Calling AI experts! Join the exoplanet hunt

Artificial intelligence (AI) experts have been challenged to help a new space mission investigate Earth’s place in the universe. The Ariel Data Challenge 2022which was launched at 15e June invites AI and machine learning experts from industry and academia to help astronomers understand planets beyond our solar system, known as exoplanets.

“AI has revolutionized many areas of science and industry in recent years,” said Dr. Ingo Waldmann, Associate Professor in Astrophysics, UCL (University College London) and head of the Ariel Data Challenge. “The field of exoplanets has fully arrived in the age of big data, and advanced AI is needed to break through some of our biggest bottlenecks holding us back.”

Understanding our place in the universe

For centuries, astronomers could only glimpse the planets in our solar system, but in recent years, telescopes in space have helped them discover more than 5,000 planets orbiting other stars in our galaxy.

The European Space Agency’s Ariel Telescope will complete one of the largest-ever surveys of these planets by observing the atmospheres of about one-fifth of the known exoplanets.

Due to the large number of planets in this study and the expected complexity of the recorded observations, Ariel’s mission scientists are enlisting the help of the AI ​​and machine learning community to help interpret the data. Here’s the original research paper description of the Ariel data challenge.

Ariel Data Challenge

Ariel will study the light from each exoplanet’s host star after it travels through the planet’s atmosphere in what’s known as a spectrum. The information from these spectra could help scientists investigate the chemical makeup of the planet’s atmosphere and discover more about these planets and how they formed.

Scientists involved in the Ariel mission need a new method to interpret this data. Advanced machine learning techniques could help them understand the impact of various atmospheric phenomena on the observed spectrum.

The Ariel Data Challenge calls on the AI ​​community to explore solutions. The competition will run from June 15 to early October 2022.

Participants are free to use any model, algorithm, data preprocessing technique or other tools to provide a solution. They can submit as many solutions as they want and collaborations between teams are welcome. For the first time this year, the competition will also provide 20 participants with access to High Powered Computing resources through DiRAC, part of the computing facilities of the UK’s Science and Technology Facilities Council.

“With the advent of next-generation instrumentation, astronomers are struggling to keep up with the complexity and volume of incoming exoplanetary data,” said Kai Hou (Gordon) Yip, postdoctoral researcher at UCL and Ariel Data Challenge Lead. “The NeurIPS Data Challenge 2022 provides an excellent platform to enable interdisciplinary solutions with AI experts.”

The competition

Winners are invited to present their solution at the prestigious NeurIPS conference. The teams that win the first prize will receive $2,000 and the second prize winners will receive $500. Winners are also invited to present their solution to the Ariel consortium. The competition is supported by the UK Space Agency, European Research Council and European Space Agency.

Previous match

This is the third Ariel Machine Learning Data Challenge after successful competitions in 2019 and 2021. The 2021 challenge welcomed 130 participants from across Europe, including participants from leading academic institutes and AI companies.

This challenge, and its predecessor, have taken a bite-sized aspect of a larger problem to make exoplanet research more accessible to the machine learning community. The challenge is not intended to solve the data analytics problems facing the mission, but provides a forum for discussion and to encourage future collaborations.

Sign up for the free insideBIGDATA newsletter

Follow us on Twitter: @InsideBigData1 –

Leave a Comment

Your email address will not be published.