Analysis of Solar Activity Complexes Based on Data from Different Layers of the Atmosphere

Solar activity, which is associated with the dynamics of magnetic fields, can be observed in various spectral ranges. The magnetic field of the sun at the level of the photosphere is a spatio-temporal chaos, in which large values of the field are localized in individual active regions (ARs) and their complexes. The dynamics of ARs are accompanied by emergent phenomena such as solar flares, prominences, and coronal mass ejections (CMEs), which can affect the parameters of the solar wind near Earth and lead to disruptions in radio communications, failures of equipment on spacecraft, and other harmful effects. All this makes predicting emergent scenarios of solar flares and CMEs an important task. Currently, this is often approached through statistical criteria and machine learning techniques. Most existing forecasting systems are based on photospheric data, but at the moment there are no large-scale forecasting systems that use radio data.At the same time, according to modern theories of flare processes, large flares originate in the chromosphere and corona, which is where radio emission takes place. Therefore, the use of radio data holds potential. This work aims to explore active regions in the radio spectrum and develop a user-friendly interface for analyzing this type of astronomical data to further assess its usefulness in predicting solar activity.