Solar and Stellar Astrophysics (astro-ph.SR)

Abstract: Solar flare forecasting research using machine learning (ML) has focused on high resolution magnetogram data from the SDO/HMI era covering Solar Cycle 24 and the start of Solar Cycle 25, with some efforts looking back to SOHO/MDI for data from Solar Cycle 23. In this paper, we consider over 4 solar cycles of daily historical magnetogram data from multiple instruments. This is the first attempt to take advantage of this historical data for ML-based flare forecasting. We apply a convolutional neural network (CNN) to extract features from full-disk magnetograms together with a logistic regression model to incorporate scalar features based on magnetograms and flaring history. We use an ensemble approach to generate calibrated probabilistic forecasts of M-class or larger flares in the next 24 hours. Overall, we find that including historical data improves forecasting skill and reliability. We show that single frame magnetograms do not contain significantly more relevant information than can be summarized in a small number of scalar features, and that flaring history has greater predictive power than our CNN-extracted features. This indicates the importance of including temporal information in flare forecasting models.

Abstract: High resolution spectral observations of the lower solar atmosphere (chromosphere and transition region) during coronal heating events, in combination with predictions from models of impulsively heated loops, provide powerful diagnostics of the properties of the heating in active region cores. Here we analyze the first coordinated observations of such events with the Interface Region Imaging Spectrograph (IRIS) and the CHROMospheric Imaging Spectrometer (CHROMIS), at the Swedish 1-m Solar Telescope (SST), which provided extremely high spatial resolution and revealed chromospheric brightenings with spatial dimensions down to ~150km. We use machine learning methods (k-means clustering) and find significant coherence in the spatial and temporal properties of the chromospheric spectra, suggesting, in turn, coherence in the spatial and temporal distribution of the coronal heating. The comparison of IRIS and CHROMIS spectra with simulations suggest that both non-thermal electrons with low energy (low-energy cutoff ~5keV) and direct heating in the corona transported by thermal conduction contribute to the heating of the low atmosphere. This is consistent with growing evidence that non-thermal electrons are not uncommon in small heating events (nano- to micro-flares), and that their properties can be constrained by chromospheric and transition region spectral observations.