Within the broad field of walkability research, a key area of focus has been the relationship between urban form and capacities for walking. Measures of walkable access can be grouped into two key types: permeability measures that quantify the ease of movement through an urban fabric, and catchment measures, quantifying the potential to reach destinations within walking distance. Of numerous street network measures in use, it has been shown that many are poor proxies of permeability and catchment. Instead, two new measures have been proposed: the area-weighted average perimeter (AwaP) and interface catchment (IC), that, combined, better capture the capacities of urban morphologies to enable and attract pedestrian movement. In this paper, we present the QGIS tool AwaP-IC, developed to overcome the difficulty of computing these measures. Unlike GIS tools based on models that abstract streets to axial lines, by employing new algorithms and spatial computation techniques, AwaP-IC analyses actual urban morphologies, based on cadastral maps delineating public and private land. This can empower a new stream of urban morphological studies with the computational power of GIS. As an open-source tool, it can be further developed for use in urban mapping and to streamline the analysis of large datasets.

The introduction and widespread use of foundation models has accelerated the necessity of identifying geographic bias in AI‐generated content. In this respect, we operationalize geographic diversity as a countermeasure. We refine the notion of geographic diversity as the quality of including data from various places and maintaining a balance across these places in both learning and generation processes. Drawing from information theory, ecology, and prior work in AI evaluation, we provide an entropy‐based definition of geographic diversity and propose to measure geographic diversity as effective numbers of places. We apply our measurement by studying generated content from six large language models, including GPT‐3.5, GPT‐4o, Mistral 7B, Mistral Large, Claude 3 Haiku, and Claude 3.5 Sonnet. Our case study reveals that prompt variations, such as modifying concept mentions or scale mentions in a user prompt, can result in more geographic diversity in their generated content. In addition, we observe that less advanced models can generate more geographically diverse content than state‐of‐the‐art ones. Furthermore, certain places dominate the generated content of these models, yet their prominence does not reflect their real‐world counterparts. Our work stresses the importance of quantifying geographic information in AI‐generated content to support GeoAI and the broader AI evaluation in the age of foundation models.

Agent-based modelling (ABM) is a computer-based system to simulate the interactions, relationships and behavior of individual agents in a defined spatial context. Due to its stochastic and heterogenic nature, the method has the potential to represent the complexity of the tourism system with a broad range of possible applications. In the context of visitor flow management for instance, ABM can function as a possible decision support tool for policy makers to better understand and evaluate the dynamics of future scenarios and proposed policy changes towards a more economically, socially and environmentally resilient tourism development altogether. The following paper discusses the potential and implications of agent-based models in tourism research with a complex system approach in regard to ABM’s inherent elements of agents, interactions and environment. It introduces the planned application of ABM in an ongoing project dealing with visitor flows in an urban as well as rural destination context and draws up possible implications for sustainable tourism development.