Applications of artificial intelligence in urban planning and governance for carbon peak and carbon neutrality

Abstract

<p>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. <br></p>

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。