Automatic Classification of Transiting Planet Candidates using Deep Learning

Space-based missions such as Kepler, and now TESS, provide large datasets that must be analyzed efficiently and systematically. Shallue & Vanderburg (2018) recently used state-of-the-art deep learning models to successfully classify Kepler transit signals as either exoplanets or false positives. We expand upon that work by including additional "scientific domain knowledge" into the network architecture and input representations to significantly increase overall model performance to 97.5% accuracy and 98.0% average precision. Notably, we achieve 15-20% gains in recall for the lowest signal-to-noise transits that can correspond to rocky planets in the habitable zone. This work illustrates the importance of including expert domain knowledge in even state-of-the-art deep learning models when applying them to scientific research problems that seek to identify weak signals in noisy data.