Opportunity for Visiting Researchers in AI for SAR Foundation Models

Deadline: August 31, 2026 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

🖊️ Topic: AI for SAR Foundation Models

🎓 Open to: PhD students, postdoctoral researchers, and early-career researchers with expertise in Artificial Intelligence and/or SAR

💻 Background: Experience with deep learning (e.g., PyTorch) and demonstrated expertise in either SAR/PolSAR/InSAR or self-supervised learning and foundation models. Expertise spanning both areas is particularly desirable.

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

📅 Duration and timing: Opportunities for an onsite research visit to ESA Φ-lab are available from Q1 2027, typically for a period of approximately six months. Remote collaboration prior to the onsite visit may be considered on a case-by-case basis.

Introduction and Context

This opportunity is issued in the context of the European Space Agency (ESA) Φ-lab Collaborative Innovation Network (CIN), an initiative designed to foster collaboration among experts in Earth Observation and Transformative Technologies. The CIN aims to attract leading researchers, distinguished advisors, and recognised experts to collaborate with ESA Φ-lab at ESA's Centre for Earth Observation (ESRIN), Frascati, Italy.

ESA Φ-lab's mission is to accelerate the future of Earth Observation through transformational innovation, namely innovations with the potential to create or transform industries through emerging technologies, thereby strengthening the global competitiveness of the European Earth Observation industrial and research sectors.

Pi School, which operates in the field of AI and research innovation and maintains extensive academic connections through its staff and network, supports ESA Φ-lab in this mission by creating, managing, coordinating, and animating the ESA Φ-lab CIN.

Purpose and Scope of Collaboration

This opportunity invites researchers to propose and pursue collaborative research activities contributing to the development, evaluation, and scientific advancement of SAR foundation models.

Visiting researchers will collaborate with ESA scientists, research fellows, and international partners on ongoing research activities aimed at advancing the state of the art in AI for SAR. The proposed research should contribute to next-generation SAR AI methodologies and foundation models capable of generalising across diverse sensors, frequencies, acquisition modes, geographic regions, and downstream Earth Observation applications.

Desired Expertise and Research Interests

Expressions of interest are welcomed from researchers with strong expertise in either:

• Advanced AI methodologies for Earth Observation, including geospatial foundation models, representation learning, self-supervised learning, and deep learning; or
• SAR-related science and applications, including Synthetic Aperture Radar (SAR), Polarimetric SAR (PolSAR), and Interferometric SAR (InSAR).
• Researchers should demonstrate a strong publication record relative to their career stage and an interest in conducting cutting-edge research at the intersection of AI and Earth Observation.
• Experience with SAR missions such as Sentinel-1, TerraSAR-X/TanDEM-X, NISAR, BIOMASS, or similar systems is highly desirable, including experience with low-level products such as SLC data.

Visiting researchers may spend a period of approximately six months at ESA Φ-lab, working closely with ESA scientists, research fellows, and project partners on jointly defined research activities.

Continued scientific collaboration with ESA Φ-lab before and/or after the onsite visit is welcomed where mutually beneficial and aligned with ongoing research activities.

During the onsite visit, participants are expected to engage actively in the jointly agreed research programme and contribute to the scientific objectives of the collaboration, including research activities, model development, benchmarking exercises, and scientific dissemination.

Possible Areas of Contribution

• Contribute to the scientific and technical development of next-generation SAR foundation models.
• Investigate and advance state-of-the-art methodologies for multi-modal representation learning across SAR modalities, including self-supervised learning, foundation models, representation learning, and multimodal learning.
• Conduct research on SAR-specific challenges, including PolSAR, InSAR, coherence analysis, time-series analysis, and the exploitation of low-level SAR products such as SLC data.
• Design and execute rigorous benchmarking and diagnostic activities to assess model generalisation, transferability, robustness, and scientific value.
• Develop and validate AI solutions for high-impact Earth Observation applications, including agriculture, forestry, biodiversity monitoring, climate and cryosphere studies, disaster management, infrastructure monitoring, and maritime applications.
• Explore multimodal approaches integrating SAR with optical, lidar, meteorological, and other geospatial data sources.
• Contribute to the development of trustworthy AI methodologies, including uncertainty estimation, explainability, and reproducible evaluation protocols.
• Collaborate with ESA scientists and project partners to define research directions and translate scientific advances into reusable capabilities for the broader Earth Observation community.
• Contribute to scientific publications, open-source software, datasets, benchmarks, and dissemination activities arising from the collaboration.

The precise balance and scope of activities will be discussed and adapted throughout the collaboration, taking into account project progress, emerging research opportunities, the visitor's expertise and interests, and the broader needs of the project and partner organisations.

Indicative Experience and Qualifications

Researchers are expected to have:

• An ongoing or completed PhD in Computer Science, Artificial Intelligence, or a related discipline. Exceptional Master's students with a strong research background and expertise relevant to the proposed collaboration may also be considered.
• Strong experience with Python and at least one machine learning framework (e.g., PyTorch, JAX).
• Ideally, a strong understanding of self-supervised learning methods and the current state of the art in Earth Observation foundation models and/or substantial experience in machine learning for SAR, together with an interest in Earth Observation, Earth system science, and scientific research.

Type of Engagement

Participation is offered through the Φ-lab Visiting Researcher Scheme, which supports collaborative research activities of mutual interest between ESA Φ-lab and external researchers by leveraging shared expertise, resources, and scientific objectives within an ESA Φ-lab team.

The collaboration is unpaid and is particularly suitable for researchers already affiliated with an academic institution or employed by a private company. Under specific conditions, ESA may provide support for travel and accommodation expenses.

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

Interested in Collaborating?

Researchers interested in establishing a collaboration with ESA Φ-lab are invited to share:

• A detailed CV;
• Supporting documents and/or references;
• A brief research proposal or concept note describing a potential area of collaboration aligned with both ESA Φ-lab's strategic priorities and the topic outlined above, highlighting where the applicant believes they can make a significant scientific contribution.

Expressions of interest will be assessed based on:

• Technical expertise and research experience;
• Alignment with ESA Φ-lab's strategic objectives and research priorities;
• Scientific merit, feasibility, and potential impact of the proposed collaboration;
• Availability and flexibility for the proposed collaboration period;
• Interest in continued scientific collaboration beyond the onsite visit;
• Compatibility with ESA Φ-lab's collaborative and exploratory research environment.

This opportunity offers a unique opportunity to contribute to ESA Φ-lab and, more broadly, to ESA's pioneering initiatives in Earth Observation and Artificial Intelligence. We look forward to engaging with researchers who are interested in advancing transformative research and innovation through collaboration with ESA Φ-lab.

Please, fill this form: