The spatiotemporal evolution pattern of urban resilience in the Yangtze River Delta urban agglomeration based on TOPSIS-PSO-ELM

Urban resilience, a methodology that can quantify the healthy operation of cities, has theoretical and practical significance for clarifying urban development rules and improving sustainable urban development. Using 49 cities in the Yangtze River Delta urban agglomeration as a research object, we employed the TOPSIS method, particle swarm optimization (PSO), and extreme learning machine (ELM) to measure urban resilience from 2010 to 2020. We used the mainstream exploratory spatial data analysis, geostatistical trend line analysis and geographical detectors to analyze urban resilience's temporal and spatial evolution characteristics and its influencing factors. The results in the Yangtze River Delta urban agglomeration were as follows: (1) The resil-ience level of cities rose, and their rank changed significantly. (2) There was an apparent spatial imbalance in the development of urban resilience. The "peak" centers of resilience were mainly distributed in first-tier developed cities such as Shanghai, Nanjing, and Hangzhou, while the "valley" centers were mainly distributed in the northwestern marginal cities such as Huainan, Huaibei, and Bozhou. (3) The spatial agglomeration of the urban resilience index was significant, with prominent H-H agglomeration in eastern coastal areas and apparent L-L clustering in the northern Huaibei plain and northern Jiangsu plain. (4) The leading driving factors that influ-enced the spatial differentiation of urban resilience were the per capita deposit balance of financial institutions; the local financial revenue; the foreign capital actually used; the average wage of fully employed staff and workers; the number of hospital beds; the public library collection per 100 persons; the electricity consumption of the whole society; the total gas supply; the number of mobile phone users at the end of each year; and the number of internet broadband users.