AI for Space Operations

I develop estimation and optimisation methods for space operations, with machine learning used for orbit prediction and information support. Conjunction analysis addresses uncertainty in the positions of orbiting objects. Satellite-network research studies topology decisions over time.

This topic also includes language models and retrieval-augmented generation for operational documents, and OrbitZoo as a benchmark for reinforcement learning in orbital systems.

The papers below connect these methods with data quality, atmospheric density forecasting and collision-risk prediction. Work on orbital dynamics and conjunction data also examines how physical and statistical models can inform the use of machine learning.

Funded projects

Projects active during 2021 or later, including completed projects.

• Thermospheric density estimation with generative diffusion models (2025). Principal investigator. Computing project on thermospheric density forecasting and uncertainty quantification. Reference 2024.12852.CPCA.
• TaRDIS (2023–2026). Task leader. Decentralised learning and task orchestration for edge systems, with use cases including satellite swarms and distributed marketplaces. Reference 101093006.
• Artificial Intelligence Fights Space Debris (2022–2026). Local PI. Collision-risk prediction and machine learning for space traffic management, in collaboration with Neuraspace. Reference C626449889-0046305.

Publications since 2021

• Satellite Safe Margin: Fast Solutions for Conjunction Analysis. Journal of Guidance, Control, and Dynamics, 2026.
• ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations. NeurIPS 2026.
• A Systematic Evaluation of Retrieval-Augmented Generation and Language Models for Space Operations. AI4Space, 2026.
• Data-Centric Preprocessing for GNSS-Based Orbit Determination via AI, Signal Processing, and Orbital Dynamics. SPAICE 2026.
• Generalizing Trilateration: Approximate Maximum Likelihood Estimator for Initial Orbit Determination in Low Earth Orbit. IEEE Transactions on Aerospace and Electronic Systems, 2025.
• OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning. NeurIPS 2025 poster.
• Language Modeling and Retrieval-Augmented Generation for Integration in Space Operation Decision Support Tools. 58th IAA Symposium on Safety, Quality and Knowledge Management in Space Activities, 2025.
• Machine learning in orbit estimation: A survey. Acta Astronautica, 2024.
• Precise and Efficient Orbit Prediction in LEO with Machine Learning using Exogenous Variables. 2024 IEEE Congress on Evolutionary Computation (CEC).
• One-Shot Initial Orbit Determination in Low-Earth Orbit. Accepted at the IEEE Aerospace Conference, 2024.
• AI for space traffic management. Journal of Space Safety Engineering, 2023.
• Taxonomy for Resident Space Objects in LEO. Accepted in the International Astronautical Congress 2023.
• Predicting the Position Uncertainty at the Time of Closest Approach with Diffusion Models. Accepted in the International Astronautical Congress 2023.
• Conjunction Data Messages behave as a Poisson Process. Workshop on AI for Spacecraft Longevity, 2021.

Preprints and related manuscripts since 2021

• Analyzing Data Quality and Decay in Mega-Constellations: A Physics-Informed Machine Learning Approach. arXiv preprint, 2025.
• Predicting the Probability of Collision of a Satellite with Space Debris: A Bayesian Machine Learning Approach. arXiv preprint, 2023.
• Finding Real-World Orbital Motion Laws from Data. arXiv preprint, 2023.
• Probability of Collision of satellites and space debris for short-term encounters: Rederivation and fast-to-compute upper and lower bounds. arXiv preprint, 2023.
• Statistical Learning of Conjunction Data Messages Through a Bayesian Non-Homogeneous Poisson Process. arXiv preprint, 2023.