ml – Europlanet Society

Calling AI experts! Join the hunt for exoplanets

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

The Ariel Data Challenge 2022, which launches on 30 June, is inviting AI and machine learning experts from industry and academia to help astronomers understand planets outside our solar system, known as exoplanets.

Dr Ingo Waldmann, Associate Professor in Astrophysics, UCL (University College London) and Ariel Data Challenge lead said: “AI has revolutionised many fields of science and industry in the past years. The field of exoplanets has fully arrived in the era of big-data and cutting edge AI is needed to break 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, thanks to telescopes in space, they have discovered more than 5000 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 around one fifth of the known exoplanets.

Due to the large number of planets in this survey, and the expected complexity the captured observations, Ariel mission scientists are calling for the help of 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 has travelled through the planet’s atmosphere in what is known as a spectrum. The information from these spectra can help scientists investigate the chemical make-up 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 these data. Advanced machine learning techniques could help them to understand the impact of different atmospheric phenomena on the observed spectrum.

The Ariel Data Challenge calls on the AI community to investigate solutions. The competition is open from 30 June to early October.

Participants are free to use any model, algorithm, data pre-processing technique or other tools to provide a solution. They may submit as many solutions as they like and collaborations between teams are welcomed.

For the first time, this year the competition is also offering 20 participants access to High Powered Computing resource through DiRAC, part of the UK’s Science and Technology Facilities Council’s computing facilities.

Kai Hou (Gordon) Yip, Postdoctoral Research Fellow at UCL and Ariel Data Challenge Lead said: “With the arrival of next-generation instrumentation, astronomers are struggling to keep up with the complexity and volume of incoming exo-planetary data. The NeurIPS data challenge 2022 provides an excellent platform to facilitate cross-disciplinary solutions with AI experts.”

The competition

Winners will be invited to present their solution at the prestigious NeurIPS conference. First prize winning teams will be awarded $2,000 and second prize winners will receive $500.
Winners will also be invited to present their solution to the Ariel consortium.

The competition is supported by the UK Space Agency, European Research Council, European Space Agency and 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 entrants from leading academic institutes and AI companies.

This challenge, and its predecessor have taken a bite-sized aspect of a larger problem to help make exoplanet research more accessible to the machine learning community. The challenge is not designed to solve the data analysis issues faced by the mission outright but provides a forum for discussion and to encourage future collaborations.
More details about the competition and how to take part can be found on the Ariel Data Challenge website. Follow @ArielTelescope for more updates.

Artist's impression of Ariel Telescope. — Artist’s impression of Ariel. Image Credit: ESA/STFC RAL Space/UCL/UK Space Agency/ ATG Medialab

Ariel will be placed in orbit around the Lagrange Point 2 (L2), a gravitational balance point 1.5 million kilometres beyond the Earth’s orbit around the Sun. Image Credit: ESA/STFC RAL Space/UCL/Europlanet-Science Office

Videos:
Note: Please get in touch with press contact for mp4 files.
Ariel animations: https://www.youtube.com/playlist?list=PL7nlYuIpjicaxp36LxZwkXOH72Otf-rgY
Welcome to Ariel: https://youtu.be/28afJ_5TTGc

Contacts:
Madeleine Russell
Ariel Consortium Communications Lead and RAL Space Communications Manager
Mob: +44 (0) 7594083386
Email:madeleine.russell@stfc.ac.uk

Notes to editors:

Ariel (Atmospheric Remote-sensing Infrared Exoplanet Large-survey)
Ariel, a mission to answer fundamental questions about how planetary systems form and evolve, is a European Space Agency (ESA) medium-class science mission due for launch in 2028. During a 4-year mission, Ariel will observe 1000 planets orbiting distant stars in visible and infrared wavelengths to study how they formed and how they evolve. It is the first mission dedicated to measuring the chemistry and thermal structures exoplanet atmospheres, enabling planetary science far beyond the boundaries of the Solar System.

The Ariel mission has been developed by a consortium of more than 50 institutes from 16ESA member state countries, including the UK, France, Italy, Poland, Belgium, Spain, the Netherlands, Austria, Denmark, Ireland, Czech Republic, Hungary, Portugal, Norway, Sweden, Estonia –plus USA contribution from NASA.

Twitter: @ArielTelescope | YouTube: Ariel Space Mission | www.arielmission.space

Ariel Machine Learning Data Challenge

https://www.ariel-datachallenge.space/

Ariel consortium
The Ariel mission payload is developed by a consortium of more than 50 institutes from 17 ESA countries – which include the UK, France, Italy, Poland, Belgium, Spain, the Netherlands, Austria, Denmark, Ireland, Czech Republic, Hungary, Portugal, Norway, Sweden, Germany, Estonia – plus a NASA contribution.

About UCL – London’s Global University
UCL is a diverse global community of world-class academics, students, industry links, external partners, and alumni. Our powerful collective of individuals and institutions work together to explore new possibilities.

Since 1826, we have championed independent thought by attracting and nurturing the world’s best minds. Our community of more than 43,800 students from 150 countries and over 14,300 staff pursues academic excellence, breaks boundaries and makes a positive impact on real world problems.

We are consistently ranked among the top 10 universities in the world and are one of only a handful of institutions rated as having the strongest academic reputation and the broadest research impact.

We have a progressive and integrated approach to our teaching and research – championing innovation, creativity and cross-disciplinary working. We teach our students how to think, not what to think, and see them as partners, collaborators and contributors.
For almost 200 years, we are proud to have opened higher education to students from a wide range of backgrounds and to change the way we create and share knowledge.
We were the first in England to welcome women to university education and that courageous attitude and disruptive spirit is still alive today. We are UCL.
www.ucl.ac.uk | Follow @uclnewson Twitter | Read news at www.ucl.ac.uk/news/| Listen to UCL podcasts on SoundCloud| Find out what’s on at UCL Minds

lnews on Twitter | Read news at www.ucl.ac.uk/news/ | Listen to UCL podcasts onSoundCloud | Find out what’s on at UCL Minds

Using AI to Predict the Danger of Solar Storms for Earth

This press release has been translated from the original German version by the Know-Center.

Researchers from the Know-Center and the Space Research Institute are developing a prediction tool, funded through Europlanet 2024 RI, that determines the strength of solar storms. Better forecasts could prevent a blackout from a massive solar storm.

While there is a current focus on the energy crisis in Europe, less attention is paid to the danger threatening from space. Solar storms are usually so weak that the atmosphere and the earth’s magnetic field protect the planet sufficiently from them. However, according to experts, a solar storm could hit us at any time and have serious effects on power grids, radio networks and satellites.

Around ten percent of all satellites could fail during such an event, and this would cause problems in areas where precise positioning is required, such as shipping and air traffic. Widespread power outages due to increased transformer voltages and damage to undersea cables, leading to nationwide internet outages, are also conceivable.

Space weather researchers can observe whether a solar storm is heading towards Earth, but it is difficult to estimate how massive the storm will be once it hits Earth. Now, data experts from the Know-Center and the Institute for Space Research, funded by the Europlanet 2024 Research Infrastructure (RI), have developed a prediction tool, based on Artificial Intelligence (AI), to better-estimate the strength of solar storms. The results were recently published as part of a study in the peer-reviewed journal, Space Weather.

Magnetic field determines the strength of solar storms

Solar activity fluctuates every eleven years between quiet and active phases. We are currently in an active phase, the maximum of which is expected in 2025. A geomagnetic storm occurs when solar storms interact with Earth’s magnetic field. In extreme cases, solar storms can reach Earth in less than a day. The ability of solar storms to cause extreme geomagnetic storms depends largely on the orientation of their magnetic field, known in technical jargon as the B_z magnetic field component. The relative orientation of this magnetic field component to the Earth’s magnetic field determines how much energy is transferred to Earth’s magnetic field. The larger a southward B_z component is, the greater the risk of a massive geomagnetic storm. To date, however, the B_z magnetic field component cannot be predicted with sufficient advance warning before the solar storm hits Earth.

Machine learning provides better forecasting

‘It only takes a few minutes for data measured by spacecraft directly in the solar wind to be transmitted to Earth. We first looked at whether information about the first few hours of a solar storm is sufficient to be able to predict its strength,’ explains Hannah Rüdisser from Know-Center.

Using Machine Learning (ML), the researchers developed a program to predict the B_z magnetic field component. The program was trained and tested with data from 348 different solar storms collected by the Wind, STEREO-A and STEREO-B spacecraft since 2007. To test the prediction tool in a real-time experimental mode, the team simulates how solar storms are measured by spacecraft and evaluates how the continuous feeding of new information improves the predictions.

‘Our forecasting tool can predict the B_z component quite well. It works particularly well when we use data from the first four hours of the solar storm’s magnetic flux rope. New space missions will provide us with even more data in the coming years, further increasing the accuracy of the predictions. Our approach could thus lead to an improved space weather forecast and in the event of a massive solar storm, affected areas could be warned at an early stage and major damage prevented,’ says Rüdisser.

In the next step, the researchers want to use AI methods to automatically detect solar storms in the solar wind. This automation is necessary to be able to use the B_z prediction method in real-time without a human expert having to continuously identify the solar storms.

Innovation for space exploration

The use of AI to analyze and classify planetary data sets is still relatively new, but is becoming increasingly important. ML enables algorithms to be trained to analyze huge amounts of data and derive predictions and new solutions from them. Potential applications of ML in planetary science have exploded over the past decade, but tools tailored to this area of research are still rare.

‘The Europlanet 2024 Research Infrastructure houses a large treasure trove of data that comes from space missions, simulations and laboratory experiments. Our goal is to extract the knowledge contained in this data and make it usable. For this we want to develop a series of ML tools that support researchers in planetary sciences in their work. This allows us to promote a broader use of ML technologies in data-driven space research,’ says Rüdisser.

More information

‘Machine Learning for Predicting the Bz Magnetic Field Component From Upstream in Situ Observations of Solar Coronal Mass Ejections‘, M. A. Reiss, C. Möstl, R. L. Bailey, H. T. Rüdisser, U. V. Amerstorfer, T. Amerstorfer, A. J. Weiss, J. Hinterreiter, A. Windisch. Space Weather, Volume 19, Issue 12. https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2021SW002859

About the Know Center

Know-Center is one of the leading European research centers for data-driven business and AI. Since 2001, well-known companies have been supported in using data as a success factor for their company. As an integral part of the European research landscape, the center successfully handles numerous projects and contract research at EU and national level. The K1 Competence Center, which is funded as part of COMET, is the leading training center for data scientists in Austria and also offers a range of Al training courses and advice for companies. The majority shareholder of the Know-Center is the Graz University of Technology, a major sponsor of local AI research, whose institutes carry out numerous projects together with the Know-Center. In 2020, Know-Center was the only Austrian center to receive the iSpace Gold Award from the Big Data Value Association, which was only given nine times in the entire EU. https://www.know-center.at