A planet outside the solar system is called an exoplanet.
Do you have experience with AI? If so, you can help scientists learn more about exoplanets
Artificial intelligence (AI) experts have been challenged to support a new space mission to explore Earth’s place in the universe.
The Ariel Data Challenge 2022, which began on June 30, calls on professionals with expertise in artificial intelligence and machine learning to help astronomers understand exoplanets, or planets outside our solar system.
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 exoplanet field has fully entered the era of big data, and cutting-edge AI is needed to overcome some of the biggest obstacles holding us back.”
Ariel will be placed in orbit around the Lagrange 2 (L2) point, a point of gravitational balance 1.5 million kilometers from Earth’s orbit around the Sun. Credit: ESA/STFC RAL Space/UCL/Europlanet-Science Office
Understanding our place in the universe
Astronomers could only see the planets in our solar system for many years, but in recent years, thanks to space telescopes, scientists have discovered more than 5,000 planets orbiting other stars in our galaxy.
By studying the atmospheres of nearly a fifth of known exoplanets, the European Space Agency’s Ariel telescope will complete one of the largest surveys ever made of these worlds.
Ariel mission scientists are asking the artificial intelligence and machine learning community to help interpret the data due to the sheer number of planets in this survey and the expected complexity of the observations.
Ariel Data Challenge
Ariel will study the light from each exoplanet’s host star after it has passed through the planet’s atmosphere in what is known as a spectrum. Information from these spectra can help scientists study the chemical composition of a planet’s atmosphere and discover more about these planets and how they formed.
Scientists involved in the Ariel mission needed a new method to interpret this data. Advanced machine learning techniques can help them understand the impact of various atmospheric phenomena on the observed spectrum.
Artist’s impressions of Ariel. Credit: ESA/STFC RAL Space/UCL/UK Space Agency/ ATG Medialab
The Ariel Data Challenge calls on the AI community to explore solutions. The contest is open from June 30 to early October.
Participants are free to use any model, algorithm, data pre-processing technique or other tools to provide a solution. They can submit as many solutions as they wish, and cross-team collaboration is welcome.
For the first time this year, the competition also offers 20 entrants access to powerful computing resources through DiRAC, part of the UK Science and Technology Facilities Council’s computing facilities.
Kai Howe (Gordon) Yip, Postdoctoral Research Fellow at UCL and Head of the Ariel Data Challenge said:
“With the advent of next-generation instrumentation, astronomers are struggling to cope with the complexity and volume of incoming exoplanet data. The NeurIPS data challenge 2022 provides an excellent platform to facilitate interdisciplinary solutions with artificial intelligence experts.”
The competition
Winners will be invited to present their solutions at the prestigious NeurIPS conference. First prize winning teams will be awarded $2,000 and second place winners will receive $500.
Winners will also be invited to present their solutions to the Ariel consortium.
The competition is supported by the British Space Agency, the European Research Council, the European Space Agency and the Europlanet Society.
Previous competition
This is the third Ariel Machine Learning Data Challenge, following 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 took a small aspect of a larger problem to make exoplanet research more accessible to the machine learning community. The challenge is not intended to directly solve the data analysis problems facing the mission, but provides a forum for discussion and fostering future collaboration.
More details about the competition and how to enter can be found on the Ariel Data Challenge website.
Add Comment