NASA SOHO COMET SEARCH
with artificial intelligence
Over $55,000 in prizes!!!
Marathon Match Challenge
Round 1 - complete
Jan 17th, 2022 - Feb 14th, 2022
Round 2 - complete
Jun 17th, 2022 - Jul 22nd, 2022
Help us develop a new AI/ML algorithm to identify comets! and get official discovery credit! The NASA SOHO Comet Search with Artificial Intelligence will include a marathon match or data science challenge to get solutions built. If you’re not already a Topcoder member, click “Sign Up” above to take part in future challenges like this.View Case Study
Why It’s Important
The SOHO is a cooperative international mission between ESA and NASA’s Goddard Space Flight Center (GSFC), where data are archived at GSFC. SOHO’s Large Angle and Spectrometric Coronagraph, or LASCO, is the instrument that provides most of the imagery, with two coronagraph telescopes designed to block direct blinding sunlight and observe the much fainter solar corona and solar outflows. As an unintended consequence of the instrument’s sensitivity, LASCO also detects large numbers of previously unknown sungrazing comets.
Thus, any algorithms that can provide enhancements to the data, including reduction of noise and/or tracking of features in motion, are highly desirable and could potentially extend beyond just comet discovery and tracking, and may be applicable to coronagraph imagery on other heliophysics observatories.
The SOHO/LASCO data set provided here comes from the instrument’s C2 telescope and comprises approximately 36,000 images spread across 2,950 comet observations. The human eye is a very sensitive tool and it is the only tool currently used to reliably detect new comets in SOHO data - particularly comets that are very faint and embedded in the instrument background noise. Bright comets can be easily detected in the LASCO data by relatively simple automated algorithms, but the majority of comets observed by the instrument are extremely faint, noise-level observations. Comets in SOHO/LASCO data are dynamic and morphologically diverse objects, and thus computationally highly complex to detect and track.
This work is supported by the NASA Open Source Science Initiative and is part of efforts to showcase the cross-disciplinary use of NASA’s science data and encourage public engagement with science data-related problems.
Congratulations to the winners:
This section will have several useful links and videos for members to learn more about Topcoder and the NASA SOHO Comet Search With Artificial Intelligence. We’ll continue to add great content here to help you be successful.
- What are Topcoder challenges?
- Support Vector Machine: A Machine Learning Algorithm
- How Does the Machine Read Images and Use them in Computer Vision?
- Asteroid Data Hunter Challenge
- NASA’s Asteroid Data Hunter