GIULIA CIABATTI

PhD Graduate

PhD program:: XXXVII


supervisor: Roberto Capobianco
co-supervisor: Shreyansh Daftry

Thesis title: Geometry-Informed Neural Architectures for Spatiotemporal Sensing and Spaceborne Autonomy: Operator-Embedded and Manifold-Aware Spectral Learning Frameworks

Modern spaceborne sensing and autonomous systems increasingly rely on deep learning methods for tasks, such as: reconstruction, classification, object extraction, tracking, and dynamical modeling. However, conventional, state-of-the-art neural architectures generally treat geometry as an emergent property, inferred from data rather than as a structural prior. This often leads to models that are physically inconsistent, too reliant on data volume, and difficult to interpret and validate in safety-critical aerospace applications. This thesis develops a unified framework for geometry-informed neural architectures, where spatial, spectral, functional, and temporal geometrical priors are directly embedded into learning systems. The central hypothesis is that incorporating geometry, such as: differential operators, spectral representations, and manifold-aware constraints within neural architectures improves robustness, physical consistency, and physics-consistent generalization in spaceborne sensing and autonomy tasks. The thesis presents four principal contributions. First, a spatial geometry-informed reconstruction framework is introduced for soil moisture field estimation from sparse satellite observations. Fixed, discrete differential operators and geometrical structures are embedded into a neural model, enabling edge-aware interpolation and improved, high-definition reconstruction fidelity without excessive parameterization. Second, geometry is extended from reconstruction to object extraction, i.e. objectization, and temporal reasoning. A spectral pipeline based on Laplace-Beltrami embeddings is developed to represent reconstructed geophysical fields as coherent-across-temporal-domain geometric objects. This formulation enables geometry-consistent feature tracking across time and preserves intrinsic shape structure. Third, a novel framework for geometry-informed autonomous dynamics modeling is proposed through Laplacian-Spectral Dynamic Movement Primitives - LSDMPs. By expanding trajectory forcing terms in the eigenbasis of a temporal graph Laplacian, orbital dynamics modeling is cast as a geometry-aware spectral approximation problem. This establishes a unified operator-theoretic perspective connecting spatial Laplace-Beltrami embeddings and temporal Laplacian representations. Finally, the work develops geometry embedding to the functional and Hilbert-space domain for remote sensing image classification. Instead of relying only on learned convolutional filters, operator-defined mappings project image patches into high-dimensional functional spaces, enforcing inner-product structure and promoting structured feature representations. The dissertation demonstrates that embedding geometry explicitly - rather than learning it implicitly - provides a reliable method towards more physics-consistent and stable neural systems for spaceborne applications - with a particular attention to remote sensing. The resulting framework bridges differential geometry, spectral graph theory, and deep learning, and defines geometry-informed neural designs as a viable paradigm for next-generation remote sensing and autonomous aerospace systems.

Research products

11573/1753386 - 2025 - Quanv4EO. Empowering Earth Observation by means of Quanvolutional Neural Networks
Sebastianelli, Alessandro; Mauro, Francesco; Ciabatti, Giulia; Spiller, Dario; Le Saux, Bertrand Honore Henri; Gamba, Paolo; Ullo, Silvia - 01a Articolo in rivista
paper: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (New York, N.Y. : Institute of Electrical and Electronics Engineers) pp. - - issn: 1558-0644 - wos: WOS:001473296000020 (10) - scopus: 2-s2.0-105003644327 (11)

11573/1684593 - 2023 - Deep Reinforcement Learning for Pin-Point Autonomous Lunar Landing: Trajectory Recalculation for Obstacle Avoidance
Ciabatti, Giulia; Spiller, Dario; Daftry, Shreyansh; Capobianco, Roberto; Curti, Fabio - 02a Capitolo o Articolo
book: AII 2022: The Use of Artificial Intelligence for Space Applications - (978-3-031-25754-4; 978-3-031-25755-1)

11573/1700251 - 2022 - A Moon Optical Navigation Robotic Facility on Simulated TERrain: MONSTER
Latorre, Francesco; Carbone, Andrea; Thottuchirayil Sasidharan, Sarathchandrakumar; Ciabatti, Giulia; Spiller, Dario; Curti, Fabio; Capobianco, Roberto - 04c Atto di convegno in rivista
paper: THE JOURNAL OF THE ASTRONAUTICAL SCIENCES (New York N.Y.: Springer) pp. - - issn: 2195-0571 - wos: (0) - scopus: (0)
conference: 2022 AAS/AIAA Astrodynamics Specialist Conference (Charlotte, NC, USA)

11573/1604061 - 2021 - Learning transferable policies for autonomous planetary landing via deep reinforcement learning
Ciabatti, G.; Daftry, S.; Capobianco, R. - 04b Atto di convegno in volume
conference: Accelerating Space Commerce, Exploration, and New Discovery conference, ASCEND 2021 (Las Vegas, Nevada USA)
book: Accelerating Space Commerce, Exploration, and New Discovery conference, ASCEND 2021 - (978-1-62410-612-5)

11573/1573792 - 2021 - Autonomous Planetary Landing via Deep Reinforcement Learning and Transfer Learning
Ciabatti, Giulia; Daftry, Shreyansh; Capobianco, Roberto - 04b Atto di convegno in volume
conference: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 (Virtual)
book: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) - (978-1-6654-4899-4)

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma