With rapid urbanization,megacities worldwide are transitioning to stock optimization and reduction planning to address spatial constraints.Dynamic monitoring and functional optimization of construction space have emer...With rapid urbanization,megacities worldwide are transitioning to stock optimization and reduction planning to address spatial constraints.Dynamic monitoring and functional optimization of construction space have emerged as crucial areas of research for interdisciplinary studies on urban inventory and reduction planning.The advent of artificial intelligence technology and high-resolution remote sensing images enables building footprint extraction and urban function identification at a relatively large scale.However,there have been limited recent attempts to explore the reuse of buildings with altered functions.Here,we introduced an artificial intelligence technology framework for implementing urban inventory and reduction planning,using Beijing as an example.Utilizing the U-Net deep learning model and highfrequency remote sensing images,we analyzed building space dynamics in Beijing between 2018 and 2019.Then,by combining the random forest regression method with data on vacated building spaces,we developed strategies to optimize and simulate the layout for various reuse functions,including recultivation and regreening in the planned non-construction areas,as well as residential,industrial,and public service facilities in planned construction areas.Our results reveal a substantial decrease in building area,primarily affecting environmentally important areas such as agricultural land areas and urban green spaces.These findings align with the reduction requirements outlined in the latest version of the Beijing Urban Master Plan(2016-2035),in accordance with the updated General Regulations and the initiative“Relief,Remediation and Promotion”.Based on the implementation principles of inventory and reduction in the new General Plan,the study explored optimized layouts for future reuse functions within planned construction and non-construction spaces.This innovative approach to urban space optimization and governance simulation offers valuable scientific insights and decision-making support for urban structure adjustments and land use efficiency enhancements in megacities.展开更多
基金supported by the National Natural Science Foundation of China(42301461)Open Research Fund Program of Technical Innovation Center of Mine Geological Environmental Restoration Engineering in Southern Karst Area,Ministry of Natural Resources(NFSS2023004).
文摘With rapid urbanization,megacities worldwide are transitioning to stock optimization and reduction planning to address spatial constraints.Dynamic monitoring and functional optimization of construction space have emerged as crucial areas of research for interdisciplinary studies on urban inventory and reduction planning.The advent of artificial intelligence technology and high-resolution remote sensing images enables building footprint extraction and urban function identification at a relatively large scale.However,there have been limited recent attempts to explore the reuse of buildings with altered functions.Here,we introduced an artificial intelligence technology framework for implementing urban inventory and reduction planning,using Beijing as an example.Utilizing the U-Net deep learning model and highfrequency remote sensing images,we analyzed building space dynamics in Beijing between 2018 and 2019.Then,by combining the random forest regression method with data on vacated building spaces,we developed strategies to optimize and simulate the layout for various reuse functions,including recultivation and regreening in the planned non-construction areas,as well as residential,industrial,and public service facilities in planned construction areas.Our results reveal a substantial decrease in building area,primarily affecting environmentally important areas such as agricultural land areas and urban green spaces.These findings align with the reduction requirements outlined in the latest version of the Beijing Urban Master Plan(2016-2035),in accordance with the updated General Regulations and the initiative“Relief,Remediation and Promotion”.Based on the implementation principles of inventory and reduction in the new General Plan,the study explored optimized layouts for future reuse functions within planned construction and non-construction spaces.This innovative approach to urban space optimization and governance simulation offers valuable scientific insights and decision-making support for urban structure adjustments and land use efficiency enhancements in megacities.
