CHIST-ERA ATLAS

GeoAI-based AugmenTation of muLti-source urbAn GIS

Taking full advantage of the wealth of geospatial data available today represents a major scientific and technological challenge, with significant societal and economic impacts. The multidisciplinary ATLAS project (GeoAI-based AugmenTation of muLti-source urbAn GIS) was proposed under the CHIST-ERA Call 2023, within the topic “Multidimensional Geographic Information Systems (MultiGIS)”.. ATLAS aims to enhance the expressiveness and quality of Geographic Information Systems (GIS) by integrating data from multiple external sources of diverse nature and quality, with a case study focused on urban mapping and flooding.

The project contributes to the broader effort of developing and applying tools and methods based on artificial intelligence, machine learning, statistics, and computer vision in the water sciences. To achieve these goals, ATLAS mobilizes researchers with expertise in GIS, data fusion and integration, 2D hydraulic modeling, flood problem modeling, spatially distributed rainfall-runoff models, and mapping of urban networks. It also leverages variational autoencoders for imprecise data, uncertainty theories, conflict resolution, data completion, 3D object modeling and analysis, computer vision, and geometric alignment and fusion of images.

Consortium

The consortium comprises CRIL (CNRS, Université d’Artois, project coordinator), HSM (Hydrosciences Montpellier, Université de Montpellier, CNRS, IRD), IUSTI (Institut Universitaire des Systèmes Thermiques Industriels, CNRS, Aix-Marseille Université, Polytech Marseille), the University of Szeged (Hungary), and the University of Oviedo (Spain).