Solar flare forecasting is one of major components of operational space weather forecasting. Complex active regions (ARs) are the main source producing major flares, but only a few studies are carried out to establish flare forecasting models for these ARs. In this study, four deep learning models, called Complex Active Region Flare Forecasting Model (CARFFM)-1, −2, −3, and −4, are established. They take AR longitudinal magnetic fields, AR vector magnetic fields, AR longitudinal magnetic fields and the total unsigned magnetic flux in the neutral line region, AR vector magnetic fields and the total unsigned magnetic flux in the neutral region as input, respectively. These four models can predict the production of M-class or above flares in the complex ARs for the next 48 h. Through comparing the performance of the models, CARFFM-4 has the best forecasting ability, which has the most abundant input information. It is suggested that more valuable and rich input can improve the model performance.
The plasmasphere is a region of cold and dense plasma around the Earth, corotating with the Earth. Its plasma density is very dynamic under the influence of the solar wind and it influences several processes such as the GPS navigation, the surface charging of the satellites and the propagation and growth of plasma waves. In this manuscript, we present a new machine-learning model of the equatorial plasma density depending only on the Kp index and the solar-wind properties at the L1 Lagrange point. We call this model PINE-RT as it has been inspired by the recently-introduced PINE (Plasma density in the Inner magnetosphere Neural network-based Empirical) model and it has been developed to run in real-time (RT) in the context of the PAGER project. This project is an EU Horizon 2020 project aiming at forecasting the threats of satellite charging as a consequence of the solar activity 1–2 days ahead. In PAGER, the Kp index and the solar-wind properties at L1 are the inputs which are made available for the plasmasphere modeling. We report here the detailed derivation of the PINE-RT model and its validation and comparison with two state-of-the-art machine-learning and physics-based models. The model is currently running in real-time and its predictions are publicly available.
Two algorithms set for automatic detection of bow shock (BS) and magnetopause (MP) boundaries at Saturn using in situ magnetic field and plasma data acquired by the Cassini spacecraft are presented. Traditional threshold-based and modern deep learning algorithms were investigated for the task of boundary detection. Sections of Cassini’s orbits were pre-selected based on empirical BS and MP boundary models, and from outlier detection in magnetic field data using an autoencoder neural network. The threshold method was applied to pre-selected magnetic field and plasma data independently to compute parameters to which a threshold was applied to determine the presence of a boundary. The deep learning method used a type of convolutional neural network (CNN) called ResNet on images of magnetic field time series data and electron energy-time spectrograms to classify the presence of boundaries. 2012 data were held out of the training data to test and compare the algorithms on unseen data. The comparison showed that the CNN method applied to plasma data outperformed the threshold method. A final multiclass CNN classifier trained on plasma data obtained F1 scores of 92.1% ± 1.4% for BS crossings and 84.7% ± 1.9% for MP crossings on a corrected test dataset (from use of a bootstrap method). Reliable automated detection of boundary crossings could enable future spacecraft experiments like the PEP instrument on the upcoming JUICE spacecraft mission to dynamically adapt the best observing mode based on rapid classification of the boundary crossings as soon as it appears, thus yielding higher quality data and improved potential for scientific discovery.