Urban studies require a rich set of information sources and techniques that enable a comprehensive depiction of urban environments. Remote sensing captures physical characteristics of urban landscapes, while social sensing collects data from social media and digital devices to reflect human activities. The combination of remote sensing and social sensing has been employed to investigate urban environments, urban dynamics, and the well-being of city residents. This review explores leading ideas and methodologies of the synergy between remote sensing and social sensing in a broad context of urban studies. The synergy involves leveraging the benefits of remote sensing and social sensing to gain a deeper understanding of urban characteristics than can be acquired through any single sensing approach. Two types of synergy are identified, namely, “transfer-based synergy” and “integration-based synergy.” The former transfers ideas and techniques between remote sensing and social sensing based on their similarity. The latter integrates these sensing ways based on their complementary advantages. The motivations and methods are summarized to show how such synergy is suited for investigating the complex nature of urban systems. Typical applications of the synergy include land use and functional zone mapping, special land use identification, estimation of natural and socioeconomic elements, and emergency response. We also identify data quality issues, refinement of methodologies, and expansion of applications that still pose challenges and are worth future research. This review lays a foundation for synergizing remote sensing and social sensing, offering researchers guidance to reexamine and reconceptualize the city from multiple sensing perspectives.

The spatial concentration of human activity is a crucial indication of socio-economic vitality. Accurately mapping activity volumes is fundamental to support regional sustainable development. Current approaches rely on mobile positioning data, which record information about human daily activity but are inaccessible in most cities due to privacy and data sharing concerns. Alternative methods are needed to provide more generalized predictions on extensive areas while maintaining low cost. This study demonstrates how remote sensing imagery can be used through an end-to-end deep learning framework for reliable estimates of human activity volumes. The neighbour effect, representing the inherent nature of spatial autocorrelation in the volumes, is incorporated to improve the network. The proposed model exhibits strong predictive power and demonstrates great explainability of physical environment on variations of activity volumes. Landscape interpretations based on hierarchical features provide both object-based and region-based insights into the co-evolvement of landscape and human activity. Our findings indicate the possibility of extensively predicting activity volumes, especially in areas with limited access to mobile data, and provide support for the promising framework to better comprehend broad aspects of human society from observable physical environments.

Similar time series search is one of the most important time series mining tasks in our daily life. As recent advances in sensor technologies accumulate abundant multi-dimensional time series data associated with multivariate quantities, it becomes a privilege to adapt similar time series searches for large-scale and multi-dimensional time series data. However, traditional similar time series search methods are mainly designed for one-dimensional time series, while advanced methods applicable for multi-dimensional time series data are largely immature and, more importantly, are not friendly to users from the domain of geography. As an alternative, we propose a novel method to search similar multi-dimensional time series with spatial databases. Compared with traditional methods that often conduct the similarity search based on features of the raw time series data sequence, the proposed method stores multi-dimensional time series as spatial objects in a spatial database, and then searches similar time series based on their spatial features. To demonstrate the validity of the proposed method, we analyzed the correlation between temporal features of the raw time series and spatial features of their corresponding spatial objects theoretically and empirically. Results indicate that the proposed method can not only support similar multi-dimensional time series searches but also markedly improve its efficiency under many specific scenarios. We believe that such a new paradigm will shed further light on the similarity search in large-scale multi-dimensional time series data, and will lower the barrier for users familiar with spatial databases to conduct complex time series mining tasks.

Intra-urban origin-destination (OD) network communities evolve throughout the day, indicating changing groups of closely connected regions. Under this variation, groups of regions with high consistency of community affiliation characterize the temporally stable structure of the evolution process, aiding in comprehending urban dynamics. However, how to quantify this consistency and identify these groups are open questions. In this study, we introduce the consensus OD network to quantify the consistency of community affiliation among regions. Furthermore, the temporally stable community decomposition method is proposed to identify groups of regions with high internal and low external consistency (named "stable groups"), where each group consists of temporally stable cores and attaching peripheries. Wuhan taxi data is used to verify our methods. On the hourly time scale, eleven stable groups containing 82.9% of regions are identified. This high percentage suggests that dynamic communities can be well organized via cores. Moreover, stable groups are spatially closed and more likely to distribute within a single district and separated by water bodies. Cores exhibit higher POI entropy and more healthcare and shopping services than peripheries. Our methods and empirical findings contribute to some practical issues, such as urban area division, polycentric evaluation and construction, and infectious disease control.