Our team and mission

Reporting to the Head of the Explore Office in the ESA Φ-lab, you will work in close cooperation with other staff in the Directorate of Earth Observation Programmes and in particular in the Earth System Science Hub.

You will be part of the ESA Φ-lab. Our mission is to accelerate the future of Earth Observation (EO) by embracing disruptive innovation and serve as a catalyst for disruptive and transformative innovation in the sector.

Our vision is to become an EO innovation hub, connecting EO with a growing ecosystem of disruptive and transformative innovation, including AI, machine learning, quantum computing and edge computing. Many of the challenges posed by new digital technologies need to be tackled at scientific, application and capability levels to deliver the maximum value from satellite-derived EO assets for our climate, society, and economy. The Φ-lab will bring together early-career and senior researchers from a variety of disciplines across EO, as well as disruptive and transformative innovation, to contribute to the development of innovative EO solutions.

We offer:

• a stimulating multinational, interdisciplinary and open work environment;
• access to high-performance computing infrastructure and unparalleled EO and technology expertise;
• a unique opportunity to work on innovative solutions to address global challenges;
• freedom and focus to conduct creative research while making an impact in relation to ESA’s strategy;
• a wide network of relationships and collaboration with top academia, industry and research centres;
• the opportunity to contribute to the Φ-lab strategy and activities.

You are encouraged to visit the ESA website: https://www.esa.int/

Field(s) of activity/research for the traineeship

This fellowship is a collaboration between the ESA Φ-lab and the Earth System Science Hub to explore the use of space EO products and advanced AI techniques to advance Earth system science and predictive capabilities for the Earth system and climate research.

In the past number of years, advances in Earth Observation (EO) capabilities have resulted in a broad range of new EO products that are opening up new opportunities to better describe and understand the Earth system. In particular, novel observation products and new geophysical variables observed from space are opening the door to the generation of regional and global multivariate data sets and data cubes, including a wide range of different variables, offering a holistic view of complex processes, such as carbon cycles, hydrological cycles, sea level coastal hazards, ice shelves, ocean-atmosphere interactions and climate change impacts on ecosystems, representing a unique opportunity for the advancement of Earth system science and contributing to the establishment of core components of future Digital Twin Earth replicas of the Earth system.

Multivariate data sets, along with regional or global multivariate data cubes, including advanced EO data products, complemented with in-situ data, and even socioeconomic observations, open the door towards novel data-driven approaches to generate 4D dynamic “reconstructions” and simulations of the Earth system. However, learning complex processes from EO data and capturing the complex interactions and feedback across different components of the Earth system is an ambitious scientific endeavour with many technical and scientific challenges. Advances in artificial intelligence (AI) and machine learning (ML) open up new possibilities to address these challenges and foster breakthroughs in the identification and analysis of complex patterns and relationships in large heterogenous data sets in several application and Earth system domains, currently not possible with standard methods. We can now not only fit and infer complex functions from the data, but can also learn causal relations. In EO, AI/ML is expected to radically improve current capabilities to reconstruct, simulate and predict complex phenomena, learning directly from the data.

This activity is aimed at advancing the use of AI and ML in the EO domain to unlock the potential offered by novel, heterogenous multivariate data sets to better characterise, simulate and predict the behaviours of key components of the Earth system and its interactions with human activities and ecosystems. In particular, these activities will focus on at least one of the following challenges:

1. AI-based reanalysis and multivariate reconstruction in common spatial/time grids;
2. Prediction of Earth system dynamics, especially anomalies and extremes;
3. Characterising poorly known and complex processes with a focus on extremes (identification of drivers of change), teleconnections and cascade events.

.

In particular, you will:

• undertake advanced research activities exploring and expanding the use of disruptive and transformative innovation such as AI, ML, quantum computing and edge computing to develop new frameworks and solutions. Research may cover a wide range of innovative topics, from the development of novel methods, algorithms and ML iterative pipelines to high-level products;
• contribute to the development and curation of open data sets and tools enabling the community to develop its own AI for applications and research;
• support the definition and implementation of rapid prototyping activities, research sprints and open challenges of innovative EO solutions addressing upcoming lab activities and wider strategy;
• engage with the innovation ecosystem to promote the uptake of new techniques and capture the latest developments in EO and disruptive/transformative innovation;
• publish the research project outcomes in high-impact journals;
• drive collaboration within the Φ-lab community and ESA internal teams to promote the uptake of these new techniques and solutions;
• contribute to the Φ-lab strategy, activities, and outreach on disruptive technologies for EO;
• maintain a continuous dialogue with the scientific community, including major international programmes and initiatives in the fields of AI, ML, quantum computing and edge computing;
• support the Φ-lab’s research network of Young Graduate Trainees, National Trainees, Interns, and Visiting Researchers, as applicable.

Technical competencies

Behavioural competencies

Result Orientation
Operational Efficiency
Fostering Cooperation
Relationship Management
Continuous Improvement
Forward Thinking

For more information, please refer to ESA Core Behavioural Competencies guidebook

Education

You should have completed within the past five years or be close to completing a PhD in a relevant field, such as data science, AI, computer science, machine learning, Earth system science or climate studies, with a thesis subject relevant to the description of the tasks outlined above.

Additional requirements

In addition to your CV and cover letter, please prepare a research proposal of no more than five pages. Your proposal should be uploaded to the “Additional documents” field of the “Application information” section.

You should have:

• sound knowledge of themes of interest, such as EO, AI, ML, quantum computing, ICT revolution technologies and edge computing;
• the ability to think outside the box and explore new avenues, with natural curiosity and a passion for new subjects and research areas;
• the ability to work in a multicultural environment as part of a team;
• experience with one or more general purpose programming languages, for example Python, and general purpose deep learning frameworks, such as Tensorflow or PyTorch;
• the ability to share knowledge with other ESA units.

You should also have good interpersonal and communication skills and should be able to work in a multi-cultural environment, both independently and as part of a team.

Your motivation, overall professional perspective and career goals will also be explored during the later stages of the selection process.

The working languages of the Agency are English and French. A good knowledge of one of these is required. Knowledge of another Member State language would be an asset.