Year: 2020
Type: preprint
Abstract: A complete study with realistic environment models, multiple processes, single optimized DNN, focused on a single prediction task (elemental ratios at surface). A complete, published as a pre-print in ESSOAr, paper of a second, more-focused study of the chronological collection of manuscripts exploring the conceptual application of machine-learning algorithms for the reconstruction of Mercury's surface composition from simulated exospheric measurements. Single DNN type: An optimized MLP with 4 hidden layers. Elemental composition prediction (11 elements) from exospheric elemental measurements; maps reconstruction and analysis; metrics evaluations. Simulated dataset - realistic assumptions for the release processes (4 main processes - MIV, SP, PSD, TD), exospheric dynamics included; chemistry, magnetic field influences, and testing on actual Mercury surface and exosphere are not included.
Source: arXiv (Cornell University)
Authors: Kazakov, Adrian, Milillo, Anna, Mura, Alessandro, Ivanovski, Stavro, Mangano, Valeria, Aronica, Alessandro, De Angelis, Elisabetta, Di Bartolomeo, Pier Paolo, Brin, Alessandro, Colasanti, Luca, Escalona-Moran, Miguel, Lazzarotto, Francesco, Massetti, Stefano, Moroni, Martina, Noschese, Raffaella, Nuccilli, Fabrizio, Orsini, Stefano, Plainaki, Christina, Richards, Grace, Rispoli, Rosanna, Sordini, Roberto, Stumpo, Mirko, Vertolli, Nello
Language: English
Topic: Astro and Planetary Science
Subfield: Astronomy and Astrophysics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
Funder: Agenzia Spaziale Italiana
Awards: G2462362907, G5065560689, G698336051
OpenAlex ID: W4417093589
Cites:
Cited by:
Related to: