Integrating Railway Infrastructure Data: A Spatial–Temporal Database for Track Deterioration Analysis

This study addresses the challenge of consolidating heterogeneous railway infrastructure data into a unified framework to support advanced analysis and data-driven asset management. The primary objective is the development of a spatial–temporal database that systematically integrates diverse data sources, including asset information, operational loading, track geometry measurements, maintenance records, and Ground Penetrating Radar (GPR) data. The methodology focuses on data harmonization, preprocessing, spatial referencing, and temporal alignment to ensure consistency across datasets with differing structures and resolutions. The resulting database enables network-wide analyses of track condition and deterioration behavior. The results indicate a non-linear relationship between traffic load and deterioration, as well as a significant influence of drainage conditions on both deterioration rates and post-maintenance quality. These findings demonstrate the added value of integrated data analysis in revealing interactions between operational and structural factors. The study concludes that a consistent and scalable database architecture is a key prerequisite for modern railway asset management and provides a robust foundation for predictive modeling and optimized maintenance strategies.