Over the past several years, volunteered geographic information (VGI) has expanded rapidly. VGI collection has been proven to serve as a highly successful means of acquiring timely and detailed global spatial data. However, VGI includes several special properties. For example, the contributor’s reputation affects the quality of objects edited, and a geographic object may have multiple versions. The existing spatio-temporal data model cannot describe the unique properties of VGI. Therefore, a spatio-temporal VGI model considering trust-related information is presented in this paper. In this model, central elements of the VGI environment, e.g., geographic entity, entity state, state version, contributor, reputation, geographic event, and edit event, and their interaction mechanisms are analysed. Major VGI objects and relations are determined using the object-oriented method and trust-related operations, and their relationships are analysed, and nine linkage rules among trust-related operations are found to maintain the consistency of corresponding data. A prototype system for the spatio-temporal VGI model is presented, and the effectiveness of the model is verified.

Road intersections are essential to road networks. How to precisely recognize road intersections based on GPS data is still challenging in intelligent transportation systems. Road intersection recognition involves detecting intersections and recognizing its scope. There are few works on intersections’ scope recognition. The existing methods always focus on road intersection detection. It includes two parts: one is selecting turning points from GPS data and extracting their geometric features, another is clustering them into center coordinates of road intersections. However, the accuracy of road intersection detection still has improvement room due to two drawbacks: (1) Besides geometric features, spatial features explored from GPS data and the interactions among all features are also important to represent intersections’ semantics more accurately, and (2) How to capture the points around intersections for clustering has great impact on the accuracy of intersection detection. To solve the preceding problems, we propose a novel approach for road intersection recognition via combining a classification model and clustering algorithm based on GPS data, which involves detecting the center coordinate and computing the radius of the intersection. Firstly, we distil geometric features and spatial features from historical GPS points. These features are inputted into the Extreme Deep Factorization Machine (xDeepFM) model which is applied for capturing the GPS points nearby road intersections. Secondly, the preceding points are clustered into center coordinates of road intersections by the Density-Based Spatial Clustering of Applications with Noise algorithm (DBSCAN). Thirdly, we present a new method of radius computing by integrating Delaunay triangulation with circle shape structure. Experiments are carried out on the GPS data of Chengdu, China. Compared with some state-of-the-art methods, our approach achieves higher accuracy on road intersection recognition based on GPS data. The precision, recall, and f-measure of our proposed center coordinates detection method are respectively 99.0%, 92.7%, and 95.8% when the matching area’s radius is 30 m. Moreover, the error of the proposed radius calculation method is less than 26.5%.

Federated learning (FL) enables privacy-preserving collaborative training by iteratively aggregating locally trained model parameters on a central server while keeping raw data decentralized. However, FL faces critical challenges arising from data heterogeneity, model heterogeneity, and excessive communication costs. To address these issues, we propose a communication-efficient federated learning via knowledge distillation and ternary compression framework (FedDT). First, to mitigate the negative impact of data heterogeneity, we pre-train personalized heterogeneous teacher models for each client and employ knowledge distillation to transfer knowledge from teachers to student models, enhancing convergence speed and generalization capability. Second, to resolve model heterogeneity, we utilize the server-initialized global model as a shared student model across clients, where homogeneous student models mask local architectural variations to align feature representations. Finally, to reduce communication overhead, we introduce a two-level compression strategy that quantizes the distilled student model into ternary weight networks layer by layer, substantially decreasing parameter size. Comprehensive evaluations on both MNIST and Cifar10 datasets confirm that FedDT attains 7.85% higher model accuracy and reduces communication overhead by an average of 78% compared to baseline methods. This approach provides a lightweight solution for FL systems, significantly lowering communication costs while maintaining superior performance.

Building type prediction is a critical task for urban planning and population estimation. The growing availability of multi-source data presents rich semantic information for building type prediction. However, existing residential building prediction methods have problems with feature extraction and fusion from multi-type data and multi-level interactions between features. To overcome these limitations, we propose a deep learning approach that takes both the internal and external characteristics of buildings into consideration for residential building prediction. The internal features are the shape characteristics of buildings, and the external features include location features and semantic features. The location features include the proximity of the buildings to the nearest road and areas of interest (AOI), and the semantic features are mainly threefold: spatial co-location patterns of points of interest (POI), nighttime light, and land use information of the buildings. A deep learning model, DeepFM, with multi-type features embedded, was deployed to train and predict building types. Comparative and ablation experiments using OpenStreetMap and the nighttime light dataset were carried out. The results showed that our model had significantly higher classification performance compared with other models, and the F1 score of our model was 0.9444. It testified that the external semantic features of the building significantly enhanced the predicted performance. Moreover, our model showed good performance in the transfer learning between different regions. This research not only significantly enhances the accuracy of residential building identification but also offers valuable insights and ideas for related studies.

Urban planning and function layout have important implications for the journeys of a large percentage of commuters, which often make up the majority of daily traffic in many cities. Therefore, the analysis and forecast of traffic flow among urban functional areas are of great significance for detecting urban traffic flow directions and traffic congestion causes, as well as helping commuters plan routes in advance. Existing methods based on ride-hailing trajectories are relatively effective solution schemes, but they often lack in-depth analyses on time and space. In the paper, to explore the rules and trends of traffic flow among functional areas, a new spatiotemporal characteristics analysis and forecast method of traffic flow among functional areas based on urban ride-hailing trajectories is proposed. Firstly, a city is divided into areas based on the actual urban road topology, and all functional areas are generated by using areas of interest (AOI); then, according to the proximity and periodicity of inter-area traffic flow data, the periodic sequence and the adjacent sequence are established, and the topological structure is learned through graph convolutional neural (GCN) networks to extract the spatial correlation of traffic flow among functional areas. Furthermore, we propose an attention-based gated graph convolutional network (AG-GCN) forecast method, which is used to extract the temporal features of traffic flow among functional areas and make predictions. In the experiment, the proposed method is verified by using real urban traffic flow data. The results show that the method can not only mine the traffic flow characteristics among functional areas under different time periods, directions, and distances, but also forecast the spatiotemporal change trend of traffic flow among functional areas in a multi-step manner, and the accuracy of the forecasting results is higher than that of common benchmark methods, reaching 96.82%.

Urbanization has been proven to be a critical factor in modifying local or regional climate characteristics. This research aims to examine the impact of urbanization on extreme climate indices in the Yangtze River Economic Belt (YREB), China, by using meteorological observation data from 2000 to 2019. Three main steps are involved. First, a clustered threshold method based on remote-sensing nighttime light data is used to extract urban built-up areas, and urban and rural meteorological stations can be identified based on the boundary of urban built-up areas. Nonparametric statistical tests, namely, the Mann–Kendall test and Sen’s slope, are then applied to measure the trend characteristics of extreme climate indices. Finally, the urbanization contribution rate is employed to quantify the impact of urbanization on extreme climate indices. The results indicate that urbanization has a more serious impact on extreme temperature indices than on extreme precipitation indices in the YREB. For extreme temperature indices, urbanization generally causes more (less) frequent occurrence of warm (cold) events. The impact of urbanization on different extreme temperature indices has heterogeneous characteristics, including the difference in contamination levels and spatial variation of the impacted cities. For extreme precipitation indices, only a few cities impacted by urbanization are detected, but among these cities, urbanization contributes to increasing the trend of all indices.