Resources

Baseline model and Metric:

Please see the Baseline page for a fully model description. For a description of the competition scoring metric, please see the Scoring page

You can access the full baseline model and competition metric on our GitHub repository.

Slack channel and email:

Please see the Slack channel for discussions and Q&A’s, or contact us via email: exoai.ucl (AT) gmail.com

DiRAC GPU computing resources:

This year DiRAC are kindly sponsoring computing resources for researchers who do not otherwise have access to sufficient compute to compete in this challenge. It is on a first-come-first-served basis and students and early career researchers are prioritised. To apply for these resources, please fill in This Form .

Associated Publications:

• Data Challenge Main description: Yip et al. (2022), Accepted in NeurIPS 2022.
• Database description: Changeat & Yip (2022).

Codes:

• Al-Refaie et al. (2021): TauREx 3: A Fast, Dynamic, and Extendable Framework for Retrievals, ApJ 917 37.
• Al-Refaie et al. (2022): A Comparison of Chemical Models of Exoplanet Atmospheres Enabled by TauREx 3.1, ApJ 932 123.
• Changeat et al. (2020): Alfnoor: A Retrieval Simulation of the Ariel Target List, AJ 160 80.
• Link to TauREx3 documentation.

Ariel Related Publications:

• Tinetti et al. (2020): Ariel: Enabling planetary science across light-years, Ariel Definition Study Report. Reviewed by ESA Science Advisory Structure.
• Edwards & Tinetti (2022): The Ariel Target List: The Impact of TESS and the Potential for Characterising Multiple Planets Within a System, Accepted in ApJ.
• Edwards et al. (2019): An Updated Study of Potential Targets for Ariel, AJ 157 242.
• Ariel official Website

Exoplanet Publications:

• Changeat et al. (2022): Five Key Exoplanet Questions Answered via the Analysis of 25 Hot-Jupiter Atmospheres in Eclipse, ApJS 260 3.
• Zhu & Dong (2021): Exoplanet Statistics and Theoretical Implications, ARA&A, 59, 291-336
• Cho et al. (2021): Storms, Variability, and Multiple Equilibria on Hot-Jupiters, ApJL 913 L32
• Venot et al. (2020): New chemical scheme for giant planet thermochemistry. Update of the methanol chemistry and new reduced chemical scheme, A&A, 634, A78, 17
• Tsiaras et al. (2019): Water vapour in the atmosphere of the habitable-zone eight-Earth-mass planet K2-18 b, Nat. Ast. 3 1086–1091.
• Madhusudhan (2019): Exoplanetary Atmospheres: Key Insights, Challenges, and Prospects, ARA&A, 57,617-663
• Tsiaras et al. (2018): A Population Study of Gaseous Exoplanets, AJ 155 156.
• Seager & Mallén-Ornelas (2003): A Unique Solution of Planet and Star Parameters from an Extrasolar Planet Transit Light Curve, AJ, 585, 2, 1038 - 1055.

Relevant ML Publications:

• Yip et al. (2022): To Sample or Not To Sample: Retrieving Exoplanetary Spectra with Variational Inference and Normalising Flows, Submitted to ApJ.
• Ardevol Martinez et al. (2022): Convolutional neural networks as an alternative to Bayesian retrievals, A&A 662, A108
• Himes et al. (2022): Accurate Machine-learning Atmospheric Retrieval via a Neural-network Surrogate Model for Radiative Transfer, Planet. Sci. J. 3 91.
• Yip et al. (2021): Peeking inside the Black Box: Interpreting Deep Learning Models for Exoplanet Atmospheric Retrievals, AJ 162 195.
• Cobb et al. (2019): An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval, AJ 158 33.
• Zingales & Waldmann (2018) : ExoGAN: Retrieving Exoplanetary Atmospheres Using Deep Convolutional Generative Adversarial Networks, AJ 156 268
• Márquez-Neila et al. (2018): Supervised machine learning for analysing spectra of exoplanetary atmospheres,Nat. Ast. 2 719–724.