Summary: The 2023 Ariel Data Challenge calls on experts in artificial intelligence and machine learning to help collect data on exoplanets.

Source: Europlanet

Artificial intelligence (AI) experts have been challenged to help a new space mission study Earth’s place in the universe.

The 2023 Ariel Data Challenge, which launches on April 14, invites experts in artificial intelligence and machine learning from industry and academia to help astronomers understand planets outside our solar system, called exoplanets.

Dr Ingo Waldmann, Associate Professor of Astrophysics, UCL (University College London) and Head of the Ariel Data Challenge, said:

“AI has revolutionized many areas of science and industry in recent years. The field of exoplanets has fully entered the era of big data and cutting-edge AI is needed to break through some of our biggest data bottlenecks. strangulation that holds us back.

Understand our place in the universe

For centuries, astronomers could only glimpse the planets of our solar system, but in recent years, thanks to telescopes in space, they have discovered more than 5,000 planets orbiting other stars in our galaxy.

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

Due to the large number of planets in this survey and the expected complexity of the observations captured, scientists on the Ariel mission are asking for help from the AI ​​and machine learning community to help interpret the data.

Ariel Data Challenge

Ariel will study the light from each exoplanet’s host star after it passes through the planet’s atmosphere in what’s called a spectrum. The information from these spectra can help scientists study the chemical makeup of the planet’s atmosphere and learn 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 different atmospheric phenomena on the observed spectrum.

The Ariel Data Challenge calls on the AI ​​community to seek solutions. The competition is open from April 14 to June 18, 2023.

Entrants are free to use any model, algorithm, data pre-processing technique or other tool to provide a solution. They can submit as many solutions as they want and cross-team collaborations are welcome.

This year, the competition is also offering entrants access to high-powered computing resources through DiRAC, part of the computing facilities of the UK’s Science and Technology Facilities Council.

Kai Hou (Gordon) Yip, postdoctoral researcher at UCL and head of Ariel’s data challenge, said:

“With the advent of next-generation instrumentation, astronomers are struggling to keep up with the complexity and volume of incoming exo-planetary data. The ECML-PKDD 2023 Data Challenge provides an excellent platform to facilitate solutions interdisciplinary with AI experts.”

The competition

The winners will be invited to present their solutions at the prestigious ECML conference. The top three winning teams will receive sponsored tickets to ECML-PKDD at Turing or the cash equivalent.

Winners will also be invited to pitch their solutions to the Ariel Consortium.

The British Space Agency, the National Center for Space Studies (CNES), the European Research Council, the UKRI Science and Technology Funding Council (STFC), the European Space Agency and the Europlanet company are supporting the competition.

For the first time, DiRAC is offering free access to GPU computing resources to selected participants. The application is open to everyone.

Previous contest

This is the fourth Ariel Machine Learning Data Challenge after successful competitions in 2019, 2021 and 2022. The 2022 challenge welcomed 230 participating teams from around the world, including participants from academic institutes and leading AI companies. plan.

This challenge and its predecessor took a small aspect of a larger problem to help make exoplanet research more accessible to the machine learning community. These challenges are not designed to solve the data analysis problems encountered by the mission, but provide a forum for new ideas, discussions and to encourage future collaborations.

More details about the contest and how to enter can be found on the Ariel Data Challenge website. Follow @ArielTelescope for more updates.

About this artificial intelligence research news

Author: Anita Heward
Source: Europlanet
Contact: Anita Heward – Europlanet
Picture: Image is in public domain