Abstract

Taking full advantage of the wealth of geospatial data available nowadays is a major scientific and technological challenge, with significant societal and economic impacts. The multidisciplinary ATLAS project addresses the challenge of leveraging diverse geospatial data to enhance Geographic Information Systems (GIS). Focused on urban flooding, the project integrates multidisciplinary expertise—such as GIS, AI, machine learning, image analysis, and statistics—to develop innovative solutions for collecting, organizing, and integrating multi-source geospatial data of varying quality.

This project aims to achieve four major scientific objectives, all focused on strengthening GIS, and each represented by a separate work package.

• Data Collection & Alignment. Gather and organize new data to fill gaps in existing datasets. Align GIS data with complex external sources.

• Data Integration & Enrichment. Define a common language and format for seamless integration. Expand GIS capabilities, including 3D data integration.

• Uncertainty & Conflict Management. Handle imperfect data (e.g., amateur videos, scanned maps). Use spatial relationship graphs to integrate data even with imprecise coordinates. Address conflicting data from multiple sources.

• Sustainable Outputs & Real-World Application. Create open-access datasets and prototypes. Demonstrate methods through a case study in Montpellier, collaborating with water management stakeholders.

The project aims to strengthen GIS with practical, scalable solutions for real-world challenges like urban flooding.