predictive performance.

Where was the work published:
Most of the content of the presentation will focus on the uploaded paper [1] and cover exoplanet characterization in the context of the upcoming ESA Ariel Mission and the 1st Data Challenge organized in anticipation of data collected from the Ariel space telescope. There will be minor references to other aspects of applying machine learning methods in the context of exoplanetary discovery [2,3] and characterization [3,4], as well as subsequent Data Challenges organized (e.g. [5]) by our group at UCL.

[1] Nikolaou, N., Waldmann, I. P., Tsiaras, A., Morvan, M., Edwards, B., Yip, K. H., ... & Simões, L. F. (2023). Lessons learned from the 1st Ariel Machine Learning Challenge: Correcting transiting exoplanet light curves for stellar spots. RAS Techniques and Instruments, 2(1), 695-709.
[2] Morvan, M., Nikolaou, N., Tsiaras, A., & Waldmann, I. P. (2020). Detrending Exoplanetary Transit Light Curves with Long Short-term Memory Networks. The Astronomical Journal, 159(3), 109.
[3] Yip, K. H., Nikolaou, N., Coronica, P., Tsiaras, A., Edwards, B., Changeat, Q., Morvan, M., Biller, B., Hinkley, S., Salmond, J., Archer, M., Sumption, P., Choquet, E., Soummer, R., Pueyo, L., & Waldmann, I. P. (2020). Pushing the limits of exoplanet discovery via direct imaging with deep learning. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2019, Würzburg, Germany, September 16–20, 2019, Proceedings, Part III (pp. 322-338). Springer International Publishing.
[4] Yip, K. H., Changeat, Q., Nikolaou, N., Morvan, M., Edwards, B., Waldmann, I. P., & Tinetti, G. (2021). Peeking inside the black box: Interpreting deep-learning models for exoplanet atmospheric retrievals. The Astronomical Journal, 162(5), 195.
[5] Yip, K. H., Changeat, Q., Waldmann, I., Unlu, E. B., Forestano, R. T., Roman, A., Matcheva, K., Matchev, K. T., Stefanov, S., Morvan, M., Nikolaou, N., Al-Refaie, A., Jenner, C., Johnson, C., Tsiaras, A., Edwards, B.,Alves de Oliveira, C., Thiyagalingam, J., Lagage, P. O., Cho, J., & Tinetti, G. (2023, August). Lessons Learned from Ariel Data Challenge 2022-Inferring Physical Properties of Exoplanets From Next-Generation Telescopes. In NeurIPS 2022 Competition Track (pp. 1-17). PMLR.

Submission Number: 34