The occurrence of large-magnitude disasters has significantly aroused public attention regarding diversified site selection of emergency facilities. In particular, emergency airport site selection (EASS) is highly complicated, and relevant research is rarely conducted. Emergency airport site selection is a scenario with a wide spatiotemporal range, massive data, and complex environmental information, while traditional facility site selection methods may not be applicable to a large-scale time-varying airport environment. In this work, an emergency airport site selection application is presented based on the GeoSOT-3D global subdivision grid model, which has demonstrated good suitability of the discrete global grid system as a spatial data structure for site selection. This paper proposes an objective function that adds a penalty factor to solve the constraints of coverage and the environment in airport construction. Through multiple iterations of the simulated annealing algorithm, the optimal airport construction location can be selected from multiple preselected points. With experimental verifications, this research may effectively and reasonably solve the emergency airport site selection issue under different circumstances.

The study of patterns of crowd flows represents an emerging and expanding research field. The most straightforward and efficient approach to investigate the patterns of crowd flows is to concentrate on traffic flow. However, assessments of simple point-to-point movement frequently lack universal validity, and little research has been conducted on the regularity of nighttime movement. Due to the suspension of public transportation at night, taxi orders are critical in capturing the features of nighttime crowd flows in a tourism city. Using Haikou as an example, this paper proposes a mixed Geogrid Spatio-temporal model (MG-STM) for the tourism city in order to address the challenges. Firstly, by collecting the pick-up/drop-off/in-out flow of crowds, this research uses DCNMF dimensionality reduction to extract semi-supervised spatio-temporal variation features and the K-Means clustering method to determine the cluster types of nighttime crowd flows’ changes in each geogrid. Secondly, by constructing a mixed-evaluation model based on LJ1-01 nighttime light data, crowd flows’ clusters, and land use data in geogrid-based regions, the pattern of nighttime crowd flows in urban land use areas is successfully determined. The results suggest that MG-STM can estimate changes in the number of collective flows in various regions of Haikou effectively and appropriately. Moreover, population density of land use areas shows a high positive correlation with the lag of crowd flows. Each 5% increase in population density results in a 30-min delay in the peak of crowd flows. The MG-STM will be extremely beneficial in developing and implementing systems for criminal tracking and pandemic prevention.

This paper proposes a dynamic airspace grid map based on a 3D subdivision framework to address the lack of standardized modeling framework in current spatial management, difficulties in finely managing small scale areas, and low efficiency issues. The dynamic airspace grid map adopts the GeoSOT-3D subdivision framework, which can seamlessly encode and manage the three-dimensional spatial domain at multiple levels without stacking. Grid map also models static and dynamic airspace, including obstacles, dynamic airspace attributes, aircraft, and can achieve intelligent visualization of time- variance airspace. Finally, the dynamic airspace grid map can organize and store static and dynamic spatial data based on a 3D subdivision framework to ensure the orderliness and security of the airspace domain.

With the development of society, spatial artificial intelligence (spatial AI) research is gradually able to play a greater role. However, spatial AI has problems such as data alignment, poor interpretability, and cross domain learning. Therefore, this paper proposes an innovative GeoSOT-3D grid modeling framework for spatial AI research, which enhances the application capabilities of spatial AI. Grid modeling will be able to run through the upstream and downstream of spatial AI research, providing encoding calculations and spatial neighborhood embedding matrices for spatial data. This paper also uses task examples to demonstrate how to effectively organize and index spatial data using GeoSOT-3D grids and conduct spatial AI research. The use of GeoSOT-3D grids for spatial AI analysis has enormous potential and broad application prospects, which will help promote the further development and application of spatial AI.