Multi-Source Multi-Scale Data Fusion for Linear Transport Infrastructure Safety and Security - Application to the Railway System – FUSAR

The FUSAR project aims to improve the safety and efficiency of railway infrastructures by developing an advanced warning system based on the fusion of multi-scale and multi-source data. This innovative approach will enable proactive risk management, minimising service interruptions and environmental impacts, while reducing maintenance costs. The project combines IoT, LiDAR, GNSS, InSar and satellite imagery to effectively detect faults and risk areas. It also addresses challenges related to geo-referencing, data interoperability and automatic fault recognition. Using hybrid Deep Learning approaches, the project aims to establish a framework for data fusion at the decision-making level. The introduction of alert thresholds will help SNCF Réseau to anticipate faults and contribute to maintaining the availability of facilities.