NASA invites coders to develop new AI/ML algorithm to identify sungrazing comets

As part of the Open Source Science Initiative (OSSI), NASA is inviting coders to develop a new artificial intelligence/machine learning algorithm to help astronomers identify comets.

NASA’s OSSI is a comprehensive program of activities to enable and support moving science towards openness, including policy adjustments, supporting open-source software, and enabling cyberinfrastructure.

The new “NASA SOHO Comet Search with Artificial Intelligence” challenge will commence on January 17 and run for four weeks. It includes a marathon match or data science challenge to get solutions built that detect very faint comets and track their movements in sequences of telescope images. Competitors whose algorithms identify previously unobserved comets will be given official comet discovery credit.

“In this challenge, your task will be to create Python code that detects comets and tracks their movements in sequences of telescope images. The presence and location of comets your algorithm returns will be compared to ground truth data, the quality of your solution will be judged by how much your solution matches the expected results, see Scoring for details,” says the official website.

For more details on the NASA Comet Discovery Challenge, head over to the website.

Launched in December 1995, SOHO is a joint NASA-ESA Solar & Heliospheric Observatory mission that studies the Sun from its interior to its outer atmosphere, with an uninterrupted view from its vantage point between the Sun and Earth. Considered one of the most successful NASA missions of all time, it has discovered thousands of new comets as well as new dynamic solar phenomena such as coronal waves and solar tornadoes.


Original post:

Leave a Reply

Your email address will not be published. Required fields are marked *