Conducting a scientifically rigorous resilience assessment of urban infrastructure is crucial for maintaining the stability of essential urban functions. By analyzing the underlying meaning of urban infrastructure resilience, an evaluation index system was developed, encompassing five key dimensions: transportation, communication, water supply and drainage, sanitation, and energy. Leveraging index data from 2018 to 2022, training and testing datasets were generated using random sampling techniques. The classification model used for assessment was refined through feature selection and parameter optimization processes, and the enhanced model was subsequently applied to evaluate the resilience across the entire study region. The findings indicate the following: (1) The performance of the optimized model has improved across all five metrics, including the F1 score, with all values exceeding 0.94; (2) Upon assessing the resilience of each subsystem, the water supply and drainage resilience exhibited relatively stable trends within a narrow fluctuation range. Communication and energy resilience both demonstrated steady upward trajectories, whereas transportation and sanitation resilience followed a pattern of "decline – recovery – stabilization"; (3) Over the study period, the resilience of urban infrastructure in Hebei Province varied both temporally and spatially. The spatial distribution of the results revealed a pattern characterized by "higher values in central regions and lower values in northern and southern areas," accompanied by localized clustering effects. The overall regional resilience experienced fluctuations but showed improvement, particularly in northwest cities. Areas with fluctuating changes exhibited relatively larger discrepancies in resilience assessment outcomes. These methodologies and findings hold significant implications for the development of resilient cities and the strategic planning of urban infrastructure.

Wang Yongxin, Dong Jiubo, Li Haijun. Research on the Resilience Assessment of Urban Infrastructure in Hebei Province Based on Random Forest. Academic Journal of Environment & Earth Science (2025), Vol. 7, Issue 3: 55-67. https://doi.org/10.25236/AJEE.2025.070308.

[1] Han, Han, et al. "Spatiotemporal analysis of the coordination of economic development, resource utilization, and environmental quality in the Beijing-Tianjin-Hebei urban agglomeration." Ecological Indicators 127 (2021): 107724.

[2] Wang, Hefeng, et al. "Interaction between urbanization and eco-environment in Hebei Province, China." Sustainability 14.15 (2022): 9214.

[3] She Shuo, Duan Fang. Evaluation of Infrastructure Resilience Degree in the Yangtze River Delta Urban Agglomeration: Based on the TOPSIS Entropy Weight Method [J]. China Real Estate, 2020, (27): 31-35. DOI: 10.13562/j.china.real.estate.2020.27.006.

[4] Yan Weidong, Ding Chunlei, Wang Xiaolei. Research on the Evaluation of Urban Infrastructure Resilience Based on Entropy Weight-TOPSIS Model: A Case Study of Shenyang City [J]. Journal of Shenyang Jianzhu University (Social Science Edition), 2024, 26(01): 71-78.

[5] Sun Haiyan. Research on Evaluation and Enhancement Strategies of Urban Infrastructure Resilience [D]. Xi'an University of Architecture and Technology, 2022. DOI: 10.27393/d. cnki. gxazu. 2022. 000801.

[6] Linstone, Harold A., and Murray Turoff, eds. The delphi method. Vol. 1975. Reading, MA: Addison-Wesley, 1975.

[7] Orencio, Pedcris M., and Masahiko Fujii. "A localized disaster-resilience index to assess coastal communities based on an analytic hierarchy process (AHP)." International Journal of Disaster Risk Reduction 3 (2013): 62-75.

[8] Xiao, Wu, et al. "Ecological resilience assessment of an arid coal mining area using index of entropy and linear weighted analysis: A case study of Shendong Coalfield, China." Ecological Indicators 109 (2020): 105843.

[9] Fu, Xingfeng, et al. "A coupled PSR-based framework for holistic modeling and flood resilience assessment: A case study of the 2022 flood events in five southern provinces of China." Journal of Hydrology 636 (2024): 131255.

[10] Meng Xiaojing, Liu Chao, Cao Yingxue, et al. Research on the Spatio-Temporal Evolution of Urban Agglomeration Flood Disaster Resilience Based on Random Forest Optimization Algorithm [J]. Journal of Disaster Prevention and Mitigation Engineering, 2024, 44(04): 784-791. DOI: 10.13409/j.cnki.jdpme.20240131001.

[11] Zhao, Ruidong, et al. "Evaluating urban ecosystem resilience using the DPSIR framework and the ENA model: A case study of 35 cities in China." Sustainable Cities and Society 72 (2021): 102997.

[12] Derras, Boumédiène, and Nisrine Makhoul. "An overview of the infrastructure seismic resilience assessment using artificial intelligence and machine-learning algorithms." Proceedings of the ICONHIC (2022).

[13] Chen, Junfei, et al. "A machine learning ensemble approach based on random forest and radial basis function neural network for risk evaluation of regional flood disaster: a case study of the Yangtze River Delta, China." International journal of environmental research and public health 17.1 (2020): 49.

[14] Bo Jingshan, Wang Yuting, Bo Tao, et al. Research Progress on Resilient Cities and Suggestions for Resilient Urban and Rural Construction [J]. World Earthquake Engineering, 2022, 38(03): 90-100. DOI: 10.19994/j.cnki.WEE.2022.0060.

[15] Wang Ting, Xu Chuan. A Brief Discussion on Infrastructure Planning in Urban Planning [J]. Sichuan Architecture, 2010, 30(03): 15-16.

[16] Liu, Wei, and Zhaoyang Song. "Review of studies on the resilience of urban critical infrastructure networks." Reliability Engineering & System Safety 193 (2020): 106617.

[17] Belgiu, Mariana, and Lucian Drăguţ. "Random forest in remote sensing: A review of applications and future directions." ISPRS journal of photogrammetry and remote sensing 114 (2016): 24-31.

[18] Darst, Burcu F., Kristen C. Malecki, and Corinne D. Engelman. "Using recursive feature elimination in random forest to account for correlated variables in high dimensional data." BMC genetics 19 (2018): 1-6.

[19] Schratz, Patrick, et al. "Hyperparameter tuning and performance assessment of statistical and machine-learning algorithms using spatial data." Ecological Modelling 406 (2019): 109-120.

[20] Wang Guangpeng, Liu Lianyou, Hu Ziying. Research on Flood Disaster Risk Assessment at Grid Scale in the Beijing-Tianjin-Hebei Metropolitan Area [J]. Journal of Catastrophology, 2020, 35(03): 186-193.

[21] Xie Zhuojuan, Lü Yuejun, Fang Yi, et al. Research on Seismic Activity in the Beijing-Tianjin-Hebei Region [J]. Progress in Geophysics, 2019, 34(03): 961-968.

[22] Chen, Min, Chen, Jia, Guo, Xiangyu, Li, Yuxin, Zhu, Xiaowen, Zhang, Jianyun, et al. Measuring urban infrastructure resilience via pressure-state-response framework in four Chinese municipalities[J]. Applied Sciences, 2022, 12(6): 2819.

[23] Yin Hongling, Cui Dongxu, Wang Linshen, et al. Evaluation Objects, Perspectives and Index System of Regional Infrastructure [J]. Regional Research and Development, 2015, 34(06): 38-42.

[24] Xu W , Cong J , Proverbs D .Evaluation of infrastructure resilience[J].International Journal of Building Pathology and Adaptation, 2021.DOI:10.1108/ijbpa-09-2020-0075.

[25] Zhang Lequn, Chen Xuemin, Fu Xiaoyong, et al. Research on the Index System of Urban Infrastructure Construction in Lanzhou [J]. Urban and Rural Construction, 2012, (04): 54-55.

[26] Yang Hui. Research on the Integration of Infrastructure in 13 Cities of Beijing-Tianjin-Hebei Region Based on Coupling Coordination Degree Model [J]. Economics and Management, 2020, 34(02): 15-24.

[27] Cui Dongwen. Application of Support Vector Machine in the Identification of Lake and Reservoir Nutritional Status [J]. Water Resources Protection, 2013, 29(04): 26-30.

[28] Cui Dongwen, Jin Bo. Comprehensive Evaluation of Water Ecological Civilization Based on Random Forest Regression Algorithm [J]. Advances in Science and Technology of Water Resources, 2014, 34(05): 56-60 + 79.