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.