Call for Visiting Researchers in Generative AI for Earth System Science

Deadline: September 30, 2025 at 23:59 CET

The ESA Φ-lab CIN is now opening applications for visionary researchers and innovators in Transformative Technologies to strengthen ESA Φ-lab’s ongoing and future projects in Earth Observation (EO). Find out more and apply now.

Main Information

🖊️ Position Title: Visiting Researcher – Generative AI for Earth System Science.

🎓 For: PhD students or postdoctoral researchers in Computer Science, Artificial Intelligence, or a related field.

💻 Minimum Requirements: experience with PyTorch, self-supervised learning, generative models.

📍 Location: ESA Φ-lab, ESRIN, Frascati, Italy.

📅 Starting: The position is available to start in January 2026 and will last for 3-6 months.

Introduction and Context

This call is in the context of the European Space Agency (ESA) Φ-lab Collaborative Innovation Network (CIN), an initiative to foster collaborations among Earth Observation and Transformative Technologies experts. The CIN was created with the aim of attracting high-level researchers, distinguished advisors and key leaders in the above-mentioned fields to the ESA Φ-lab at the ESA Centre for Earth Observation (ESRIN), Frascati, Italy.

ESA Φ-lab is the division of ESA with the mission to accelerate the future of EO by means of transformational innovation, i.e., innovations with the potential to create or transform industries via new technologies, thereby strengthening the global competitiveness of the European EO industrial and research sectors.

Pi School, which operates in the field of AI and research innovation and has numerous academic contacts through its staff, is responsible for supporting ESA Φ-lab in this mission by creating, managing, coordinating, animating the ESA Φ-lab CIN.

Purpose and Scope of Work

This specific call aims to engage with young researchers (PhD candidates, postdoctoral researchers, or equivalent) in Computer Science, Artificial Intelligence, or a related field that are eager to work on AI for Earth System Science. This collaboration offers a unique opportunity to shape next-generation AI capabilities in space and EO, with the potential to deliver high societal impact. The position is available to start in January 2026 (on site) and will last for 3-6 months.

The project aims to train generative models of various dynamical systems in Earth system science, such as for hydrology or oceanology. The goal is to take steps towards the establishment of core components of future purely data-driven Digital Twin Earth replicas of the Earth system. One important challenge is to develop methods for heterogenous and possibly sparse data, integrating a variety of sensors or measurements, data shapes and types. Another core challenge is adequately modelling the temporal dimension of dynamical systems that evolve through time. The obtained models should be general-purpose, serving various downstream purposes including but not limited to densification (in space/time), reanalysis, reconstruction (e.g. filling gaps or predicting missing sensors), and forecasting. We want the methodology to be domain agnostic, so it could be applied across various Earth system science settings. Ideally, we would like to avoid assimilation and reanalysis, and develop purely data-driven alternatives for numerical models. Concretely, we expect to train graph neural networks or transformers with masked autoencoding or diffusion/flow matching.

Who are we looking for?

Through our selective process, we are looking for a Visiting Researcher, i.e. a highly motivated researcher in Computer Science, Artificial Intelligence, or a related field to support ongoing projects that apply AI to Earth system science. Candidates should have strong programming skills and at least one peer-reviewed publication in a top-tier AI or machine learning venue. They should have at least a strong interest in (or preferred: experience with) EO data and/or Earth system science. However, the call is open to candidates with expertise in Artificial Intelligence, even if their primary focus has not been on EO or Earth system science.

The researcher would join onsite at the ESA Φ-lab for a period of 3 to 6 months to collaborate with ESA Φ-lab staff and research fellows. In addition, the visitor will have the opportunity to collaborate closely with scientists at the Earth System Science Hub, ESA’s facility for advanced Earth system and climate science studies (also located at ESRIN). We will prefer candidates that are interested in continuing the collaboration after the visiting period ends, for example in the context of their PhD.

Key Responsibilities:

• Assist in the conceptualization of the methodology, considering the requirements outlined by the Earth system science use cases.
• Gather and preprocess relevant data from EO or other sources.
• Implement and run models and training on HPC infrastructure.
• Design, implement, run and interpret evaluations with special attention to relevance to Earth system science research communities.
• Contribute to joint publications with leading academic and industrial partners.

Requirements:

• Ongoing or completed PhD in Computer Science, AI, or related discipline.
• Strong experience with Python and machine learning frameworks (e.g., PyTorch, Huggingface, Weights & Biases).
• Ideally: experience with masked autoencoding (MAE), self-supervised learning, diffusion/flow matching, generative modelling.
• Interest in Earth Observation, Earth system science and scientific research.

Opportunities:

• Collaborate with top-tier organizations and leading researchers in AI, EO and Earth system science.
• Contribute to high-impact publications and innovative projects.
• Work in a dynamic, interdisciplinary research environment.

Type of Engagement

As a Visiting Researcher, you will be engaged through the Φ-lab Visiting Researcher Scheme: this is a collaboration performed at ESA Φ-lab with the goal of jointly advancing a specific research proposal of shared interest by leveraging shared expertise, resources and time within an ESA Φ-lab team. The collaboration is unpaid and ideal for researchers already affiliated with an academic institution or employed by a private company. Under specific conditions, ESA may provide coverage for travel and accommodation.

If selected, ESA will send you an invitation letter (see template here).

How to apply?

Interested candidates are invited to submit their application, including a detailed CV and any supporting documents or references in the form below. They are asked to include a brief research proposal or concept note outlining a potential area of collaboration aligned with both ESA Φ-lab's strategic focus and the topic summarized above, where they believe they could make a significant impact.

Selection Criteria:

• Technical expertise and experience
• Alignment with ESA Φ-lab’s strategic objectives and mission goals
• Availability and flexibility for short-term engagements
• Interest in continuing collaboration after the stay at Φ-lab ends
• Compatibility with ESA Φ-lab’s collaborative and exploratory working culture

This call represents a unique opportunity to contribute to ESA Φ-lab and, more broadly, to ESA’s pioneering projects, influencing the future of space technology. We look forward to welcoming esteemed researchers who are eager to collaborate on transformative space initiatives.

Please, fill this form: