基于敏捷方法的自动化城市规划地理计算 An Agile Approach to Automating Geo-Computational Planning Tasks

Abstract

This paper describes the development of a novel geo-computational methodology for automating planning tasks. The knowledge contribution focuses on the ability of the planner to interact with and override the automated procedures. This approach is referred to as 'agile automated modelling'. The framework is evaluated by developing and testing workflows for two real-world case studies: one focusing on mixed-use potentiality analysis, and another focusing on district planning. In the mixed-use potentiality analysis case study, the core decision-making process uses a set of decision parameters that are combined using a weighted decision tree. In the district planning methodology case study, three adjacent districts are generated with a total area of approximately 1300 hectares with automated generation of street networks, land parcels, and 3-dimensional urban models. The methodology aims to help planners to iteratively generate and assess various planning options.