The forecasting of local GIC effects has largely relied on the forecasting of dB/dt as a proxy and, to date, little attention has been paid to directly forecasting the geoelectric field or GICs themselves. We approach this problem with machine learning tools, specifically recurrent neural networks or LSTMs by taking solar wind observations as input and training the models to predict two different kinds of output: first, the geoelectric field components Ex and Ey; and second, the GICs in specific substations in Austria. The training is carried out on the geoelectric field and GICs modelled from 26 years of one-minute geomagnetic field measurements, and results are compared to GIC measurements from recent years. The GICs are generally predicted better by an LSTM trained on values from a specific substation, but only a fraction of the largest GICs are correctly predicted. This model had a correlation with measurements of around 0.6, and a root-mean-square error of 0.7 A. The probability of detecting mild activity in GICs is around 50%, and 15% for larger GICs.

Accurate forecasting of the arrival time and arrival speed of coronal mass ejections (CMEs) is a unsolved problem in space weather research. In this study, a comparison of the predicted arrival times and speeds for each CME based, independently, on the inputs from the two STEREO vantage points is carried out. We perform hindcasts using ELlipse Evolution model based on Heliospheric Imager observations (ELEvoHI) ensemble modelling. An estimate of the ambient solar wind conditions is obtained by the Wang-Sheeley-Arge/Heliospheric Upwind eXtrapolation (WSA/HUX) model combination that serves as input to ELEvoHI. We carefully select 12 CMEs between February 2010 and July 2012 that show clear signatures in both STEREO-A and STEREO-B HI time-elongation maps, that propagate close to the ecliptic plane, and that have corresponding in situ signatures at Earth. We find a mean arrival time difference of 6.5 hrs between predictions from the two different viewpoints, which can reach up to 9.5 hrs for individual CMEs, while the mean arrival speed difference is 63 km s$^{-1}$. An ambient solar wind with a large speed variance leads to larger differences in the STEREO-A and STEREO-B CME arrival time predictions ($cc = 0.92$). Additionally, we compare the predicted arrivals, from both spacecraft, to the actual in situ arrivals at Earth and find a mean absolute error of 7.5 $\pm$ 9.5 hrs for the arrival time and 87 $\pm$ 111 km s$^{-1}$ for the arrival speed. There is no tendency for one spacecraft to provide more accurate arrival predictions than the other.

The evolution and propagation of coronal mass ejections (CMEs) in interplanetary space is still not well understood. As a consequence, accurate arrival time and arrival speed forecasts are an unsolved problem in space weather research. In this study, we present the ELlipse Evolution model based on HI observations (ELEvoHI) and introduce a deformable front to this model. ELEvoHI relies on heliospheric imagers (HI) observations to obtain the kinematics of a CME. With the newly developed deformable front, the model is able to react to the ambient solar wind conditions during the entire propagation and along the whole front of the CME. To get an estimate of the ambient solar wind conditions, we make use of three different models: Heliospheric Upwind eXtrapolation model (HUX), Heliospheric Upwind eXtrapolation with time dependence model (HUXt), and EUropean Heliospheric FORecasting Information Asset (EUHFORIA). We test the deformable front on a CME first observed in STEREO-A/HI on February 3, 2010 14:49 UT. For this case study, the deformable front provides better estimates of the arrival time and arrival speed than the original version of ELEvoHI using an elliptical front. The new implementation enables us to study the parameters influencing the propagation of the CME not only for the apex, but for the entire front. The evolution of the CME front, especially at the flanks, is highly dependent on the ambient solar wind model used. An additional advantage of the new implementation is given by the possibility to provide estimates of the CME mass.