PhD in Geophysics and Artificial Intelligence / PhD: Towards general-purpose representation learning for environmental seismic signals using Distributed Acoustic Sensing (M/F)

DATA TERRA

STRASBOURG • Bas-Rhin

  • FTC PhD student / Offer for thesis
  • 36 month
  • Doctorate

This offer is available in English version

This offer is open to people with a document recognizing their status as a disabled worker.

Offer at a glance

The Unit

DATA TERRA

Contract Type

FTC PhD student / Offer for thesis

Working hHours

Full Time

Workplace

67000 STRASBOURG

Contract Duration

36 month

Date of Hire

01/09/2026

Remuneration

2300 € gross monthly

Apply Application Deadline : 02 July 2026 23:59

Job Description

Thesis Subject

Recent advances in Fiber-Optics Distributed Acoustic Sensing (FO-DAS) are transforming seismological observations by enabling dense, continuous measurements of ground deformation along fiber-optic cables over tens of kilometers. These systems generate unprecedented volumes of data, capturing a wide variety of tectonic, but also environmental seismic sources, such as landslides, volcanic activity, oceanic processes, or anthropogenic signals. However, the vast majority of these data remain largely unexplored because traditional seismological workflows rely on supervised detection and predefined event classes. At the same time, recent developments in self-supervised and generative artificial intelligence have demonstrated the potential of foundation models capable of learning general representations of complex signals from large unlabelled datasets. These approaches could enable a paradigm shift: moving from targeted analyses of known signals toward systematic and exhaustive exploration of continuous seismic observations.
This PhD aims to establish the first foundation representation model for distributed environmental sensing, leveraging large-scale fiber-optic DAS observations to learn transferable latent representations of environmental dynamics across heterogeneous geophysical contexts (land, marine). The project will combine self-supervised learning, generative AI and scalable AI infrastructures to enable AI-native exploration, retrieval (detection, characterization) and monitoring of continuous Earth system observations. The developed tools will be integrated into operational EOSC infrastructures (EOSC node Data Terra).
This PhD project is part of the GenAI4Earth Horizon Europe, which aims to develop and implement generative AI tools for Earth sciences and deploy them as consolidated services within the nodes of the European Open Science Cloud (EOSC).

Your Work Environment

The successful candidate will join the Data Terra research and services unit, operating at the interface between scientific communities, research infrastructures, and European programs. The position is geographically located at the Earth and Environmental Sciences Observatory (EOST) within the Institute of Earth and Environment (ITES).
The PhD project will draw on extensive FO-DAS datasets acquired across a wide range of geophysical environments, including submarine, volcanic, mountainous, and urban settings, to support the development of large-scale self-supervised and generative learning approaches for environmental observation.
The research will be carried out within an international collaboration involving the Helmholtz Centre for Geosciences (GFZ), the Spanish National Research Council (CSIC), and IFREMER. It will contribute to the development of AI-native services for large-scale exploration, indexing, and semantic search of DAS observations within the ecosystem of the European Open Science Cloud.

Candidate Profile
We are seeking a highly motivated candidate with a strong background in data science, artificial intelligence, signal processing, geophysics, or applied mathematics. The successful applicant must hold a Master's degree (or equivalent) in one of these fields and demonstrate solid programming and data analysis skills. Experience with deep learning architectures (such as transformers, autoencoders, contrastive learning, or generative models) will be considered a significant advantage. Familiarity with geophysical or seismological data would be appreciated but is not essential.

Constraints and risks

No identified risk.

Compensation and benefits

Compensation

2300 € gross monthly

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

Offer reference UAR2013-JEAMAL-005
CN Section(s) / Research Area Earth and telluric planets: structure, history, models

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions

Create your alert

Don't miss any opportunity to find the job that's right for you. Register for free and receive new vacancies directly in your mailbox.

Create your alert

PhD in Geophysics and Artificial Intelligence / PhD: Towards general-purpose representation learning for environmental seismic signals using Distributed Acoustic Sensing (M/F)

FTC PhD student / Offer for thesis • 36 month • Doctorate • STRASBOURG

You might also be interested in these offers!

    All Offers