Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning

Solar activity plays a quintessential role in influencing the interplanetary medium and space-weather around Earth. Remote sensing instruments onboard heliophysics space missions provide pool of information about Sun's via measurement its magnetic field emission light from multi-layered, multi-thermal, dynamic solar atmosphere. Extreme UV (EUV) wavelength observations help understanding subtleties outer layers Sun, namely chromosphere corona. Unfortunately, such instruments, like Atmospheric Imaging Assembly (AIA) NASA's Dynamics Observatory (SDO), suffer time-dependent degradation, reducing their sensitivity. Current state-of-the-art calibration techniques rely on periodic sounding rockets, which can be infrequent rather unfeasible for deep-space missions. We present an alternative approach based convolutional neural networks (CNNs). use SDO-AIA data our analysis. Our results show that CNN-based models could comprehensively reproduce rocket experiments' outcomes within reasonable degree accuracy, indicating it performs equally well compared with current techniques. Furthermore, comparison standard "astronomer's technique" baseline model reveals CNN significantly outperforms this baseline. establishes framework novel technique to calibrate EUV advance cross-channel relation between different channels.