Surface information derived from exospheric measurements at planetary bodies complements surface mapping provided by dedicated imagers, offering critical insights into surface release processes, dynamics of various interactions within the planetary environment, erosion, space weathering, and planetary evolution. This study explores a method for deriving the elemental composition of Mercury’s regolith from in-situ measurements of its neutral exosphere using deep neural networks (DNNs). We present a supervised feed-forward DNN architecture—a network of fully-connected neural layers, the so-called multilayer perceptron (MLP). This network takes exospheric densities and proton precipitation fluxes, derived from a simulated orbital run through Mercury’s exosphere, as inputs and predicts the chemical elements of the surface regolith below. It serves as an estimator for the surface-exosphere interaction and the processes leading to exosphere formation, including micrometeoroid impact vaporization, ion sputtering, photon-stimulated desorption, and thermal desorption. Extensive training and testing campaigns demonstrate the MLP DNN’s ability to accurately predict and reconstruct surface composition maps from simulated exospheric measurements. These results not only affirm the algorithm’s robustness but also illuminate its extensive capabilities in handling complex data sets for the creation of estimators for modeled exospheric generation. Furthermore, the tests reveal substantial potential for further development, suggesting that this method could significantly enhance the analysis of complex surface-exosphere interactions and reduce uncertainties in planetary exospheres models. This work anticipates the analysis of data from the SERENA (Search for Exospheric Refilling and Emitted Natural Abundances) instrument package aboard the BepiColombo Mercury Planetary Orbiter, with its nominal phase starting in 2026.

Several techniques have been developed in the last two decades to forecast the occurrence of Solar Proton Events (SPEs), mainly based on the statistical association between the $>$10 MeV proton flux and precursor parameters. The Empirical model for Solar Proton Events Real Time Alert (ESPERTA, Laurenza et al., 2009) provides a quite good and timely prediction of SPEs after the occurrence of $\geq$M2 X-ray bursts, by using as input parameters the flare heliolongitude, the soft X-ray and the $\sim$1 MHz radio fluence. Here, we reinterpret the ESPERTA model in the framework of machine learning and perform a cross validation, leading to a comparable performance. Moreover, we find that, by applying a cut-off on the $\geq$M2 flares heliolongitude, the False Alarm Rate (FAR) is reduced. The cut-off is set to E20° where the cumulative distribution of $\geq$M2 flares associated with SPEs shows a break which reflects the poor magnetic connection between the Earth and eastern hemisphere flares. The best performance is obtained by using the SMOTE algorithm, leading to probability of detection of 0.83 and a FAR of 0.39. Nevertheless, we demonstrate that a relevant FAR on the predictions is a natural consequence of the sample base rates. From a Bayesian point of view, we find that the FAR explicitly contains the prior knowledge about the class distributions. This is a critical issue of any statistical approach, which requires to perform the model validation by preserving the class distributions within the training and test datasets.