Geospatial artificial intelligence (GeoAI) is proliferating in urban analytics, where graph neural networks (GNNs) have become one of the most popular methods in recent years. However, along with the success of GNNs, the black box nature of AI models has led to various concerns (e.g. algorithmic bias and model misuse) regarding their adoption in urban analytics, particularly when studying socio-economics where high transparency is a crucial component of social justice. Therefore, the desire for increased model explainability and interpretability has attracted increasing research interest. This article proposes an explainable spatially explicit GeoAI-based analytical method that combines a graph convolutional network (GCN) and a graph-based explainable AI (XAI) method, called GNNExplainer. Here, we showcase the ability of our proposed method in two studies within urban analytics: traffic volume prediction and population estimation in the tasks of a node classification and a graph classification, respectively. For these tasks, we used Street View Imagery (SVI), a trending data source in urban analytics. We extracted semantic information from the images and assigned them as features of urban roads. The GCN first provided reasonable predictions related to these tasks by encoding roads as nodes and their connectivities and networks as graphs. The GNNExplainer then offered insights into how certain predictions are made. Through such a process, practical insights and conclusions can be derived from the urban phenomena studied here. In this paper we also set out a path for developing XAI in future urban studies.

Public participation is crucial in promoting built environment quality. By using Nancuiping park in China as a case study, this research brings attention to the digital twin park compared to the physical replica in a participatory workshop. Using UAV oblique photography, we created a digital twin model of this park and divided it into six layers to better manage and analyze the environment. Bracing the ‘bottom-up’ design philosophy, in the workshop, we analyzed existing issues in the park and simulated built environment changes, taking suggestions and comments from participants into account to support the decision-making of the park’s optimization. Our digital twin model and physical replica were assessed through a questionnaire in which 59 participants used 3 defined indicators: usability, interactivity, and scenario simulation and visualization quality. The results suggest that the physical replica is easier to use in the participatory design. However, the digital twin model can provide better interactivity and efficient scene simulation and visualization quality. The statistical analysis of the relationship between participants’ feedback on the two models and their sociodemographics (age, gender, and education background) shows that age is a barrier to promoting digital twins for older participants. Meanwhile, the digital twin’s highly interactive features and high-resolution visualization capability were attractive to the younger and well-educated participants. Our study indicates future directions to improve the urban digital twin by incorporating human feedback into the urban model, thus establishing a two-way interaction between the digital system, the physical environment, and human perceptions.