The Exoplanet Citizen Science Pipeline: Human Factors and Machine Learning
This work addresses the problem of enabling wider participation and efficiency in citizen science projects for exoplanet observation, though it is incremental as it builds on existing collaborations like ExoClock and Exoplanet Watch.
The paper tackles the challenge of streamlining exoplanet observation for citizen scientists by combining human-centric design and machine learning to reduce barriers and automate data processing, resulting in a scalable solution for large-scale research.
We present the progress of work to streamline and simplify the process of exoplanet observation by citizen scientists. International collaborations such as ExoClock and Exoplanet Watch enable citizen scientists to use small telescopes to carry out transit observations. These studies provide essential supports for space missions such as JWST and ARIEL. Contributions include maintenance or recovery of ephemerides, follow up confirmation and transit time variations. Ongoing observation programs benefit from a large pool of observers, with a wide variety of experience levels. Our projects work closely with these communities to streamline their observation pipelines and enable wider participation. Two complementary approaches are taken: Star Guide applies human-centric design and community consultation to identify points of friction within existing systems and provide complementary online tools and resources to reduce barriers to entry to the observing community. Machine Learning is used to accelerate data processing and automate steps which are currently manual, providing a streamlined tool for citizen science and a scalable solution for large-scale archival research.