ThermoONet -- a deep learning-based small body thermophysical network: applications to modelling water activity of comets
This work addresses the problem of slow modeling for researchers studying cometary activity, offering a significant speed-up while maintaining accuracy, though it is incremental as it applies existing deep learning methods to a specific domain.
The authors tackled the computational intensity of traditional thermophysical models for comets by developing ThermoONet, a neural network that predicts temperature and water ice sublimation flux with about 2% error and reduces computation time by nearly six orders of magnitude, as demonstrated by fitting water production rates for comets 67P and 21P.
Cometary activity is a compelling subject of study, with thermophysical models playing a pivotal role in its understanding. However, traditional numerical solutions for small body thermophysical models are computationally intensive, posing challenges for investigations requiring high-resolution or repetitive modeling. To address this limitation, we employed a machine learning approach to develop ThermoONet - a neural network designed to predict the temperature and water ice sublimation flux of comets. Performance evaluations indicate that ThermoONet achieves a low average error in subsurface temperature of approximately 2% relative to the numerical simulation, while reducing computational time by nearly six orders of magnitude. We applied ThermoONet to model the water activity of comets 67P/Churyumov-Gerasimenko and 21P/Giacobini-Zinner. By successfully fitting the water production rate curves of these comets, as obtained by the Rosetta mission and the SOHO telescope, respectively, we demonstrate the network's effectiveness and efficiency. Furthermore, when combined with a global optimization algorithm, ThermoONet proves capable of retrieving the physical properties of target bodies.