Explainable multimodal AI using geospatial data for rapid estimation of displacement and people in need in crises

Context

This doctoral position is offered under the Collaborative Doctoral Partnership (CDP) Programme, a joint initiative of the European Commission’s Joint Research Centre (JRC) and European universities. The programme is designed to train a new generation of researchers at the science-policy interface, strengthening collaboration between academia and EU institutions to support evidence-based policymaking and address pressing societal challenges. More specifically, Université Bretagne Sud has been selected by the JRC among the key international academic partners on the topic Artificial Intelligence for Earth Observation (AI4EO).

The PhD will be jointly hosted by the Disaster Risk Management (DRM) Unit at the JRC (Ispra, Italy) and the OBELIX group within IRISA research institute at Université Bretagne Sud (Vannes, France). This collaboration combines advanced AI and remote sensing techniques to address complex issues in disaster risk reduction.

The JRC’s Disaster Risk Management Unit plays a central role in supporting EU civil protection and humanitarian policies through data-driven risk analytics, including the Risk Data Hub, the INFORM suite of indices, the Copernicus Emergency Management Service, and the Global Disaster Awareness and Coordination System. These systems combine Earth Observation (EO), statistical and physical models, and Artificial Intelligence to inform risk assessment, early warning and crisis response. The JRC is a research centre located in an attractive setting at Lake Maggiore, in commutable distance to Milan (1h by car, 1.5h by public transport), offering a modern and flexible work environment.

The OBELIX group is an internationally recognized team in AI4EO, with strong expertise in machine and deep-learning-driven analysis and processing of complex, multidimensional geospatial data, and privileged access to cutting-edge high-performance computing resources at the local and national level. It belongs to IRISA, one of the largest French research laboratories (more than 850 people) in the field of computer science and information technology, and it is hosted at Université Bretagne Sud (UBS), a multidisciplinary university located in Vannes, a beautiful medieval city of medium size close to the sea (2h30 in train from Paris). Together, JRC and UBS/IRISA provide a unique interdisciplinary setting where technical innovation is directly connected to policy application.

 

Scientific challenges and objectives

The increasing frequency and severity of complex, multi-hazard disasters—intensified by climate change—are causing growing human and economic impacts worldwide. In such situations, EU humanitarian actors need, within 24–72 hours, robust estimates of how many people are exposed, displaced, or in urgent need of assistance, to inform fast funding decisions. Yet, in the immediate aftermath of an event, it remains extremely challenging to obtain reliable estimates of the number of people affected, displaced, or in need of assistance. Such information is essential both for planning rapid humanitarian response and resource allocation, and, in the longer term, for understanding underlying vulnerability and reducing future risk.

 

Remote sensing has emerged as a valuable technology for estimating and monitoring disaster impacts, enabling a more proactive approach to mitigating adverse consequences. Currently, several complementary data sources are available: EO missions like Sentinel-1 and Sentinel-2 provide systematic observations of physical impacts, while displacement-focused sources such as IOM’s DTM, IDMC, and UNHCR statistics offer information on displaced populations. Datasets like GHSL and INFORM composite index establish baseline population exposure and vulnerability. However, these datasets are often heterogeneous, asynchronous with a frequency of update that does not match with the urgent needs for rapid humanitarian response. Using "population exposed to disasters" as a proxy for crisis magnitude fall short in capturing displacement dynamics and underlying vulnerability. Integrating these diverse datasets remains challenging, limiting comprehensive disaster response strategies.

 

Several studies have demonstrated the relevance of remote sensing data to identify high-risk regions and assess the structural integrity of buildings and critical infrastructure before and after disasters strike, to map socio-economic vulnerabilities by cross-referencing physical data with demographic information, or to assess resilience-centred development interventions in local administrative units where socioeconomic survey data are available. Satellite observations from missions such as Sentinel-1 and Sentinel-2 provide pre- and post-event data that support the detection of disaster-related impacts, including physical damage, inundation, and large-scale destruction.

 

However, satellite images alone are not sufficient to fully capture the complexity of disaster impacts, such as cascading effects. These limitations highlight the importance of integrating remote sensing with complementary data sources, such as textual information from news reports, situation updates, and rapid damage assessments. Leveraging rapid developments in Natural Language Processing—especially large language models—offers a promising way to combine these heterogeneous information streams, enabling multimodal approaches that can provide more complete and timely estimates of disaster impacts.

 

This research project aims to position AI at the forefront of disaster risk management: The overarching objective of this PhD is to design, implement and evaluate explainable multimodal AI methods to estimate displacement from one administrative area to another, and people in need, by looking at areas affected by hazardous disasters, in support of EU humanitarian response. Scientific and technical challenges include the desynchronization and heterogeneity of data modalities, the robustness to missing modalities during inference, the high level of performance needed to meet end-user requirements (e.g., 80% accuracy), and the low quantity and quality of labels available to train AI models. Moreover, learning complex and context-dependent impact indicators—such as displacement, humanitarian needs, or damage levels—from available data presents its own set of difficulties.

 

The PhD will address these challenges by:

• Improving conflict-based baseline methods to better approximate displaced populations using combined conflict, EO-derived impact, and vulnerability data;
• Developing AI4EO methods (also experimenting with state-of-the-art multimodal models like CLIP and GEMMA) for non-conflict and multi-hazard crises, integrating EO-derived hazard layers with displacement data from DTM/IDMC, UNHCR, and reports;
• Creating prototype indicators of “effective population at risk/affected” for integration into JRC impact calculators, improving risk assessments.

The work will be grounded in real case studies, in close collaboration with stakeholders from civil protection, ensuring that scientific innovation eventually contributes to concrete improvements in humanitarian decision-making.

 

Working plan

The doctoral project will start in Spring 2026 and be implemented through 2 working periods in JRC, Italy and UBS, France:

1) 18 to 24 months in JRC, Ispra, Italy (2026, 2027);

1) 12 to 18 months in UBS, Vannes, Vannes (2028, extension to 2029 if needed).

 

At the JRC, the candidate will be employed by a Grantholder contract (category 20, indicative gross annual salary, 40.966,56 €, see working conditions and salary simulations under contract staff, and JRC grantholder rules under research fellows) in accordance with Grantholder rules and the applicable Vademecum (GH Rules).

At UBS, the candidate will be employed by a temporary contract aligned with the recommended level of remuneration and protection that is offered by the doctoral contract as defined by national regulations (indicative gross annual salary, 27.600,00 €). The salary may be supplemented by teaching duties (64 hours annually, accounting for an extra 3.200,00 €).

 

The work programme will include the following steps:

1. conceptual understanding and indicator review: study the theory and frameworks underpinning disaster impact assessment in the context of climate change and disaster risk reduction, conduct a comprehensive review of relevant proxies for people in need (e.g., displaced people, houses damaged);
2. dataset compilation: focus on European datasets due to data availability and relevance to EU decision-makers, collect and compile EO data, including satellite imagery (mainly Sentinel-1, Sentinel-2) and nightlight imagery, along with textual (e.g., reports and news from the European Media Monitor) and tabular datasets for model training (e.g. displaced people from IDMC);
3. development of explainable multimodal AI models: create AI models capable of processing multimodal data (EO, textual, tabular) and providing explainable outputs, perform validation of the models against ground truth (e.g., IDMC displacement data).
4. baseline evaluation: establish a baseline performance using existing models and analyse their explainability, develop a data processing and analysis pipeline that integrates AI with EO datasets;

 

Candidate profile

The offer is restricted to candidates having the nationality of a Member State of the EU or a country associated to the EU Research Framework Programme in force or being resident in an EU Member State since at least five years.

We are seeking an enthusiastic researcher willing to conduct a doctoral project in an international context with mobilities between France and Italy. A MSc degree in remote sensing, computer science, geoinformatics, data science, or a related field is required. The ideal candidate will have a solid foundation in computer vision and machine learning, and a strong interest in disaster risk reduction and the science-policy interface. The candidate should be proficient in Python programming and familiar with at least one deep learning framework (preferably PyTorch). Multidisciplinary collaboration skills are highly desirable. Excellent analytical and communication skills in English, as well as the ability to work across disciplines, are essential.

 

Supervision team

The candidate will be enrolled in a PhD programme in computer science at Université Bretagne Sud and MathSTIC - Bretagne Océane doctoral school.

At UBS, the PhD will be co-supervised by Prof. Sébastien Lefèvre and Assoc. Prof. Marc Chaumont. Both are researchers in artificial intelligence for Earth observation within the OBELIX group of IRISA. At JRC, co-supervision will be ensured by Christina Corbane (Deputy Head of Unit) and Michele Ronco (AI Specialist).

In the context of the CDP between JRC and UBS/IRISA, a team of 3 PhD candidates will be hired at the very same period, with the same mobility plan. It is thus expected that the candidate will interact regularly with 2 other PhD students working on related topics.

Besides, the project will be implemented within the experienced AI chair PANORAMIX held by Prof. Sébastien Lefèvre within SequoIA (a 20 M€ centre of excellence in AI research and training in Brittany), offering additional networking opportunities, including with the ESA Φ-lab at which Prof. Lefèvre is Visiting Professor.

 

How to apply?

Interested candidates holding, at least, a BSc degree and a MSc degree, should submit their application (CV + cover letter + academic transcripts + any relevant supplementary material, e.g. github account or master’s thesis) before January 15, 2026 (but the sooner the better) through the AMETHIS platform: https://amethis.doctorat.org.

Applications will be processed along the way, and preselected candidates will be offered interviews with UBS supervisors between January 12 and 30, 2026. Shortlisted candidates will then be invited for a second interview by the JRC CDP committee between February 2 and February 10, 2026. Final notification will be given end of February 2026, for a tentative start in April 2026.

The JRC reserves the right to request additional documents to ensure the compliance with all requirements and specific rules applicable to JRC sites. The selected candidate must also be recognized as medically fit to carry out the work activities foreseen. To this end, the candidate must undergo, in advance and independently, the medical checks specified by the JRC.

Direct link to apply: https://amethis.doctorat.org/amethis-client/prd/consulter/offre/2592