Multisource Data-Driven Resilience Assessment and Optimization of Metro Station Public Spaces: A Case Study of Suzhou Metro

With the gradual expansion of the underground public space network, metro public space faces multiple challenges such as extreme weather and sudden surges in passenger flow. Existing research lacks a toughness evaluation model based on multisource data, which makes it difficult to systematically identify weaknesses in toughness in composite spaces. Based on multisource data, this paper constructs an evaluation model containing three dimensions of resilience, adaptability and changeability, and adopts the TOPSIS-entropy weight-AHP method to achieve standardised assessment of metro public space data. The Guangji South Road Station of Suzhou Metro in China is taken as an example to validate the model. Through GIS analysis and the street view semantic segmentation method, the resilience weaknesses of the station in the dimensions of spatial resources, environmental comfort, and management mechanisms are visualised. The study proposes a construction strategy of spatial transformation, data monitoring, and collaborative management to enhance the resilience performance by increasing spatial redundancy, introducing the data-based management mode, and improving the facility service capability. The study shows that the resilience evaluation model driven by multisource data can effectively identify weak points in metro public space resilience.It provides theoretical and practical references for establishing highly resilient metro public space.