2007—2023年机器学习在绿色基础设施研究中的发展：一项知识综述

王堉锦

内蒙古科技大学建筑与艺术设计学院，内蒙古包头，014010；

摘要：随着城市化进程加快，绿色基础设施在雨洪调节、热环境改善、污染缓解和生态系统服务提升中的作用日益突出，但其识别、评估与优化涉及多源数据和复杂变量关系，传统方法在处理高维、动态和异质数据时存在局限。本文采用系统回顾与知识图谱分析方法，对2007—2023年间149篇相关文献进行梳理。结果表明，机器学习在绿色基础设施研究中的应用总体呈持续增长趋势，热点主要集中于遥感分类、热环境评估和雨洪管理。支持向量机、人工神经网络、自适应神经模糊推理系统、随机森林和XGBoost等算法在GI识别、预测与优化中表现出不同优势。总体来看，机器学习为绿色基础设施研究提供了新的技术路径，但仍面临时间相关性不足、黑箱性较强和可解释性有限等问题。未来应进一步加强多源数据融合、时空动态建模及高可解释性算法应用。

关键词：绿色基础设施；机器学习；遥感分类；热环境评估；雨洪管理

参考文献

[1]. Brzoska, P., & Spāģe, A. (2020). From City- to Site-Dimension: Assessing the Urban Ecosystem Services of Different Types of Green Infrastructure. Land, 9(5). https://doi.org/10.3390/land9050150   

[2].Dikshit, A., Pradhan, B., & Alamri, A. M. (2021). Pathways and challenges of the application of artificial intelligence to geohazards modelling. Gondwana Research, 100, 290-301. https://doi.org/10.1016/j.gr.2020.08.007  

[3].Fu, G., Jin, Y., Sun, S., Yuan, Z., & Butler, D. (2022). The role of deep learning in urban water management: A critical review. Water Res, 223, 118973. https://doi.org/10.1016/j.watres.2022.118973    

[4].Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996). Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research, 4, 237-285. https://doi.org/https://doi.org/10.48550/arXiv.cs/9605103

[5].Ko, H., & Son, Y. (2018). Perceptions of cultural ecosystem services in urban green spaces: A case study in Gwacheon, Republic of Korea. Ecological Indicators, 91, 299-306. https://doi.org/10.1016/j.ecolind.2018.04.006   

[6].Lin, Y., Zhao, L., Liu, X., Yang, W., Hao, X., & Tian, L. (2021). Design Optimization of a Passive Building with Green Roof through Machine Learning and Group Intelligent Algorithm. Buildings, 11(5). https://doi.org/10.3390/buildings11050192  

[7].Liu, H., Chen, H. L., Hong, R., Liu, H. G., & You, W. J. (2020). Mapping knowledge structure and research trends of emergency evacuation studies. Safety Science, 121, 348-361. https://doi.org/10.1016/j.ssci.2019.09.020