Bachelor's degree theses

NOTE: In order to apply for any of the following theses or internships, the candidate must have no more than 3 exams left.

MACHINE LEARNING

Multi-Class Satellite Image Classification with PyTorch

This thesis aims to develop a deep neural network in PyTorch for multi-class satellite classification problem, evaluating various CNN architectures and loss functions for optimal classification accuracy.

COLLISION AVOIDANCE – SPACE DEBRIS

Effects of Earth albedo on the visual magnitude of artificial satellites in the context of space-based optical tracking

Satellite-to-satellite optical tracking is increasingly gaining attention due to its applications in space-based surveillance systems and opportunistic situational awareness. The effectiveness of such systems is based on the detectability of the target from the camera onboard the observer satellite, which, in turn, depends on the visual magnitude of the target.

Usually, this last is estimated based on the reflected solar flux. However, when the target travels in LEO, the contribution of Earth's albedo may be significant. The thesis aims to develop a mathematical model of the visual magnitude of a LEO spacecraft, including the effect of the Earth's albedo, tailored to the scenario when the observer is an orbiting platform. A numerical simulation tool shall also be developed to assess the predictions of the mathematical model as a function of the observer and target orbits and evaluate the impact of Earth Albedo on the overall visual magnitude of the target. 

Contacts

Prof. Alfredo Locarini

Via Fontanelle 40, 47121 Forlì (FC)

Write an e-mail

Go to the website

Available by appointment

Prof. Dario Modenini

Via Fontanelle 40, 47121 Forlì (FC)

+39 0543 374 450

Write an e-mail

Go to the website

Available by appointment

Prof. Paolo Tortora

Via Fontanelle 40, 47121 Forlì (FC)

+39 0543 374456

Write an e-mail

Go to the website

Available by appointment