Utilizing Acoustic Power Maps and Machine Learning for Early Detection of Active Region Emergence

The development of an accurate forecast for solar eruptive activity has become increasingly important in order to prevent any potential impact on activities in space and the Earth’s environment. Therefore, it is crucial to detect active regions before they appear on the solar surface, which will enable the creation of early warning capabilities for upcoming Space Weather disturbances. To accomplish this, we have created a catalog of emerging active and quiet-Sun regions, which allows us to identify characteristic features in the evolution of acoustic power density to predict magnetic flux emergence. For our study, we have utilized Doppler shift and continuum intensity full-disk images obtained with a 45-sec cadence from the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO). Our approach involves local tracking of 30x30-degree patches in the vicinity of active regions before their emergence on the solar surface, which allows us to observe the response of the acoustic power density in various oscillation frequency bands to the upcoming emergence of magnetic flux. We have developed a machine learning model to capture variations of the acoustic power flux density associated with upcoming magnetic flux emergence. The performed study allows us to investigate the potential of the machine learning approach to predict the emergence of active regions using the acoustic power maps as input.