Ariel Machine Learning Data Challenge 2019

1 minute read

We are excited to announce that the ExoAI team together with the European Space Agency’s ARIEL mission have launched the first machine learning data challenge!

ARIEL, a mission dedicated to make a large-scale survey of exoplanet atmospheres, has launched a global competition series to find innovative solutions for the interpretation and analysis of exoplanet data. ARIEL has been selected by the European Space Agency as its next medium-class science mission and is due for launch in 2028.

The first ARIEL Data Challenge invites professional and amateur data scientists around the world to use Machine Learning (ML) to remove noise from exoplanet observations caused by starspots and by instrumentation. Automated solutions for improved analysis of light-curves through the ARIEL Machine Learning and Stellar Activity Challenge (MLSAC) will lead to better accuracy in the detection and characterisation of exoplanets – for current missions as well as future ARIEL observations. The ARIEL MLSAC contest has been selected as a Discovery Challenge by the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD). The closing date is Thursday 15th August. Results will be presented at ECMLPKDD in Würzburg from 16- 20th September.

A second ARIEL Data Challenge that focuses on the retrieval of spectra from simulations of cloudy and cloud-free super-Earth and hot-Jupiter data was also launched. A further data analysis challenge to create pipelines for faster, more effective processing of the raw data gathered by the mission will be launched in June during the EWASS conference in Lyon. Outcomes from all three ARIEL Data Challenges will be discussed at the EPSC-DPS Joint Meeting 2019.

Details of the ARIEL Data Challenge Series 2019 are available at: