Space Weather forecasting methods for the HENON mission

One of the main objectives of the HEliospheric pioNeer for sOlar and interplanetary threats defeNce (HENON) mission is the provision of  alerts for potential harmful Space Weather events, such as Solar Energetic Particle (SEP) events and geomagnetic storms. Therefore,  we have developed several types of methods and have evaluated their performance. In particular, we have implemented a machine learning model, based on the Random Forest Regressor algorithm, to forecast SEP events at the Earth by using HENON observations of only energetic electrons which will be made by the REPE detector. The model can provide a reliable prediction of the >10 MeV proton flux expected at the Earth with an advance of 1 hour (i.e., before an increase of the proton flux is directly measured) by taking as input: the electron flux in four differential channels between 0.25 and 10.40  MeV; their derivatives; the proton derivative in the integral channel between 7-8 and 53 MeV; these nine physical observables multiplied by the two statistical measures (mean and standard deviation). For forecasting geomagnetic storms,  we have developed two methods which will exploit data of the solar wind velocity velocity V from the FCA instrument and the magnetic field (IMF) from the MAGIC instrument. The first method uses both V and the IMF southward component Bz. It provides an alert if both the VBz parameter and the Bz component have values that are above the chosen thresholds (4 mV/m and -6 nT for the VBz and the Bz) for at least 3 hours. The second method is an Artificial Neural Network (ANN) for making a real-time regression of SYM-H index. We adapted the EDDA (Empirical Dst Data Algorithm) algorithm, developed by Pallocchia et al. (2016), using only magnetic field data,  to predict the Sym-H index 1 hour ahead every 20 minutes. We remark that HENON observations will allow us to compute alerts of geoeffective storms with a 10 time improvement in the lead times with respect to current predictions.