Keynote talk via Livestream: Where no model has gone before: Applications of LLMs and NLP in the Space Field with Dr Audrey Berquand Event

Abstract

Designing complex systems such as spacecraft requires a multidisciplinary approach, careful planning, and attention to detail. Naturally, it also involves extensive documentation of the systems and interfaces, in the shape of requirements, models, and text documents.

In this keynote, Dr. Audrey Berquand will present how the recent advances in the fields of Natural Language Processing and Large Language Models can accelerate the design of space missions, and contribute to a more agile and competitive European space sector. From investigating missions’ heritage to the analysis of the space ecosystem dynamics and the development of virtual assistants for astronauts, this presentation will cover a wide range of current and future applications.

About the speaker

Dr. Audrey Berquand is a Research Fellow in Advanced Software Technologies at the European Space Agency (ESA) in The Netherlands.

Audrey is an outspoken advocate for the use of AI in space. She strives to solve concrete issues met by space experts, facilitating their access to knowledge, and enhancing their design processes. She was awarded her PhD in 2021 from the University of Strathclyde (Glasgow, Scotland) for her thesis on “Text Mining and Natural Language Processing for the Early Stages of Space Mission Design”. Audrey has a background in space systems engineering, she holds an MSc in Aerospace Engineering from the Royal Institute of Technology KTH (Sweden), and a diplôme d'ingénieur from the EPF Graduate School of Engineering (France). She is also an alumna of the International Space University (ISU) Space Studies Program.

Before diving into the world of AI, she spent 3 years at ESA being involved in the early design phases of future Earth Observation missions. Finally, Audrey has been an active member of the Space Generation Advisory Council (SGAC) and Women in Aerospace Europe (WIA-E) networks for several years.

This event is supported by The Alan Turing Institute. The Turing is not involved in the agenda or content planning.