A survey of urban visual analytics: Advances and future directions

Abstract

Developing effective visual analytics systems demands care in characterization of domain problems and integration of visualization techniques and computational models. Urban visual analytics has already achieved remarkable success in tackling urban problems and providing fundamental services for smart cities. To promote further academic research and assist the development of industrial urban analytics systems, we comprehensively review urban visual analytics studies from four perspectives. In particular, we identify 8 urban domains and 22 types of popular visualization, analyze 7 types of computational method, and categorize existing systems into 4 types based on their integration of visualization techniques and computational models. We conclude with potential research directions and opportunities.

SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization

“…Visualization systems for geospatial data are an active field of research due to their significance in helping researchers understand and analyze the pattern, trend, uncertainty and correlation of data [7]. Numerous systems are proposed for various applications, such as climatology [9], aerodynamics [20], social media analysis [30], and urban computing [6,54], as comprehensively reviewed in surveys by Chen et al [7] and Deng et al [10] However, bias in the understanding of users' needs for spatial and temporal selection in geospatial systems is widespread and challenging to address [64,78] The concept user-driven approaches in geospatial systems encompasses quite a broad scope. It refers to the idea that we allow users to define their specified constraints or priorities to perform selections, rather than making presumptions about their preferences.…”

ClinicLens: Visual Analytics for Exploring and Optimizing the Testing Capacity of Clinics given Uncertainty

“…For example, we might look to incorporate more metadata into our datasets where spatiotemporal features allocate beside multidimensional features. This is a need that has been listed in a systematic survey as a valuable future direction of research to prevent the spread of disease [6]. In these situations, despite the introduction of adequate visual analytics methods [18], [26], [34] and AI4VIS [25], [27], [32] with the goal of providing interactions and artificial intelligence advantages to deal with data correlations and other complexities, dynamic and multi-aspect visual analyses of COVID-19 remain insufficient.…”