Projects

Title: MUltiscale Flood Forecasting with INnovating Solutions (ANR-21-CE04-0021-05).
Partners: INRAE, IMT, Univ Eiffel, Cerema IMFT, CCR, Météo/SPCME, SCHAPI
The objective of the MUFFINS project is to develop new accurate and computationally efficient flood forecasting approaches, enabling transferring information between modelings (meteo-hydrology-hydraulic-damage) and scales (from local runoff generation over areas lesser than 1km2 to flood propagation on catchments of thousands km2), and taking advantage of innovative data (in situ, remote observation, opportunistic) to reduce forecasts uncertainties.
More precisely, the MUFFINS project is expected to provide significant advances on the following aspects:
• Understanding and specifying the different requirements and expectations of actors having to take decisions at different times: hours before the crisis (i.e.: internal pre-alerts in a rescue service for preparedness actions), during the crisis (i.e.: immediate rescue of people at risk) and hours after (i.e: first loss assessments by insurance companies);
• Design of new methodologies and tools, in adequacy with user’s needs, for next generation of spatially distributed flood warning methods (improved handling of hydro-meteorological inputs in high uncertainty & low predictibility contexts, seamless regionalizable and multi-scale hydrological-hydraulic modeling chains, fast & accurate computations, flood impact mapping, enhanced synergies with multi-source data);
• Integration of information from multi-source data for improving the accuracy of integrated chains and their adequacy with flood impacts mapping;
• Demonstrators of the methods on Mediterranean catchments with multi-scale issues and rich datasets

Urban water network managers are increasingly faced with the analysis of massive heterogeneous data/information (imprecise and uncertain geographical data, digital/analogue maps, etc.). Intelligent analysis of this data is a challenge that needs to be addressed in order to obtain accurate maps of networks, monitor environmental variables and identify areas for intervention.

The multi-disciplinary CROQUIS project is set in this context where researchers in Water Sciences and Artificial Intelligence will join their efforts to propose new methods for the representation, completion, fusion, archiving, repair and interrogation of heterogeneous data describing wastewater networks.

The consortium, composed of two partners in Artificial Intelligence (CRIL: Centre de Recherche en Informatique de Lens, project coordinator, and I3S: Laboratoire d’Informatique, Signaux et Systèmes de Sophia Antipolis) and one partner in Water Sciences (HSM: HydroSciences Montpellier), offers complementary skills that are essential to the achievement of the objectives of this project.

Title: Machine Learning and Risk Evaluation (ANR-20-CE23-0011).
Partners: University Côte d’Azur, University of Montpellier, INRAE, Inria and CNRS.

The overall objective of the project is to bring significant innovations in the fields of statistical learning (and more particularly unsupervised learning, i.e. clustering) and risk assessment, linked by the problem of level sets estimation. To achieve this, the project has set three specific objectives:

• Improve and propose quantization or depth based clustering methods for this new type of data (Machine Learning) ;
• Address the topic of risk evaluation ;
• Link these two axis by a transversal axis “level sets estimation”.

Title: Combining earth observation with a large scale model cascade for assessing flood hazard at high spatial resolution.
Partner: LIST (Luxembourg Institute of Science and Technology)
The CASCADE project aims at developing a Satellite Earth Observation (SEO)-based modelling framework that enables an assessment of flood hazard at large scale and high spatial resolution. The project intends to unlock the potential offered by recent developments in terms of high performance computing, parsimonious and efficient hydrological and hydraulic models, as well as the availability of globally coherent remote sensing data. By using SEO data and other globally and freely available data sets as default data for driving and parameterizing the model, the project aims at developing a modelling solution that is no longer relying entirely on the availability of long records of reliable in situ observations. Such developments are considered a pre-requisite for hydrology-related disaster risk reduction worldwide.
Website

Title: Generating Advances in Modeling Biodiversity And ecosystem Services
Partners: CIRAD, INRAE, LECA, MUSEUM National d’Histoire Naturelle, IMAG, Université Paris-Saclay
GAMBAS gathers a collective comprised of quantitative ecologists and mathematicians with aspirations in ecology . An advisory committee composed of representatives of the French government and civil societies will support these investigators. Together, they have set the goal of expanding JSDMs and to promote their use in community ecology, biogeography, and conservation ecology. Multiple datasets will contribute to fulfill the objectives of GAMBAS, including terrestrial (birds, temperate and tropical forests) and aquatic (freshwater functional diversity) biological communities.
Website

Title: Analysis and Numerical Simulation of Water Ecosystems in Response to anthropogenic environmental changes
Partners: MISTEA, LEESU, iEES Paris, LBE, NIGLAS, Chineese Academy of Sciences
The increase in the occurence of cyanobacterial blooms threaten the ecosystem services provided by lakes and reservoirs worldwide. In this French-Chinese collaborative project, researchers of various fields will work together to develop an integrative platform for lake ecosystems modeling, which will include some tools of data management and knowledge representation, some models and some methods of analysis.
Website

This collaboration is intended to implement and evaluate the relevance of AI tools in physical and numerical modeling. These physical and numerical methods, exploited within the framework of problems whose physical processes are well controlled, are however limited by computation times and the resolution of mesh-to-mesh numerical problems. These classical methods therefore require a multiplication of technical means (such as the processor computing capabilities, or parallelization) when downscaling or parallelization is required. spatial or temporal refinement is required. Conversely, an upscaling process can be undertaken in order to spatially simplify the resolution of physical processes and mathematical tools through a coarser mesh for example.