Changes in land use/cover are among the most prominent impacts that humans have on the environment. Therefore, exploring land use/cover change is of great significance to urban planning and sustainable development. In this study, we preprocessed multiperiod land use and socioeconomic data, combined with spatial zoning, multilayer perception (MLP) artificial neural network, and Markov chain (MC), to construct a cellular automaton model of spatial zoning. Moreover, with the help of ArcGIS 10.2 and TerrSet 18.07 software, we explore the current status of land use and predict future changes. The results showed that drastic changes have occurred among different land use classes in Jinzhou District over the past 13 years owing to the impact of economic development and reclamation projects. Construction land, arable land, and waters have changed by +85.09, −24.42, and −23.62 km², respectively. By comparing the FoM and Kappa coefficients, we concluded that the prediction accuracy of partitioned MLP-MC is better than that of unpartitioned MLP-MC. Therefore, using the spatial zoning approach to identify the conversion rules among land use classes in different zones can more effectively predict future land use changes and provide a reference for urban planning and policy making.

Background: Accessibility is considered as an important indicator for the public transit service level. Transit accessibility is generally evaluated by its distance to transit access points such as bus stops and metro stations, and methods of measuring the access distances to transit points have been relying heavily on geographic data of transit facilities, built environments and pedestrian routes. Data collecting and analyzing are tedious for researchers in conventional approaches. As the application of cloud computing is on the rise, open services provided by Google Cloud Platform may simplify the procedure of accessibility measurement if the outputs of the open computing services could be validated. Aims and Objectives: This paper aims to develop a method of measuring public transit accessibility based on Google Direction API rather than local data analyzing. A mechanism of API (Application Program Interface) probing is introduced. In a case study, the metropolitan area of Beijing was sliced into gridded spaces, with transit access distance of each cell space calculated by Google Direction API. The access distances in the API feedbacks were compared with transit access numbers in each cell area in order to validate the method with their correlation coefficient. Results and Conclusion: It was found that Google Direction API generally gave shorter access distances in cell areas with more public access points. The conclusion is that open cloud services such as Google Direction API may serve as alternative solutions to public transit accessibility measurement. Transit researchers and agencies may take advantage of such open API services to avoid the tediousness of collecting and processing geographic data sets on transit facilities.