Understanding dynamic human mobility changes and spatial interaction patterns at different geographic scales is crucial for assessing the impacts of non-pharmaceutical interventions (such as stay-at-home orders) during the COVID-19 pandemic. In this data descriptor, we introduce a regularly-updated multiscale dynamic human mobility flow dataset across the United States, with data starting from March 1st, 2020. By analysing millions of anonymous mobile phone users’ visits to various places provided by SafeGraph, the daily and weekly dynamic origin-to-destination (O-D) population flows are computed, aggregated, and inferred at three geographic scales: census tract, county, and state. There is high correlation between our mobility flow dataset and openly available data sources, which shows the reliability of the produced data. Such a high spatiotemporal resolution human mobility flow dataset at different geographic scales over time may help monitor epidemic spreading dynamics, inform public health policy, and deepen our understanding of human behaviour changes under the unprecedented public health crisis. This up-to-date O-D flow open data can support many other social sensing and transportation applications.

Fine-grained prediction of urban population is of great practical significance in many domains that require temporally and spatially detailed population information. However, fine-grained population modeling has been challenging because the urban population is highly dynamic and its mobility pattern is complex in space and time. In this study, we propose a method to predict the population at a large spatiotemporal scale in a city. This method models the temporal dependency of population by estimating the future inflow population with the current inflow pattern and models the spatial correlation of population using an artificial neural network. With a large dataset of mobile phone locations, the model’s prediction error is low and only increases gradually as the temporal prediction granularity increases, and this model is adaptive to sudden changes in population caused by special events.

Integrating raw Global Position System (GPS) trajectories with a road network is often referred to as a map-matching problem. However, low-frequency trajectories (e.g., one GPS point for every 1-2 min) have raised many challenges to existing map-matching methods. In this paper, we propose a novel and global spatial-temporal map-matching method called spatial and temporal conditional random field (ST-CRF), which is based on insights relating to: 1) the spatial positioning accuracy of GPS points with the topological information of the underlying road network; 2) the spatial-temporal accessibility of a floating car; 3) the spatial distribution of the middle point between two consecutive GPS points; and 4) the consistency of the driving direction of a GPS trajectory. We construct a conditional random field model and identify the best matching path sequence from all candidate points. A series of experiments conducted for real environments using mass floating car data collected in Beijing and Shanghai shows that the ST-CRF method not only has better performance and robustness than other popular methods (e.g., point-line, ST-matching, and interactive voting-based map-matching methods) in low-frequency map matching but also solves the “label-bias” problem, which has long existed in the map matching of classical hidden Markov-based methods.

Dynamic human activity intensity information is of great importance in many location-based applications. However, two limitations remain in the prediction of human activity intensity. First, it is hard to learn the spatial interaction patterns across scales for predicting human activities. Second, social interaction can help model the activity intensity variation but is rarely considered in the existing literature. To mitigate these limitations, we proposed a novel dynamic activity intensity prediction method with deep learning on graphs using the interactions in both physical and social spaces. In this method, the physical interactions and social interactions between spatial units were integrated into a fused graph convolutional network to model multi-type spatial interaction patterns. The future activity intensity variation was predicted by combining the spatial interaction pattern and the temporal pattern of activity intensity series. The method was verified with a country-scale anonymized mobile phone dataset. The results demonstrated that our proposed deep learning method with combining graph convolutional networks and recurrent neural networks outperformed other baseline approaches. This method enables dynamic human activity intensity prediction from a more spatially and socially integrated perspective, which helps improve the performance of modeling human dynamics.

Trajectory prediction plays an important role in supporting many advanced applications such as location-based services and advanced intelligent traffic managements. Most existing trajectory prediction methods employed fixed spatial division and focused on human closeness movement patterns. However, these methods could lead to a sharp boundary limitation and ignore the periodic characteristics of human mobility. This paper proposes a novel trajectory prediction method based on long short-term memory network (LSTM) called the trajectory predictor with fuzzy-long short-term memory network (TrjPre-FLSTM). First, we introduce a new fuzzy trajectory concept and extend the LSTM to a fuzzy-LSTM to overcome the sharp boundary limitation. Second, we explicitly incorporate the periodic movement patterns of moving objects in the trajectory prediction. Using a real-world mobile phone dataset, we evaluate the performance of TrjPre-FLSTM with two latest competitors. The case study results indicate that the proposed method outperforms the comparative methods in terms of the prediction accuracy.