Simulating and Predicting the Impacts of Light Rail Transit Systems on Urban Land Use by Using Cellular Automata: A Case Study of Dongguan, China

• Published in: Sustainability Vol. 10; no. 4; p. 1293
• Main Authors: Lin, Jinyao, Chen, Tongli, Han, Qiazi
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 23.04.2018
• Subjects: Case studies; Computer simulation; Housing developments; Impact prediction; Industrial development; Land cover; Land use; Land use management; Light rail transportation; Neural networks; Residential development; Rural development; Rural land use; Sustainability; Sustainable development; Technical services; Transportation; Transportation planning; Trends; Urban areas; Urban development; Urban rail; Urban transportation
• ISSN: 2071-1050; 2071-1050
• DOI: 10.3390/su10041293

The emergence of Light Rail Transit systems (LRTs) could exert considerable impacts on sustainable urban development. It is crucial to predict the potential land use changes since LRTs are being increasingly built throughout the world. While various land use and land cover change (LUCC) models have been developed during the past two decades, the basic assumption for LUCC prediction is the continuation of present trends in land use development. It is therefore unreasonable to predict potential urban land use changes associated with LRTs simply based on earlier trends because the impacts of LRT investment may vary greatly over time. To tackle this challenge, our study aims to share the experiences from previous lines with newly planned lines. Dongguan, whose government decided to build LRTs around 2008, was selected as the study area. First, we assessed the impacts of this city’s first LRT (Line R2) on three urban land use types (i.e., industrial development, commercial and residential development, and rural development) at different periods. The results indicate that Line R2 exerted a negative impact on industrial development and rural development, but a positive impact on commercial and residential development during the planning stage of this line. Second, such spatial impacts (the consequent land use changes) during this stage were simulated by using artificial neural network cellular automata. More importantly, we further predicted the potential impacts of Line R1, which is assumed to be a newly planned line, based on the above calibrated model and a traditional method respectively. The comparisons between them demonstrate the effectiveness of our method, which can easily take advantage of the experiences from other LRTs. The proposed method is expected to provide technical support for sustainable urban and transportation planning.