Method for refined function zoning prediction of tourist town urban design based on big data and conditional GAN

Abstract

Looking at the urban design of a tourist town, it is necessary to refine further the function zoning given by the urban plan. However, in the traditional urban design process, this step requires the designers to manually research for similar cases studies to analyze the spatial distribution relationships between businesses and geographical elements such as road networks, water bodies, and topography, which is not only time-consuming and laborious but also lacks reliability and accuracy. Therefore, this paper aims to propose a method that uses big data and conditional Generation Adversarial Network(cGAN) to obtain a POI-guided refined function zoning efficiently and accurately based on multiple proven precedents. Taking Nanjing's Tangquan Hot Spring Town as an example, this paper shows the process of acquiring and processing the dataset, building and training the model, and finally applying it to the target site and generating a preliminary urban design massing based on Rhinoceros and Grasshopper.

Keywords: Urban Design, Big Data, Conditional GAN, Function Zoning, Tourist Town Design