Large Language Models (LLMs) demonstrate various capabilities previously considered unique to humans. However, current evidence is insufficient to determine whether LLMs have developed spatial cognition, a fundamental aspect of human cognition underpinning logical-mathematical reasoning and various other skills. Previous studies on this topic have primarily concentrated on small-scale perceptions, leaving the spatial cognition within the context of GIScience largely unexamined. We introduce a benchmark that evaluates spatial cognition abilities across seven categories to systematically assess how well LLMs process and generate three types of spatial knowledge: landmark, route, and survey knowledge. Furthermore, we propose a tool-augmented approach named Hybrid Mind, which integrates LLMs with deterministic GIS algorithms to enhance their performance in spatial cognitive tasks. The core idea involves the implementation of a mental map builder that generates a quantitative map based on segmented qualitative constraints, overcoming LLMs’ fallacies in synthesizing spatial information. Our experimental results revealed that although LLMs exhibited potential for spatial cognition, their performance was poor across most spatial cognitive tasks, particularly in constructing route and survey knowledge. The leading model, GPT-4-turbo, correctly answered fewer than one-fourth of the questions. In contrast, the Hybrid Mind approach significantly improved performance, correctly solving 70.48% of the questions.

In this paper, we present a data-driven framework to support exploratory spatial, temporal, and statistical analysis of intra-urban human mobility. We leveraged a new mobility data source, the dockless bike-sharing service Mobike, to quantify short-trip transportation patterns in Shanghai, China, the world’s largest bike-share city. A data-driven framework was established to integrate multiple data sources, including transportation network data (roads, bikes, and public transit), road characteristics, and urban land use, to achieve a detailed, accurate analysis of cycling patterns at both the individual and group levels. The results provide a comprehensive view of mobility patterns in the use of shared-ride bicycles, including: (1) the temporal and spatiotemporal distribution of shared-bike usage and how this varies according to different land use; (2) the statistical distribution of Mobike trips, which are primarily short-distance; and (3) the travel behavior and road factors that influence Mobike users’ route choice. The findings offer valuable insights for city planners regarding infrastructure development, for shared-ride bike companies to offer better bike rebalancing strategies to meet user demand, and for the promotion of this new green transportation mode to alleviate traffic congestion and enhance public health.