Accurate and efficient air quality prediction is crucial for public health protection and environmental sustainability. While numerous grid-based and graph-based prediction models have been developed, they encounter challenges in large-scale scenarios: (1) Grid-based models, though computationally efficient, have limited prediction accuracy in large-scale sparse scenarios; (2) Graph-based models, despite higher prediction accuracy, suffer from significant computational inefficiencies when dealing with a large number of sensors, i.e. graph nodes. To address these issues, we propose a Lightweight Ensemble Predictor (LiEnPred) for efficient air quality prediction in large-scale sparse scenarios. First, we present a data structure transformation algorithm that converts sparse monitoring sensors from graph structures to compact grid structures, preserving the connections between graph nodes. Next, we present a lightweight parameter-shared spatio-temporal dilation convolution network that efficiently captures spatio-temporal dependencies in air quality data without significantly increasing computation time or parameter scale. In our experiments, we collected air quality data from over 2000 sensors across China over the past three years and evaluated LiEnPred’s prediction performance in large-scale scenarios using PM2.5 and NO2 concentration data. The experimental results demonstrate that the proposed LiEnPred model matches or exceeds the predictive accuracy of eight baselines with faster time efficiency and fewer model parameters.

Modeling population-level human mobility has been attracting multidisciplinary research attention due to its profound implications for sustainable urban development. However, previous studies have often neglected the explicit consideration of spatial heterogeneity of travel demand, which limits their abilities to accurately estimate mobility flows. In this study, we introduce a prior-guided, data-driven human mobility model that integrates the position of origins and destinations, spatial travel patterns, and physical models as priors to capture spatial heterogeneity of human mobility. Specifically, we introduce the concept of ‘relative attractiveness’ to emulate the underlying driving force for the formation of spatial heterogeneity in human mobility. To learn the embeddings of ‘relative attractiveness’, we propose a suite of methods that integrate prior knowledge and graph neural networks, mainly including a relative position encoding module to encode the position of different origin-destination (OD) pairs relative to the entire geographical space and a message-passing method inspired by the classical physical models to simulate the mechanisms of mobility flow generation. Finally, a gradient boosting regression tree is trained to generate the mobility flow based on the learned embeddings. Extensive experiments on two real-world datasets have showed our model outperforms state-of-the-art data-driven mobility models in terms of accuracy and generalization.

Explainable spatio-temporal prediction gains attraction in the development of geospatial artificial intelligence. The neural ordinal differential equation (NODE) emerges as a new solution for explainable spatio-temporal prediction. However, challenges still need to be solved in most existing NODE-based prediction models, such as difficulty modeling spatial data and mining long-term temporal dependencies in data. In this study, we propose a spatio-temporal attentional NODE (STA-ODE) to address the two challenges above. First, we define a spatio-temporal ordinary differential equation to predict a value at each time iteratively by a novel spatio-temporal derivative network. Second, we develop an attention mechanism to fuse multiple prediction values for capturing long-term temporal dependencies in data. To train the STA-ODE model, we design a loss function that aligns the prediction results in spatial dimension with prediction results in temporal dimension to calibrate the parameters of the model. The proposed model was validated with three real-world spatio-temporal datasets (traffic flow dataset, PM2.5 monitoring dataset, and temperature monitoring dataset). Experimental results showed that STA-ODE outperformed seven existing baselines regarding prediction accuracy. In addition, we used visualization to demonstrate the sound interpretability and prediction accuracy of the STA-ODE model.

Accurate traffic flow prediction on the urban road network is an indispensable function of Intelligent Transportation Systems (ITS), which is of great significance for urban traffic planning. However, the current traffic flow prediction methods still face many challenges, such as missing values and dynamic spatial relationships in traffic flow. In this study, a dynamic temporal graph neural network considering missing values (D-TGNM) is proposed for traffic flow prediction. First, inspired by the Bidirectional Encoder Representations from Transformers (BERT), we extend the classic BERT model, called Traffic BERT, to learn the dynamic spatial associations on the road structure. Second, we propose a temporal graph neural network considering missing values (TGNM) to mine traffic flow patterns in missing data scenarios for traffic flow prediction. Finally, the proposed D-TGNM model can be obtained by integrating the dynamic spatial associations learned by Traffic BERT into the TGNM model. To train the D-TGNM model, we design a novel loss function, which considers the missing values problem and prediction problem in traffic flow, to optimize the proposed model. The proposed model was validated on an actual traffic dataset collected in Wuhan, China. Experimental results showed that D-TGNM achieved good prediction results under four missing data scenarios (15% random missing, 15% block missing, 30% random missing, and 30% block missing), and outperformed ten existing state-of-the-art baselines.

Accurate estimation of missing traffic data is one of the essential components in intelligent transportation systems (ITS). The non-Euclidean data structure and complex missing traffic flow patterns make it challenging to capture nonlinear spatiotemporal correlations of missing traffic flow, which are critical for the imputation of missing traffic data. In this study, we propose a novel multi-view bidirectional spatiotemporal graph network called Multi-BiSTGN to impute urban traffic data with complex missing patterns. First, three spatiotemporal graph sequences are constructed to comprehensively describe traffic conditions from different temporal correlation views, i.e. temporal closeness view, daily periodicity view, and weekly periodicity view. Then, three bidirectional spatiotemporal graph networks are fused by a parametric-matrix-based method to obtain the final imputation results. To train the Multi-BiSTGN model, a novel loss function that considers the interactions between three temporal correlation views is designed to optimize the parameters of the Multi-BiSTGN model. The proposed model was validated on real-world traffic datasets collected in Wuhan, China. Experimental results showed that Multi-BiSTGN outperformed ten existing baselines under different missing types (random missing, block missing, and mixed missing) and missing rates.

Effective public transit planning needs to address realistic travel demands, which can be illustrated by corridors across major residential areas and activity centers. It is vital to identify public transit corridors that contain the most significant transit travel demand patterns. We propose a two-stage approach to discover primary public transit corridors at high spatio-temporal resolutions using massive real-world smart card and bus trajectory data, which manifest rich transit demand patterns over space and time. The first stage was to reconstruct chained trips for individual passengers using multi-source massive public transit data. In the second stage, a shared-flow clustering algorithm was developed to identify public transit corridors based on reconstructed individual transit trips. The proposed approach was evaluated using transit data collected in Shenzhen, China. Experimental results demonstrated that the proposed approach is a practical tool for extracting time-varying corridors for many potential applications, such as transit planning and management.

The temporal dimensions of public transit accessibility have recently garnered an increasing amount of interest. However, the existing literature on transit accessibility is heavily based on oversimplified assumptions that transit services operate at deterministic speeds using predetermined timetables. These measurements may overestimate transit accessibility, especially for large metropolitan areas where inter- and intra-modal transfers are frequent. To handle travel time uncertainty, a multi-modal transit accessibility modeling approach is proposed to account for realistic variations in travel time and service reliability. The proposed approach is applied to the mapping of transit accessibility in Shenzhen (China), where transit services exhibit significant travel time variations over space and time. Compared to traditional transit accessibility measures, our method has been demonstrated to better capture intrinsic spatial and temporal accessibility variations with complex multi-modal transit networks. Normal distribution of inter-stop travel times and constant travel speed between GPS sampling points are assumed to simply the computation, which we consider to adjust in future studies to better quantify the dynamics of transit accessibility across space and time.

The continually increasing size of geospatial data sets poses a computational challenge when conducting interactive visual analytics using conventional desktop-based visualization tools. In recent decades, improvements in parallel visualization using state-of-the-art computing techniques have significantly enhanced our capacity to analyse massive geospatial data sets. However, only a few strategies have been developed to maximize the utilization of parallel computing resources to support interactive visualization. In particular, an efficient visualization intensity prediction component is lacking from most existing parallel visualization frameworks. In this study, we propose a data-driven view-dependent visualization intensity prediction method, which can dynamically predict the visualization intensity based on the distribution patterns of spatio-temporal data. The predicted results are used to schedule the allocation of visualization tasks. We integrated this strategy with a parallel visualization system deployed in a compute unified device architecture (CUDA)-enabled graphical processing units (GPUs) cloud. To evaluate the flexibility of this strategy, we performed experiments using dust storm data sets produced from a regional climate model. The results of the experiments showed that the proposed method yields stable and accurate prediction results with acceptable computational overheads under different types of interactive visualization operations. The results also showed that our strategy improves the overall visualization efficiency by incorporating intensity-based scheduling.