Lessons Learned from Ariel Data Challenge 2022 - Inferring Physical Properties of Exoplanets From Next-Generation Telescopes

Kai Hou Yip, Quentin Changeat, Ingo Waldmann, Eyup B. Unlu, Roy T. Forestano, Alexander Roman, Katia Matcheva, Konstantin T. Matchev, Stefan Stefanov, Ond\vrej Podsztavek, Mario Morvan, Nikolaos Nikolaou, Ahmed Al-Refaie, Clare Jenner, Chris Johnson, Angelos Tsiaras, Billy Edwards, Catarina Alves de Oliveira, Jeyan Thiyagalingam, Pierre-Olivier Lagage, James Cho, Giovanna Tinetti
Proceedings of the NeurIPS 2022 Competitions Track, PMLR 220:1-17, 2022.

Abstract

Exo-atmospheric studies, i.e. the study of exoplanetary atmospheres, is an emerging frontier in Planetary Science. To understand the physical properties of hundreds of exoplanets, astronomers have traditionally relied on sampling-based methods. However, with the growing number of exoplanet detections (i.e. increased data quantity) and advancements in technology from telescopes such as JWST and Ariel (i.e. improved data quality), there is a need for more scalable data analysis techniques. The Ariel Data Challenge 2022 aims to find interdisciplinary solutions from the NeurIPS community. Results from the challenge indicate that machine learning (ML) models have the potential to provide quick insights for thousands of planets and millions of atmospheric models. However, the machine learning models are not immune to data drifts, and future research should investigate ways to quantify and mitigate their negative impact.

Cite this Paper

BibTeX
@InProceedings{pmlr-v220-yip23a, title = {Lessons Learned from Ariel Data Challenge 2022 - Inferring Physical Properties of Exoplanets From Next-Generation Telescopes}, author = {Yip, Kai Hou and Changeat, Quentin and Waldmann, Ingo and Unlu, Eyup B. and Forestano, Roy T. and Roman, Alexander and Matcheva, Katia and Matchev, Konstantin T. and Stefanov, Stefan and Podsztavek, Ond\vrej and Morvan, Mario and Nikolaou, Nikolaos and Al-Refaie, Ahmed and Jenner, Clare and Johnson, Chris and Tsiaras, Angelos and Edwards, Billy and Alves de Oliveira, Catarina and Thiyagalingam, Jeyan and Lagage, Pierre-Olivier and Cho, James and Tinetti, Giovanna}, booktitle = {Proceedings of the NeurIPS 2022 Competitions Track}, pages = {1--17}, year = {2022}, editor = {Ciccone, Marco and Stolovitzky, Gustavo and Albrecht, Jacob}, volume = {220}, series = {Proceedings of Machine Learning Research}, month = {28 Nov--09 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v220/yip23a/yip23a.pdf}, url = {https://proceedings.mlr.press/v220/yip23a.html}, abstract = {Exo-atmospheric studies, i.e. the study of exoplanetary atmospheres, is an emerging frontier in Planetary Science. To understand the physical properties of hundreds of exoplanets, astronomers have traditionally relied on sampling-based methods. However, with the growing number of exoplanet detections (i.e. increased data quantity) and advancements in technology from telescopes such as JWST and Ariel (i.e. improved data quality), there is a need for more scalable data analysis techniques. The Ariel Data Challenge 2022 aims to find interdisciplinary solutions from the NeurIPS community. Results from the challenge indicate that machine learning (ML) models have the potential to provide quick insights for thousands of planets and millions of atmospheric models. However, the machine learning models are not immune to data drifts, and future research should investigate ways to quantify and mitigate their negative impact.} }
Endnote
%0 Conference Paper %T Lessons Learned from Ariel Data Challenge 2022 - Inferring Physical Properties of Exoplanets From Next-Generation Telescopes %A Kai Hou Yip %A Quentin Changeat %A Ingo Waldmann %A Eyup B. Unlu %A Roy T. Forestano %A Alexander Roman %A Katia Matcheva %A Konstantin T. Matchev %A Stefan Stefanov %A Ond\vrej Podsztavek %A Mario Morvan %A Nikolaos Nikolaou %A Ahmed Al-Refaie %A Clare Jenner %A Chris Johnson %A Angelos Tsiaras %A Billy Edwards %A Catarina Alves de Oliveira %A Jeyan Thiyagalingam %A Pierre-Olivier Lagage %A James Cho %A Giovanna Tinetti %B Proceedings of the NeurIPS 2022 Competitions Track %C Proceedings of Machine Learning Research %D 2022 %E Marco Ciccone %E Gustavo Stolovitzky %E Jacob Albrecht %F pmlr-v220-yip23a %I PMLR %P 1--17 %U https://proceedings.mlr.press/v220/yip23a.html %V 220 %X Exo-atmospheric studies, i.e. the study of exoplanetary atmospheres, is an emerging frontier in Planetary Science. To understand the physical properties of hundreds of exoplanets, astronomers have traditionally relied on sampling-based methods. However, with the growing number of exoplanet detections (i.e. increased data quantity) and advancements in technology from telescopes such as JWST and Ariel (i.e. improved data quality), there is a need for more scalable data analysis techniques. The Ariel Data Challenge 2022 aims to find interdisciplinary solutions from the NeurIPS community. Results from the challenge indicate that machine learning (ML) models have the potential to provide quick insights for thousands of planets and millions of atmospheric models. However, the machine learning models are not immune to data drifts, and future research should investigate ways to quantify and mitigate their negative impact.
APA
Yip, K.H., Changeat, Q., Waldmann, I., Unlu, E.B., Forestano, R.T., Roman, A., Matcheva, K., Matchev, K.T., Stefanov, S., Podsztavek, O., Morvan, M., Nikolaou, N., Al-Refaie, A., Jenner, C., Johnson, C., Tsiaras, A., Edwards, B., Alves de Oliveira, C., Thiyagalingam, J., Lagage, P., Cho, J. & Tinetti, G.. (2022). Lessons Learned from Ariel Data Challenge 2022 - Inferring Physical Properties of Exoplanets From Next-Generation Telescopes. Proceedings of the NeurIPS 2022 Competitions Track, in Proceedings of Machine Learning Research 220:1-17 Available from https://proceedings.mlr.press/v220/yip23a.html.

Related Material