As an essential material carrier of cultural heritage, the accurate identification and effective monitoring of buildings in traditional Chinese villages are of great significance to the sustainable development of villages. However, along with rapid urbanization in recent years, many towns have experienced problems such as private construction, hollowing out, and land abuse, destroying the traditional appearance of villages. This study combines deep learning technology and UAV remote sensing to propose a high-precision extraction method for conventional village architecture. Firstly, this study constructs the first sample database of traditional village architecture based on UAV remote sensing orthophotos of eight representative villages in Beijing, combined with fine classification; secondly, in the face of the diversity and complexity of the built environment in traditional villages, we use the Mask R-CNN instance segmentation model as the basis and Path Aggregate Feature Pyramid Network (PAFPN) and Atlas Space Pyramid Pool (ASPP) as the main strategies to enhance the backbone model for multi-scale feature extraction and fusion, using data increment and migration learning as auxiliary means to overcome the shortage of labeled data. The results showed that some categories could achieve more than 91% accuracy, with average precision, recall, F1-score, and Intersection over Union (IoU) values reaching 71.3% (+7.8%), 81.9% (+4.6%), 75.7% (+6.0%), and 69.4% (+8.5%), respectively. The application practice in Hexi village shows that the method has good generalization ability and robustness, and has good application prospects for future traditional village conservation.

Understanding the regularity and determinants of mobility is indispensable for the reasonable deployment of shared bicycles and urban planning. A spatial interaction network covering streets in Beijing’s six main districts, using bike sharing data, is constructed and analyzed. as Additionally, the exponential random graph model (ERGM) is used to interpret the influencing factors of the network structure and the mobility regularity. The characteristics of the spatial interaction network structure and temporal characteristics between weekdays and weekends show the following: the network structure on weekdays is obvious; the flow edge is always between adjacent blocks; the traffic flow frequently changes and clusters; the network structure on weekends is more complex, showing scattering and seldom changing; and there is a stronger interaction between blocks. Additionally, the predicted result of the ERGM shows that the influencing factors selected in this paper are positively correlated with the spatial interaction network. Among them, the three most important determinants are building density, housing prices and the number of residential areas. Additionally, the determinant of financial services shows greater effects on weekdays than weekends.

Urban multimodal travel trajectory prediction is a core challenge in Intelligent Transportation Systems (ITSs). It requires modeling both spatiotemporal dependencies and dynamic interactions among different travel modes such as taxi, bike-sharing, and buses. To address the limitations of existing methods in capturing these diverse trajectory characteristics, we propose a spatiotemporal multi-model ensemble framework, which is an ensemble model called GLEN (GCN and LSTM Ensemble Network). Firstly, the trajectory feature adaptive driven model selection mechanism classifies trajectories into dynamic travel and fixed-route scenarios. Secondly, we use a Graph Convolutional Network (GCN) to capture dynamic travel patterns and Long Short-Term Memory (LSTM) network to model fixed-route patterns. Subsequently the outputs of these models are dynamically weighted, integrated, and fused over a spatiotemporal grid to produce accurate forecasts of urban total traffic flow at multiple future time steps. Finally, experimental validation using Beijing’s Chaoyang district datasets demonstrates that our framework effectively captures spatiotemporal and interactive characteristics between multimodal travel trajectories and outperforms mainstream baselines, thereby offering robust support for urban traffic management and planning.

With the accelerating pace of urbanization, historic districts are increasingly confronted with the dual challenge of coordinating heritage preservation and sustainable development. This study proposes an intelligent evaluation framework that integrates spatiotemporal street view imagery, affective perception modeling, and scene recognition to reveal the evolutionary dynamics of built environment spatial quality in historic districts. Empirical analysis based on multi-temporal data (2013–2020) from the Wudadao Historic District in Tianjin demonstrates that spatial quality is shaped by a complex interplay of factors, including planning and preservation policies, landscape greening, pedestrian-oriented design, infrastructure adequacy, and equitable resource allocation. These findings validate the framework’s effectiveness as a tool for monitoring urban sustainability. Moreover, it provides actionable insights for the development of resilient, equitable, and culturally vibrant built environments, effectively bridging the gap between technological innovation and sustainable governance in the context of historic districts.

Reasonably allocating medical resources can effsectively optimize the utilization efficiency of such resources. This paper took Taiyuan City as an example and established a model to evaluate the rationality of medical resource spatial allocation, incorporating two key dimensions: the spatial layout and the supply and demand of medical resources. In terms of the spatial layout, three indexes were included: Firstly, the service coverage rates of different levels of medical institutions, based on residents’ medical orientations, were calculated using network analysis methods. Secondly, the Huff-2SFCA method was improved to calculate the accessibility of medical resources for four different modes of transportation. Then, the Health Resource Agglomeration Degree (HRAD) and Population Agglomeration Degree (PAD) were used to quantify the equity of medical resources. In terms of the supply and demand of medical resources, one index was included: the supply–demand ratio of medical resources during sudden public health events, which was calculated using the number of beds per thousand people as an indicator. These four indexes were weighted using the entropy weight method to obtain the rationality grade of medical resource spatial allocation in Taiyuan City. The study found that the rationality evaluation level of medical resource allocation in the central urban area of Taiyuan City followed a “concentrically decreasing” pattern. The rating ranged from “very reasonable” to “less reasonable”, with the area of each level expanding gradually. The areas rated within the top two categories only accounted for 19.92% of the study area, while the area rated as “less reasonable” occupied 38.73% of the total area. These results indicate that the model accounted for residents’ travel for various medical orientations and the availability of resources during public health emergencies. It considered both the spatial layout and supply and demand of medical resources, offering recommendations for the precise allocation of urban medical resources.

Building change detection involves identifying areas where buildings have changed by comparing multi-temporal remote sensing imagery of the same geographical region. Recent advances in Transformer-based methods have significantly improved remote sensing change detection. However, current Transformer models still exhibit persistent limitations in effectively extracting multi-scale semantic features within complex scenarios. To more effectively extract multi-scale semantic features in complex scenes, we propose a novel model, which is the Transformer-based Multi-Scale Semantic Extraction Change Detection Network (MSSE-CDNet). The model employs a Siamese network architecture to enable precise change recognition. MSSE-CDNet comprises four parts, which together contain five modules: (1) a CNN feature extraction module, (2) a multi-scale semantic extraction module, (3) a Transformer encoder and decoder module, and (4) a prediction module. Comprehensive experiments on the standard LEVIR-CD benchmark for building change detection demonstrate our approach’s superiority over state-of-the-art methods. Compared to existing models such as FC-Siam-Di, FC-Siam-Conc, DTCTSCN, BIT, and SNUNet, MSSE-CDNet achieves significant and consistent gains in performance metrics, with F1 scores improved by 4.22%, 6.84%, 2.86%, 1.22%, and 2.37%, respectively, and Intersection over Union (IoU) improved by 6.78%, 10.74%, 4.65%, 2.02%, and 3.87%, respectively. These results robustly substantiate the effectiveness of our framework on an established benchmark dataset.