M/F PhD Earth and Environmental Sciences- Machine Learning for water management: Earth Observation and Data-Driven Monitoring

CNRS; France; Sur place; EUR 25 000 - 34 000; Plein temps

Avantages offerts par ce poste

GPU workstation

Travel funding

Conferences covered

Résumé du poste

CNRS, through the Institute Terre Environnement Strasbourg, invites applications for a PhD position within the TRHYCO group. The PhD will be affiliated with the Doctoral School of Earth and Environmental Sciences of the University of Strasbourg, with collaborations across European partners.

A dedicated GPU-equipped workstation will be provided, and travel and conference costs are covered. The project focuses on water resource resilience, Earth observation, and AI, leveraging multi-sensor

Qualifications

• PhD candidate in Earth and Environmental Sciences.
• Strong interest in machine learning applications to hydrology and water resources.

Responsabilités

• Collect and preprocess environmental data from satellite imagery and in situ observations.
• Develop and implement machine learning models to extract indicators for water resources management.
• Collaborate with international project partners and participate in meetings, workshops, and conferences.

Description du poste

Organisation/Company CNRS Department Institut Terre Environnement Strasbourg Research Field Geosciences Biological sciences Researcher Profile First Stage Researcher (R1) Application Deadline 17 Oct 2026 - 23:59 (UTC) Country France Type of Contract Temporary Job Status Full-time Hours Per Week 35 Offer Starting Date 1 Dec 2026 Is the job funded through the EU Research Framework Programme? Horizon Europe Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The research work will be carried out at the Institute of Earth and Environmental Sciences of Strasbourg (ITES) of the University of Strasbourg, within the TRHYCO research group (TRansfers in HYdrosystems COntinentaux).
The PhD will be affiliated with the Doctoral School of Earth and Environmental Sciences of the University of Strasbourg. Close collaborations with the various project partners are also planned throughout the PhD.
A dedicated computer equipped with high-performance GPU cards will be provided to the PhD student to support the development, training, and implementation of machine learning models. Travel and participation costs for project meetings and international scientific conferences will also be covered. The research will be conducted at the Institute of Earth and Environmental Sciences (ITES), University of Strasbourg, within the TRHYCO research group.
This PhD offers a particularly stimulating research environment at the interface of water sciences, Earth observation, and artificial intelligence. The PhD student will have the opportunity to work on current challenges related to the sustainable and resilient management of water resources, using diverse datasets such as satellite imagery and in situ observations.
The PhD is part of the European HORIZON EUROPE INTEGRATOR project, which brings together academic and institutional partners from eleven European countries. This international dimension will enable the PhD student to develop a scientific network, collaborate with different European research teams, and participate in meetings, conferences, workshops, and summer schools.
ITES is located on the main campus of the University of Strasbourg, just 10 minutes from Strasbourg city center. The PhD student will also have access to a nearby university staff restaurant offering subsidized meals.

This PHD is part of the HORIZON EUROPE project INTEGRATOR. The project involves partners from Turkey, Germany, Norway, Netherland, Estonia, Lativia, Italy, Spain, Greece, Belgium and France. The overarching objective of INTEGRATOR is to strengthen Europe's climate-resilient and equitable water management by enabling anticipatory, evidence-based decision-making at river basin scale under changing climatic and socio-economic conditions. INTEGRATOR aims at delivering a Digital Water Intelligence System (DWIS) that integrates site-specific Digital Twins with climate and socio-economic drivers, operational forecasting, and co-designed technical, governance, and financial instruments developed through the Decision Theatre Approach.
This PhD will deliver basin-scale EO (Earth Observation)–derived indicators for several demonstration basins across Europe, based on the integration of high-resolution EO data and advanced text-mining techniques to characterize biophysical and hydrological dynamics relevant to water resilience. The monitoring strategy combines biogeophysical, hydrological, and socio-environmental assessment streams to support early warning, pressure diagnostics, and adaptive water management. Multi-sensor satellite constellations will be used to assess land-surface processes, vegetation dynamics, and hydrological states in riverine and, where relevant, coastal systems. Vegetation condition will be characterized using advanced biogeophysical parameters (e.g. GPP/NPP, Leaf Area Index, above-ground biomass) derived from Sentinel-1/2/3, BIOMASS, and forthcoming LSTM missions, while hydrological variables will be monitored using optical EO for surface water extent, active and passive microwave observations (Sentinel-1, SMOS, HydroGNSS) for soil moisture, and satellite altimetry (Sentinel-3, SWOT) for lake and river water levels. In parallel, socio-environmental signals on water-related extremes and pressures will be extracted using natural language processing and text-mining techniques, drawing on reports, policy documents, media sources, and stakeholder inputs, and contextualized using insights from the IPBES Nexus. Assessment to complement EO-based monitoring with relevant social and biodiversity dimensions. The PhD thesis will rely on core Copernicus services (C3S, CLMS, CEMS), accessed via APIs, ensuring consistency with JRC datasets and alignment with EU Missions and Partnerships (e.g. Water4All, Biodiversa+). By integrating EO-derived outputs with in situ observations, biodiversity indicators, and modelling and decision-support workflows, this thesis will deliver harmonized EO datasets supporting early warning systems, scenario development, and adaptive water management Earth Observation Earth.
The recruited PhD student will be responsible for collecting and processing various sources of environmental data, including satellite imagery and in situ observations collected from rivers. The student will develop and implement machine learning approaches to analyze these data and extract relevant indicators to improve water resources management.

For further information, please contact the scientific coordinator.