Francisco
Caldas

PhD student at NOVA School of Science and Technology.

Presentation

I am a PhD student at the NOVA School of Science and Technology (Portugal), since 2022, under the supervision of Cláudia Soares (NOVA School of Science and Technology). The PhD is funded by PTSpace (Portuguese Space Agency) and it is directed towards the area of space safety using Machine learning. Our goal is to use data and machine learning algorithms to improve Orbit Determination of satellites and space debris in Low Earth Orbit (LEO). This goal touches on several areas of knowledge, from orbital mechanics and space weather forecast, to probabilistic forecasting, explainable AI and physics-informed machine learning. In this page you will be able to follow my most recent work, with paper and code available when possible, alongside other projects and interesting collaborations.

Main Research

September 1, 2023

Precise and Efficient Orbit Prediction in LEO with Machine Learning using Exogenous Variables

The increasing volume of space objects in Earth’s orbit presents a significant challenge for Space Situational Awareness (SSA). Accurate orbit prediction is crucial to anticipate the position and velocity of space objects, for collision avoidance and space debris mitigation. However, conventional propagator methods like the SGP4 inadequately account for non-conservative forces, leading to uncertainty in future positions.

September 1, 2022

A Temporal Fusion Transformer for Long-term Explainable Prediction of Emergency Department Overcrowding

Emergency Departments (EDs) are a fundamental element of the Portuguese National Health Service, serving as an entry point for users with diverse and very serious medical problems. Due to the inherent characteristics of the ED, forecasting the number of patients using the services is particularly challenging. And a mismatch between the affluence and the number of medical professionals can lead to a decrease in the quality of the services provided and create problems that have repercussions for the entire hospital, with the requisition of health care workers from other departments and the postponement of surgeries.