A Machine Learning-Based Method for Predicting Urban Land Use

Abstract

Land use is one of the most basic elements of urban management. In urban planning and design, land use is often determined by experience and case studies. However, the development of urbanization has led to a combinatory trend for land use, and the land use of a plot is always impacted by the surrounding environment. In such a complex situation, it is difficult to find hidden relationships among types of land use by humans alone. Within artificial intelligence, machine learning can help find correlations among data. This paper presents a new method for learning the rules relating the known land use data and predicting the land use of a target plot by constructing an artificial neural network. We take Nanjing as a specific case and study the logic of its land use. The results not only demonstrate associations between the surroundings and the target but also show the feasibility of a combinatory land use index in urban planning and design.