Get Started

Data Science in Space Exploration

Scaling AI Marie Merveilleux du Vignaux

Not only does data science impact virtually every aspect of our earthly lives, but it has also managed to make its way into space! In a recent Egg On Air Episode, Igor Girard-Carrabin, SESAME Project Manager at ArianeGroup, and William Lacheny, SESAME Technical Leader at ArianeGroup, walked us through the goals and challenges of the SESAME project and explained how data science is being used to improve the economic and operational performance of European launchers.

→ Watch the Full Episode

arianegroup speakers egg on air

What Is the SESAME Project and What Is ArianeGroup’s Role in the Project?

The Smart European Space Access Through Modern Exploitation of Data Science (SESAME) project is a research and development project that uses data science to improve the economic and operational performance of European launchers, the Ariane and Vega families of rockets. It is a project supported by the European Commission, which is organized in a consortium of eight entities across four different European countries.

The two organizations coordinating this project are ArianeGroup, the manufacturers of the Ariane family of launchers, and CNES, the French National Center for Space Studies.

Um, What Exactly Is a Launcher?

ArianeGroup calls these launchers because the objective of a rocket like Ariane is to put a satellite (or satellites) into orbit. The services provided by these satellites are numerous and, for the most part, indispensable. We call upon different satellite services each day without really realizing it, by watching television services or using the internet for example. Scientific research uses satellites to measure climate change with scientific programs such as Copernicus, but also services that have become commonplace, such as location and geolocation.
a launcher

The 3 Objectives of the Consortium and Their Challenges

  1. Ensuring and implementing a process of collaboration across Europe in the space sector within the four different countries and eight entities. The main challenge here is learning to work with different people of different companies, nationalities, and types of profiles. This heterogeneity of profiles and nationalities is one of the first challenges of the project.
  2. The second objective is to be able to exploit sensitive data. When working on launchers, teams use data that is controlled for export and so being able to exploit them remotely on a cloud is a challenge. Of course, this also brings up the need for a high level of cybersecurity. Since the value that will be co-created in the designed algorithms will be of extreme importance for the independence of European launchers and their competitiveness on the international market, teams must ensure the level of cybersecurity remains very high.

→ Executing Data Privacy-Compliant Data Projects: A Guide for Data Teams

3. The third objective of the project is to use data science tools to make the manufacturing of Ariane launchers and their integration at the Kourou Guiana Space Center more competitive. Europe's vocation to use data as a lever to make the European space industry more competitive is part of a global picture, since for a little more than a decade now, a certain number of private state actors have entered the heavy launchers industry. This includes SpaceX for Americans, but also Mitsubishi Heavy Industries for the Japanese and the Chinese Academy of Launch Technologies, both direct competitors of Ariane and of this project.

The objective of this project is to make access to space more competitive and more accessible for Ariane and Vega launchers using the support of data science. If you are as excited and fascinated as we are and want to go even further after watching this Egg On Air Episode, you can learn more about the project here.

You May Also Like

Bring Everyday AI to Your Organization: Leveraging Gartner® Insights to Push Further

Read More

Mitigating Data Bias by Implementing Responsible AI Practices

Read More

Smart Manufacturing: How We’ll Get There and How We Won’t

Read More

Data Transformation: How to Transform Data More Efficiently

Read More