Improving the Automated Coronal Jet Identification with U-NET

Abstract Coronal jets are one of the most common eruptive activities in the solar atmosphere. They are related to rich physics processes, including, but not limited to, magnetic reconnection, flaring, instabilities, and plasma heating. Automated identification of off-limb coronal jets has been difficult due to their abundant nature, complex appearance, and relatively small size compared to other features in the corona. In this paper, we present an automated jet identification algorithm (AJIA) that utilizes true and fake jets previously detected by a laborious semiautomated jet detection algorithm (SAJIA) as the input of an image segmentation neural network U-NET. It is found that AJIA can achieve a much higher (0.81) detecting precision than SAJIA (0.34) while giving the possibility of whether each pixel in an input image belongs to a jet. We demonstrate that with the aid of artificial neural networks, AJIA can enable fast, accurate, and real-time off-limb coronal jet identification from Solar Dynamics Observatory/Atmospheric Imaging Assembly 304 Å observations, which are essential in studying the collective and long-term behavior of coronal jets and their relation to the solar activity cycles.