Coupling Big Data and Synthetic Spatial Simulation for Guangzhou-Shenzhen-Hong Kong High-speed Railway Alignment

Objectives: The existing roads and railways in the Greater Bay Area are hard to fulfilling the growing travel demand. Current facility location models consider terrain, traffic, population, ecology, etc. to generate the suitable route schemes, They ignore the promoting effect of major infrastructure construction on regional development. For the location of major infrastructure such as high-speed railway, factors such as promoting land development, and driving the economic and social development of the region should also be taken into account. To fill this gap, this study combines big data and spatial synthetic simulation model to develop an intelligent high-speed railway alignment method. Methods: Multi-source geographic big data such as railway network, highways, population, gross regional product, and digital elevation model are used to generate high-quality high-speed railway candidate lines. The spatial synthetic simulation model for land, population, economy and transportation was developed to predict the future development scenario of high-speed railway. Considering multi-stakeholders, including the city, enterprises and individuals, the benefits and costs of the new high-speed railway is calculated and compared. Results: The experimental results in show that the best northern Line connects the future development areas of four cities through Guangzhou Baiyun Airport, Guangzhou Knowledge City, Dongguan Songshan Lake, Shenzhen Qianhai and Hong Kong Northern Metropolitan Area. Under the influence of this high-speed railroad, the new construction land reached 92 km², the additional population was 970,000, and the additional GDP was 849.5 billion yuan, which shows a significant advantage over other alignment strategies, and the line has the characteristics of fully utilizing the existing lines and enhancing the convenience of residents' travel. Upon completion, it will significantly shorten the travelling time in the core urban area and further promote the development of the Greater Bay Area. Conclusions: The results not only provide data and model support for the selection of the second Guangzhou-Shenzhen-Hong Kong high-speed railway line, but also provide useful reference for the location of major infrastructure in urban agglomeration.