With the rapid development of mobile data acquisition technology, the volume of available spatial data is growing at an increasingly fast pace. The real-time processing of big spatial data has become a research frontier in the field of Geographic Information Systems (GIS). To cope with these highly dynamic data, we aim to reduce the time complexity of data updating by modifying the traditional spatial index. However, existing algorithms and data structures are based on single work nodes, which are incapable of handling the required high numbers and update rates of moving objects. In this paper, we present a distributed spatial index based on Apache Storm, an open-source distributed real-time computation system. Using this approach, we compare the range and K-nearest neighbor (KNN) query efficiency of four spatial indexes on a single dataset and introduce a method of performing spatial joins between two moving datasets. In particular, we build a secondary distributed index for spatial join queries based on the grid-partition index. Finally, a series of experiments are presented to explore the factors that affect the performance of the distributed index and to demonstrate the feasibility of the proposed distributed index based on Storm. As a real-world application, this approach has been integrated into an information system that provides real-time traffic decision support.

Prediction of traffic violations plays a key role in transportation safety. Combining with deep learning to predict traffic violations has become a new development trend. However, existing methods are based on regular spatial grids which leads to a fuzzy spatial expression and ignores the strong correlation between traffic violations and road network. A spatial topological graph can express the spatiotemporal correlation more accurately and then improve the accuracy of traffic violation prediction. Therefore, we propose a GATR (graph attention network based on road network) model to predict the spatiotemporal distribution of traffic violations, which adopts a graph attention network model combined with historical traffic violation features, external environmental features, and urban functional features. Experiments show that the GATR model can express the spatiotemporal distribution pattern of traffic violations more clearly and has higher prediction accuracy (RMSE = 1.7078) than Conv-LSTM (RMSE = 1.9180). The verification of the GATR model based on GNN Explainer shows the subgraph of the road network and the influence degree of features, which proves GATR is reasonable. GATR can provide an important reference for prevention and control of traffic violations and improve traffic safety.

Traffic violations, the primary cause of road accidents, threaten public safety by disrupting traffic flow and causing substantial casualties and economic losses. Accurate spatiotemporal prediction of violations offers critical insights for proactive traffic management. While Graph Attention Network (GAT) methods excel in spatiotemporal forecasting, their practical deployment is hindered by prohibitive computational costs when handling dynamic large-scale data. To address this issue, we propose a Lightweight Traffic Violation Prediction with Graph Attention Distillation (LTVPGA) model, transferring spatial topology comprehension from a complex GAT to an efficient multilayer perceptron (MLP) via knowledge distillation. Our core contribution lies in topology-invariant knowledge transfer, where spatial relation priors distilled from the teacher’s attention heads enable the MLP student to bypass explicit graph computation. This approach achieves significant efficiency gains for large-scale data—notably accelerated inference time and reduced memory overhead—while preserving modeling capability. We conducted a performance comparison between LTVPGA, Conv-LSTM, and GATR (teacher model). LTVPGA achieved revolutionary efficiency: consuming merely 15% memory and 0.6% training time of GATR while preserving nearly the same accuracy. This capacity enables practical deployment without sacrificing fidelity, providing a scalable solution for intelligent transportation governance.