The COVID-19 viral disease surfaced at the end of 2019 and quickly spread across the globe. To rapidly respond to this pandemic and offer data support for various communities (e.g., decision-makers in health departments and governments, researchers in academia, public citizens), the National Science Foundation (NSF) spatiotemporal innovation center constructed a spatiotemporal platform with various task forces including international researchers and implementation strategies. Compared to similar platforms that only offer viral and health data, this platform views virus-related environmental data collection (EDC) an important component for the geospatial analysis of the pandemic. The EDC contains environmental factors either proven or with potential to influence the spread of COVID-19 and virulence or influence the impact of the pandemic on human health (e.g., temperature, humidity, precipitation, air quality index and pollutants, nighttime light (NTL)). In this platform/framework, environmental data are processed and organized across multiple spatiotemporal scales for a variety of applications (e.g., global mapping of daily temperature, humidity, precipitation, correlation of the pandemic to the mean values of climate and weather factors by city). This paper introduces the raw input data, construction and metadata of reprocessed data, and data storage, as well as the sharing and quality control methodologies of the COVID-19 related environmental data collection.

The death of George Floyd has brought a new wave of 2020 Black Lives Matter (BLM) protests into U.S. cities. Protests happened in a few cities accompanied by reports of violence over the first few days. The protests appear to be related to rising crime. This study uses newly collected crime data in 50 U.S. cities/counties to explore the spatiotemporal crime changes under BLM protests and to estimate the driving factors of burglary induced by the BLM protest. Four spatial and statistic models were used, including the Average Nearest Neighbor (ANN), Hotspot Analysis, Least Absolute Shrinkage, and Selection Operator (LASSO), and Binary Logistic Regression. The results show that (1) crime, especially burglary, has risen sharply in a few cities/counties, yet heterogeneity exists across cities/counties; (2) the volume and spatial distribution of certain crime types changed under BLM protest, the activity of burglary clustered in certain regions during protests period; (3) education, race, demographic, and crime rate in 2019 are related with burglary changes during BLM protests. The findings from this study can provide valuable information for ensuring the capabilities of the police and governmental agencies to deal with the evolving crisis.

Urban vitality serves as a crucial metric for evaluating sustainable urban development and the well-being of residents. Existing studies have predominantly focused on analyzing the direct effects of urban vitality intensity (VI) and its influencing factors, while paying less attention to the urban vitality diversity (VD) and its indirect impact mechanisms. Supported by multisource remote sensing data, this study establishes a five-dimensional urban vitality evaluation system and employs the Partial Least Squares Structural Equation Model (PLS-SEM) to quantify direct and indirect interrelationships between these multidimensional factors and VI/VD. The findings are as follows: (1) Spatial divergence between VI and VD: VI exhibited stronger clustering (I = 1.12), predominantly aggregating in central urban areas, whereas VD demonstrated moderate autocorrelation (I = 0.45) concentrated in mixed-use central or suburban zones. (2) Drivers of vitality intensity: VI are strongly associated with commercial density (β = 0.344) and transportation accessibility (β = 0.253), but negatively correlated with natural environment quality (r = −0.166). (3) Mechanisms of vitality diversity: VD is closely linked to public service (β = 0.228). This research provides valuable insights for city development and decision-making, particularly in strengthening urban vitality and optimizing urban functional layouts.

With the rapid development of location-based social networks (LBSNs), because human behaviors exhibit specific distribution patterns, personalized geo-social recommendation has played a significant role for LBSNs. In addition to user preference and social influence, geographical influence has also been widely researched in location recommendation. Kernel density estimation (KDE) is a key method in modeling geographical influence. However, most current studies based on KDE do not consider the problems of influence range and outliers on users’ check-in behaviors. In this paper, we propose a method to exploit geographical and synthetic social influences (GeSSo) on location recommendation. GeSSo uses a kernel estimation approach with a quartic kernel function to model geographical influences, and two kinds of weighted distance are adopted to calculate bandwidth. Furthermore, we consider the social closeness and connections between friends, and a synthetic friend-based recommendation method is introduced to model social influences. Finally, we adopt a sum framework which combines user’s preferences on a location with geographical and social influences. Extensive experiments are conducted on three real-life datasets. The results show that our method achieves superior performance compared to other advanced geo-social recommendation techniques.

Spatial clustering is dependent on spatial scales. With the widespread use of web maps, a fast clustering method for multi-scale spatial elements has become a new requirement. Therefore, to cluster and display elements rapidly at different spatial scales, we propose a method called Multi-Scale Massive Points Fast Clustering based on Hierarchical Density Spanning Tree. This study refers to the basic principle of Clustering by Fast Search and Find of Density Peaks aggregation algorithm and introduces the concept of a hierarchical density-based spanning tree, combining the spatial scale with the tree links of elements to propose the corresponding pruning strategy, and finally realizes the fast multi-scale clustering of elements. The first experiment proved the time efficiency of the method in obtaining clustering results by the distance-scale adjustment of parameters. Accurate clustering results were also achieved. The second experiment demonstrated the feasibility of the method at the aggregation point element and showed its visual effect. This provides a further explanation for the application of tree-link structures.

PM_2.5, a primary component of haze, is an inhalable form of particulate matter that is hazardous to both the environment and human health. Accurate PM_2.5 concentration forecasting is of great significance for governments in formulating haze prevention and control measures. Previous studies have insufficiently explored the non-Euclidean relationships of monitoring stations and the cross-sample features within PM_2.5 concentration sequences. To fully exploit the spatiotemporal characteristics of PM_2.5 concentrations from both spatial and temporal perspectives, this study proposes a dual-graph spatiotemporal convolutional network with reasoning alignment (DGST-RA). Specifically, through considering non-Euclidean relationships representations for each station, a dual-graph convolutional network is constructed to model spatial dependencies between stations from both static and dynamic dimensions. Subsequently, we reframe temporal feature extraction as a sequence reasoning process. To improve the consistency of the learned temporal representations, the intra-reasoning alignment and inter-reasoning alignment modules are introduced for temporal modeling. Finally, the features extracted by the spatial and temporal modeling modules are fused to obtain the predicted PM_2.5 concentration values. Extensive experiments on both short-term and long-term forecasting demonstrate that, compared to other baseline methods, DGST-RA achieves the best forecasting performance for both short-term and long-term PM_2.5 concentration forecasting. On average, compared to the best baseline model, our DGST-RA model improves RMSE, MAE, and SMAPE by 8.04%, 8.10%, and 11.12%, respectively, for 1‑hour prediction, and CRMSE by 41.44% for 24‑hour prediction. These results confirm that the DGST-RA is an effective model for multi-horizon PM_2.5 concentration forecasting.