Ground magnetic observatories measure the Earth’s magnetic field and its coupling with the solar wind responsible for ionospheric and magnetospheric current systems. Predicting effects of solar- and atmospheric-driven disturbances is a crucial task. Using data from the magnetic observatory Chambon-la-Forêt at mid-latitude, we investigate the capability of our developed deep artificial neural networks in the modeling of the contributions above 24 hours and the daily variations. Two neural networks were built with the long short-term memory architecture with multiple layers. Using the data from 1995 onwards, the neural networks were trained with physical parameters indicative of solar variabilities and geographical daily and seasonal variations. By excluding the secular variation owing to the change of the Earth’s intrinsic magnetic field, we demonstrate that our approach can model the observed signals with overall good agreements for both a solar-quiet period in 2009 and a solar-active period in 2012. Particularly, using the walk forward training, we updated our models with new data leading up to the test year. The implication of this work is twofold. First, our approach can be adapted for near real-time prediction of intensity of solar and atmospheric disturbances. Second, the neural networks can be used to model the quiet variations when excluding the solar variabilities with important applications in the calculation of magnetic activity indices. This work is a proof-of-concept that deep neural networks can be used to model solar- and atmospheric-driven perturbations modulated by daily and seasonal variations as recorded at a ground magnetic observatory.

Flux Transfer Events (FTEs) are transient magnetic flux ropes typically found at the Earth’s magnetopause on the dayside. While it is known that FTEs are generated by magnetic reconnection, it remains unclear how the details of magnetic reconnection controls their properties. A recent study showed that the helicity sign of FTEs positively correlates with the east-west (By) component of the Interplanetary Magnetic Field (IMF). With data from the Cluster and Magnetospheric Multiscale missions, we performed a statistical study of 166 quasi force-free FTEs. We focus on their helicity sign and possible association with upstream solar wind conditions and local magnetic reconnection properties. Using both in situ data and magnetic shear modeling, we find that FTEs whose helicity sign corresponds to the IMF By are associated with moderate magnetic shears while those that does not correspond to the IMF By are associated with higher magnetic shears. While uncertainty in IMF propagation to the magnetopause may lead to randomness in the determination of the flux rope core field and helicity, we rather propose that for small IMF By, which corresponds to high shear and low guide field, the Hall pattern of magnetic reconnection determines the FTE core field and helicity sign. In that context we explain how the temporal sequence of multiple X-line formation and the reconnection rate are important in determining the flux rope helicity sign. This work highlights a fundamental connection between kinetic processes at work in magnetic reconnection and the macroscale structure of FTEs.