Starshade Exoplanet Data Challenge: What We Learned

Abstract

Starshade is one of the technologies that will enable the observation and characterization of small planets around nearby stars through direct imaging. The Starshade Exoplanetary Data Challenge (SEDC) was designed to validate starshade-imaging's noise budget and evaluate the capabilities of image-processing techniques, by inviting community participating teams to analyze >1000 simulated images of hypothetical exoplanetary systems observed through a starshade. Because the starshade would suppress the starlight so well, the dominant noise source and the main challenge for the planet detection becomes the exozodiacal disks and their structures. In this paper, we summarize the techniques used by the participating teams and compare their findings with the truth. With an independent component analysis to remove the background, about 70% of the inner planets (close to the inner working angle) have been detected and ~40% of the outer planet (fainter than the inner counterparts) have been identified. Planet detection becomes more difficult in the cases of higher disk inclination, as the false negative and false positive counts increase. Interestingly, we found little difference in the planet detection ability between 1e-10 and 1e-9 instrument contrast, confirming that the dominant limitations are from the astrophysical background and not due to the performance of the starshade. Finally, we find that a non-parametric background calibration scheme, such as the independent component analysis reported here, results in a mean residual of 10% the background brightness. This background estimation error leads to substantial false positives and negatives and systematic bias in the planet flux estimation, and should be included in the estimation of the planet detection signal-to-noise ratio for imaging using a starshade and also a coronagraph that delivers exozodi-limited imaging.