增强沿海城市台风灾害韧性是支撑海洋经济高质量发展的基础。基于2011—2023年我国55个沿海城市面板数据,采用OLS、Logit、RF与XGBoost等方法,考察数智化对沿海城市台风灾害韧性的影响。研究发现,数智化能显著提升沿海城市台风灾害韧性,该结论经内生性处理与多项稳健性检验后依然成立。包容性绿色增长可强化韧性提升效应,要素市场错配程度更高的城市存在更大提升空间。异质性分析显示,数智化对沿海城市台风灾害韧性趋势增强型、角色属于枢纽型、数智化—韧性耦合成熟型城市的提升效应更为突出,北方沿海城市的提升效应强于南方沿海城市。此外,数智化对韧性网络度中心性的影响不显著,其中可能同时涉及“区域协同强化”与“本地自立增强”两种作用。为此,应着力推进数智化防灾建设,促进其与绿色包容发展、要素配置优化相结合,并持续关注数智化对区域韧性协同治理的潜在价值。
Enhancing coastal urban resilience to typhoon disasters is fundamental to supporting the high-quality development of the marine economy. From 55 Chinese coastal cities from 2011 to 2023, this paper employs OLS, Logit, RF and XGBoost to examine the impact of digitalization on typhoon disaster resilience. The results show that digitalization significantly enhances resilience, a finding that remains robust after endogenous treatment and a series of robustness checks. Inclusive green growth reinforces this resilience-enhancing effect, while cities with higher factor market misallocation exhibit greater room for improvement. Heterogeneity analysis reveals that the effect is more pronounced in cities with strengthening resilience trends, hub-type cities, and cities with mature digitalization- resilience coupling; the effect is also stronger in northern cities than in southern cities. Network analysis reveals that the effect of digitalization on network centrality is not statistically significant, which may point to the coexistence of two mechanisms: "regionally coordinated reinforcement" and "locally self-reliant enhancement". Accordingly, digital disaster prevention should be advanced in stages, integrated with inclusive green development and optimal factor allocation, while its potential value for regional resilience governance deserves sustained attention.
[1] 中国气象局气候变化中心. 中国气候变化蓝皮书(2024)[R].北京:气象出版社,2024
[2] 吴家臣,杜志章. 超大城市灾害韧性的生成机制及其治理转向——基于CAS理论视角的分析[J].城市问题,2025(6):87-94
[3] 张海波,戴新宇,钱德沛,等. 新一代信息技术赋能应急管理现代化的战略分析[J]. 中国科学院院刊,2022(12):1727-1737
[4] 陈晓红,李杨扬,宋丽洁,等. 数字经济理论体系与研究展望[J].管理世界,2022(2):208-224
[5] 吴非,胡慧芷,林慧妍,等. 企业数字化转型与资本市场表现——来自股票流动性的经验证据[J].管理世界,2021(7):130-144
[6] 韩沅刚,李振涛,谷雨,等. 数字技术合作与城市经济韧性——基于专利文本分析的证据[J].城市问题,2025(2):70-81
[7] Sharifi A.Urban resilience assessment: Mapping knowledge structure and trends[J]. Sustainability, 2020(15):5918
[8] 李广东,关洛桐,刘志涛. 国际城市韧性研究:过程视角下的韧性框架和系统综述[J].城市问题,2024(10):4-16
[9] Ribeiro P J G, Gonçalves L A P J. Urban resilience: A conceptual framework[J]. Sustainable Cities and Society, 2019, 50:101625
[10] Holling C S.Resilience and stability of ecological systems[J]. Annual Review of Ecology and Systematics, 1973, 4:1-23
[11] Bertilsson L, Wiklund K, Tebaldi I M, et al.Urban flood resilience: A multi-criteria index to integrate flood resilience into urban planning[J]. Journal of Hydrology, 2019, 573:970-982
[12] 贺娴静,乔观民,潘政允,等. 海岸带城市灾害韧性的时空特征及响应组态路径研究[J].灾害学,2026(1):212-219
[13] Zscheischler J, Martius O, Westra S, et al.A typology of compound weather and climate events[J]. Nature Reviews Earth & Environment, 2020, 1:333-347
[14] Mendelsohn R,Emanuel K,Chonabayashi S, et al.The impact of climate change on global tropical cyclone damage[J]. Nature Climate Change, 2012(3): 205-209
[15] 张卓群,何玉凤,李晓晓. 国家级海洋公园建设对海岸带生态韧性的影响[J/OL]. 海洋通报, (2026-03-03)[2026-05-28]
[16] 韩晶,陈曦. 数字经济赋能绿色发展:内在机制与经验证据[J]. 经济社会体制比较,2022(2):73-84
[17] Wahl T, Jain S, Bender J, et al.Increasing risk of compound flooding from storm surge and rainfall for major US ities[J]. Nature Climate Change, 2015(12): 1093-1097
[18] 张钹,朱军,苏航. 迈向第三代人工智能[J].中国科学:信息科学,2020(9):1281-1302
[19] 中国信息通信研究院. 人工智能算力基础设施赋能研究报告(2025年)[R]. 北京:中国信息通信研究院,2025
[20] 张涛,李均超. 网络基础设施、包容性绿色增长与地区差距——基于双重机器学习的因果推断[J].数量经济技术经济研究,2023(4):113-135
[21] 林伯强,杜克锐. 要素市场扭曲对中国能源效率的影响[J]. 经济研究,2013(9):125-136
[22] Breiman L.Random Forests[J]. Machine Learning, 2001(1):5-32
[23] Probst P, Wright M N, Boulesteix A L.Hyperparameters and tuning strategies for Random Forest[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2019(3):e1301
[24] Chen T, Guestrin C.XGBoost: A Scalable Tree Boosting System[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016:785-794
[25] Bentéjac C, Csörgő A, Martínez-Muñoz G.A comparative analysis of gradient boosting algorithms[J]. Artificial Intelligence Review, 2021, 54:1937-1967
[26] Lundberg S M, Lee S I.A Unified Approach to Interpreting Model Predictions[C]//Advances in Neural Information Processing Systems, 2017, 30:4765-4774
[27] Lundberg S M, Erion G, Chen H, et al.From local explanations to global understanding with explainable AI for trees[J]. Nature Machine Intelligence, 2020(1):56-67
[28] 田鸽,张勋. 数字经济、非农就业与社会分工[J].管理世界,2022(5):72-84
[29] Jolliffe I T, Cadima J.Principal component analysis: A review and recent developments[J]. Philosophical Transactions of the Royal Society A, 2016(2065):20150202
[30] 马述忠,张道涵,胡增玺. 数字知识流动如何促进区域协调发展——兼论经济增长和平衡发展双重目标[J].中国工业经济,2025(2):80-98
[31] Borgatti S P, Everett M G, Johnson J C.Analyzing Social Networks[M]. London: SAGE Publications, 2018
