The unequal allocation of healthcare resources raises many fundamental problems, one of which is how to address inequity in population health. This paper focuses on disparities in public transport healthcare accessibility, with a special focus on an expanding subway system. Based on a vulnerability index, including factors that are likely to limit healthcare opportunities, a two-step floating catchment area method was used to assess the distribution of supply and demand for healthcare. Quantity, quality, and walking distance accessibility were aggregated into hexagonal grids. The Theil index was used to measure inequity and understand the influence of subways on spatial disparities in healthcare accessibility. The ongoing construction of the subway has heterogeneous impacts on healthcare accessibility for different parts of the city and exacerbates spatial inequity in many areas. In an environment where people in peri-urban areas are excluded from healthcare access because of low subway coverage, the results suggest that the potential for subways to address inaccessibility is limited. The findings highlight the requirement of efficient public transport services and are relevant to researchers, planners, and policymakers aiming to improve accessibility to healthcare, especially for populations who dwell in winter cities.

The precise leveling method is often used to monitor the uneven deformation of the highway bridge head, which requires manual contact, dangerous and heavy workload. In order to solve these issues, this paper proposes a method to extract deformation features of the highway bridge head based on mobile terrestrial laser scanning (TLS) point clouds. Firstly, an automatic data acquisition system is designed to analyze and determinate the scanning station spacing and scanning resolution. Then acquired road point clouds are denoised based on the plane fitting method, which usually sets the experimental threshold. The road dividing line information is used for point clouds coarse registration, and the weighted average elevation method is used for refined registration. Lastly, the elevation of the deformation monitoring point is the average elevation of all points in the selected grid surface, which will mitigate random errors in the elevation of a single point. Point clouds of three different roads were collected to verify the proposed method. The results show that the accuracy of the elevation repeatability is better than ± 1mm, and the accuracy of the elevation check with the TM50 total station is better than ± 2mm, which meets the requirements of deformation monitoring. In addition, it takes about 3-4 minutes to complete the data collection of a station on the highway bridge head. Therefore, the proposed method based on mobile TLS data can be suitable for highway bridge head deformation measurement.

It is essential to understand the spatial equity of healthcare services to achieve the Sustainable Development Goals. Spatial and non-spatial factors affect access to healthcare, resulting in inequality in the hierarchical medical treatment system. Thus, to provide a comprehensive equity evaluation, it is indispensable to investigate the extent to which spatial accessibility to healthcare services varies due to various factors. This study attempted to analyze the determinants of healthcare accessibility under multi-trip modes and integrate them into Theil index, as a demand index to evaluate spatial equity in the system. The results reveal an inadequate and inequitable distribution of healthcare resources. While access to primary hospitals is limited (47.37% of residential locations cannot access them on foot), 96.58% of residential locations can access general and tertiary hospitals via public transport or driving. Furthermore, inequitable access to the three-tiered medical system was evaluated on a more granular scale, with primary hospitals being closest to achieving equity (inequitable for only 48.83% of residential locations), followed by general and tertiary hospitals (82.01% and 89.20%, respectively). The unequal residential locations brought on by an abundance of medical resources are far from those with a shortage of resources (66.86% > 5.34%). It is thus suggested that services be expanded or resources be transferred to move toward a more equitable system. Our findings provide policymakers with insights into how to increase accessibility to public health.

Small differences between classes and big variations within classes in multi-category semantic segmentation are problems that are not completely solved by the “encoder-decoder” structure of the fully convolutional neural network, leading to the imprecise perception of easily confused categories. To address this issue, in this paper, we believe that sufficient contextual information can provide more interpretation clues to the model. Additionally, if we can mine the class-specific perceptual information for each semantic class, we can enhance the information belonging to the corresponding class in the decoding process. Therefore, we propose the Class-Guidance network based on Pyramid Vision Transformer (PVT). In detail, with the PVT as the encoder network, the following decoding process is composed of three stages. Firstly, we design a Receptive Field Block (RFB) to expand the receptive field to different degrees using parallel branching processing and different dilatation rates. Secondly, we put forward a Semantic Guidance Block (SGB) to utilize the high-level features to guide the channel enhancement of low-level features. Thirdly, we propose the Class Guidance Block (CGB) to achieve the class-aware guidance of adjacent features and achieve the refined segmentation by a progressive approach. The overall accuracy of the method is 88.91% and 88.87%, respectively, according to experimental findings on the Potsdam and Vaihingen datasets.

This study quantifies forest aboveground biomass (AGB) using integrated remote sensing features from high-resolution GaoFen-7 (GF-7) satellite imagery. We combined texture features, vegetation indices, and RGB spectral bands to improve estimation accuracy. Three machine learning algorithms—Random Forest (RF), Gradient Boosting Tree (GBT), and XGBoost—were compared with a stacking ensemble model using five-fold cross-validation on forest plots in Beijing’s Daxing District. Feature importance was evaluated through SHAP to identify key predictive variables. Results show that texture features exhibit scale-dependent predictive power, while visible-band vegetation indices strongly correlate with AGB. The Stacking ensemble achieved optimal performance (R² = 0.62, RMSE = 57.34 Mg/ha, MAE = 39.99 Mg/ha), outperforming XGBoost (R² = 0.59), RF (R² = 0.58), and GBT (R² = 0.57). Compared to the best individual model, Stacking improved R² by 5.1% and effectively mitigated over- and underestimation biases. These findings demonstrate the effectiveness of ensemble learning for forest AGB estimation and suggest potential for regional-scale carbon monitoring applications.