潘浩之 施睿 杨天人

Pan Haozhi, Shi Rui, Yang Tianren

关键词：城市规划；城市治理；碳达峰；碳中和；碳排放；人工智能

Keywords：Urban Planning; Urban Governance; Carbon Peak; Carbon Neutrality; Carbon Emission; Artificial Intelligence

摘要：

城市是我国温室气体排放的主要来源，也是各项节能减排政策实施的行动中心，因此亟须在城市层面加快制定与实施“碳达峰、碳中和”行动方案。目前，城市碳排放研究的难点主要有三个方面：空间非线性、城市异质性和数据可得性。针对这三方面难点，本文提出使用人工智能模型方法探析城市空间形态演化与碳排放关系的研究框架，以机器学习、土地利用与空间形态演化模拟、系统集成与“自下而上”碳排放计量等方法支撑国土空间规划。通过芝加哥与斯德哥尔摩气候行动方案支撑研究案例，本文展示了整合城市扩张异质性影响因素分析、土地利用与空间形态演化预测、分门类精细空间碳排放计量的空间人工智能模型，并对未来研究方向提出了建议。

Abstract：

Cities are the main sources of greenhouse gas emissions in China, and are also the center of climate actions to implement various energy-saving and emission-reduction policies. It is urgent to formulate and implement carbon peak and carbon neutrality action plans at the city level. At present, there are three main difficulties in urban carbon emissions research: spatial nonlinearity, urban heterogeneity, and data availability. To address these three difficulties, this paper proposes a research framework for using artificial intelligence methods to analyze the relationship between urban spatial morphology evolution and carbon emissions, including machine learning, land use and spatial morphology evolution simulation, system coupling and bottom-up carbon emission calculation to support urban spatial planning. Through the cases of Chicago and Stockholm’s practices of spatial artificial intelligence in supporting city climate action plans, this paper demonstrates a spatial artificial intelligence model that integrates urban heterogeneity analysis, land use and spatial morphological evolution simulation, and carbon emission calculation at fine spatial granularity. Finally, suggestions for future research directions are proposed.

潘浩之，上海交通大学国际与公共事务学院，副教授，硕士生导师；中国城市治理研究院，研究员。panhaozhi@sjtu.edu.cn

施睿，上海交通大学国际与公共事务学院，硕士研究生。raythree@sjtu.edu.cn

杨天人（通信作者），香港大学建筑学院，助理教授；香港大学深圳研究院，副研究员。tianren@hku.hk

• [1] 张雅欣, 罗荟霖, 王灿. 碳中和行动的国际趋势分析[J/OL]. 气候变化研究进展, 2020[2020-12-25]. https://nxgp.cnki.net/kcms/detail?v=3uoqIhG8C46NmWw7YpEsKHTPvOGrUOOqX1coEOzL8AHOd38SC5vEliY2DLCJm0cXHzmOmRgV9_wHibp0XJLA36g5kr2yBJG-&uniplatform=NZKPT.

  [2] 郭芳, 王灿, 张诗卉. 中国城市碳达峰趋势的聚类分析[J]. 中国环境管理, 2021, 73(1): 40-48. DOI: 10.16868/j.cnki.1674-6252.2021.01.040.

  [3] STAD S. Strategy for a fossil-fuel free Stockholm by 2040[Z]. 2016.

  [4] BARCELONA T C C O. Barcelona’s Climate Action Plan 2018-2030[Z]. 2018.

  [5] 王灿, 张雅欣. 碳中和愿景的实现路径与政策体系[J]. 中国环境管理, 2020, 12(6): 58-64.

  [6] PAN H, PAGE J, ZHANG L, et al. Understanding interactions between urban development policies and GHG emissions: a case study in Stockholm Region[J]. Ambio, 2020, 49(7): 1313-1327.

  [7] 何宛余, 李春, 聂广洋, 等. 深度学习在城市感知的应用可能——基于卷积神经网络的图像判别分析[J]. 国际城市规划, 2019, 34(1): 8-17. DOI: 10.22217/upi.2018.514.

  [8] BATTY M. Artificial intelligence and smart cities[J]. Environment and planning b: urban analytics and city science, 2018, 45(1): 3-6.

  [9] 杨天人, 金鹰, 方舟. 多源数据背景下的城市规划与设计决策——城市系统模型与人工智能技术应用[J]. 国际城市规划, 2021, 36(2): 1-6. DOI: 10.19830/j.upi.2021.034.

  [10] BASSE R M, CHARIF O, BODIS K. Spatial and temporal dimensions of land use change in cross border region of Luxembourg. Development of a hybrid approach integrating GIS, cellular automata and decision learning tree models[J]. Applied geography, 2016, 67: 94-108.

  [11] 孔宇, 甄峰, 李兆中, 等. 智能技术辅助的市（县）国土空间规划编制研究[J]. 自然资源学报, 2019, 34(10): 2186-2199.

  [12] 陈逸敏, 黎夏. 机器学习在城市空间演化模拟中的应用与新趋势[J]. 武汉大学学报( 信息科学版), 2020, 45(12): 1884-1889. DOI: 10.13203/j.whugis20200423.

  [13] 吴志强. 人工智能辅助城市规划[J]. 时代建筑, 2018(1): 6-11. DOI: 10.13717/j.cnki.ta.2018.01.003.

  [14] SHAFIZADEH-MOGHADAM H, ASGHARI A, TAYYEBI A, et al. Coupling machine learning, tree-based and statistical models with cellular automata to simulate urban growth[J]. Computers, environment and urban systems, 2017, 64: 297-308.

  [15] 刘荣增, 陈浩然. 基于ANN-CA 的杭州城市空间拓展与增长边界研究[J]. 长江流域资源与环境, 2021, 30(6): 1298-1307.

  [16] WU M, WEI Y, LAM P T, et al. Is urban development ecologically sustainable? ecological footprint analysis and prediction based on a modified artificial neural network model: a case study of Tianjin in China[J]. Journal of cleaner production, 2019, 237: 117795.

  [17] 邱烨珊, 车生泉, 谢长坤, 等. 基于深度学习的上海城市街景与景观美学公众认知研究[J]. 中国园林, 2021, 37(6): 77-81. DOI: 10.19775/j.cla.2021.06.0077.

  [18] XIANG X, LI Q, KHAN S, et al. Urban water resource management for sustainable environment planning using artificial intelligence techniques[J]. Environmental impact assessment review, 2021, 86: 106515.

  [19] 李建豹, 黄贤金, 孙树臣, 等. 长三角地区城市土地与能源消费CO2排放的时空耦合分析[J]. 地理研究, 2019, 38(9): 2188-2201.

  [20] LEE S, LEE B. The influence of urban form on GHG emissions in the US household sector[J]. Energy policy, 2014, 68: 534-549.

  [21] 柯新利, 唐兰萍. 城市扩张与耕地保护耦合对陆地生态系统碳储量的影响——以湖北省为例[J]. 生态学报, 2019, 39(2): 672-683.

  [22] LAI L, HUANG X, YANG H, et al. Carbon emissions from land-use change and management in China between 1990 and 2010[J]. Science advances, 2016, 2(11): e1601063.

  [23] MILOJEVIC-DUPONT, N, CREUTZIG F. Machine learning for geographically differentiated climate change mitigation in urban areas[J]. Sustainable cities and society, 2021, 64: 102526.

  [24] MARDANI A, LIAO H, NILASHI M, et al. A multi-stage method to predict carbon dioxide emissions using dimensionality reduction, clustering, and machine learning techniques[J]. Journal of cleaner production, 2020, 275:

  122942.

  [25] 禹湘, 陈楠, 李曼琪. 中国低碳试点城市的碳排放特征与碳减排路径研究[J]. 中国人口·资源与环境, 2020, 30(7): 1-9.

  [26] 陈占明, 吴施美, 马文博, 等. 中国地级以上城市二氧化碳排放的影响因素分析：基于扩展的STIRPAT 模型[J]. 中国人口·资源与环境, 2018, 28(10): 45-54.

  [27] 黄蕊, 王铮, 丁冠群, 等. 基于STIRPAT 模型的江苏省能源消费碳排放影响因素分析及趋势预测[J]. 地理研究, 2016, 35(4): 781-789.

  [28] WANG Y, ZHANG X, KUBOTA J, et al. A semi-parametric panel data analysis on the urbanization-carbon emissions nexus for OECD countries[J]. Renewable and sustainable energy reviews, 2015, 48: 704-709.

  [29] ROBINSON C, DILKINA B, HUBBS J, et al. Machine learning approaches for estimating commercial building energy consumption[J]. Applied energy, 2017, 208: 889-904.

  [30] ZHANG X, YAN F, LIU H, et al. Towards low carbon cities: a machine learning method for predicting urban blocks carbon emissions (UBCE) based on built environment factors (BEF) in Changxing City, China[J]. Sustainable cities and society, 2021, 69: 102875.

  [31] 马静, 柴彦威, 刘志林. 基于居民出行行为的北京市交通碳排放影响机理[J]. 地理学报, 2011, 66(8): 1023-1032.

  [32] AMIRI S S, MOTTAHEDI S, LEE E R, et al. Peeking inside the black-box: explainable machine learning applied to household transportation energy consumption[J]. Computers, environment and urban systems, 2021, 88: 101647.

  [33] CHEN P, WU Y, ZHONG H, et al. Exploring household emission patterns and driving factors in Japan using machine learning methods[J]. Applied energy, 2022, 307: 118251.

  [34] 王深, 吕连宏, 张保留, 等. 基于多目标模型的中国低成本碳达峰、碳中和路径[J]. 环境科学研究, 2021, 34(9): 2044-2055. DOI: 10.13198/j.issn.1001-6929.2021.06.18.

  [35] 庄贵阳. 我国实现“双碳”目标面临的挑战及对策[J]. 人民论坛, 2021(18): 50-53.

  [36] 李晓易, 谭晓雨, 吴睿, 等. 交通运输领域碳达峰、碳中和路径研究[J]. 中国工程科学, 2021, 23(6): 15-21.

  [37] 徐政, 左晟吉, 丁守海. 碳达峰、碳中和赋能高质量发展：内在逻辑与实现路径[J]. 经济学家, 2021(11): 62-71. DOI: 10.16158/j.cnki.51-1312/f.2021.11.008.

  [38] 张友国. 碳达峰、碳中和工作面临的形势与开局思路[J]. 行政管理改革, 2021(3): 77-85. DOI: 10.14150/j.cnki.1674-7453.2021.03.005.

  
  

• 收起