No abstract

No abstract

The quality of the ecological environment determines human well-being, and the degree of ecological environment quality has a significant impact on regional sustainable development. Currently, the assessment content of ecological environment quality in Luoyang is relatively single-indicator-based and is insufficient to comprehensively reflect the changes in the ecological environment quality of Luoyang city. Therefore, the study aims to use the Remote Sensing Ecological Index (RSEI), a comprehensive evaluation model, with Landsat remote sensing images and statistical yearbooks as the data sources, to evaluate the spatiotemporal dynamic changes in the ecological environment quality of Luoyang city from 2002 to 2022 through trend analysis and mutation testing; the study employs geographical detectors to analyze the driving factors about the changes in ecological environment quality. The study found that: (1) the average RSEI value in Luoyang city has increased by 0.102 in the past 20 years, indicating an overall improvement in the ecological environment quality of Luoyang city. (2) The northern region of the study area has lower RSEI values, while the southern region has better ecological environment quality, which corresponds to the fact that the northern part of Luoyang city has intensive human activities, while the southern part is characterized by higher vegetation coverage in mountainous areas. (3) The proportion of areas with medium and above ecological environment quality grades have increased from 47.2% to 67.5%, indicating a positive trend in future ecological environment quality changes. (4) The population change was the strongest single factor influencing the ecological environment quality change in Luoyang city. The interaction between temperature and GDP was relatively the strongest. The current ecological environment status in the study area is the result of the combined effects of natural and anthropogenic factors. The research conclusions contribute to improving regional ecological environment quality and are of great significance for the regional ecological environment planning and the achievement of sustainable development goals.

Deep learning algorithms offer an effective solution to the inefficiencies and poor results of traditional methods for building a footprint extraction from high-resolution remote sensing imagery. However, the heterogeneous shapes and sizes of buildings render local extraction vulnerable to the influence of intricate backgrounds or scenes, culminating in intra-class inconsistency and inaccurate segmentation outcomes. Moreover, the methods for extracting buildings from very high-resolution (VHR) images at present often lose spatial texture information during down-sampling, leading to problems, such as blurry image boundaries or object sticking. To solve these problems, we propose the multi-scale boundary-refined HRNet (MBR-HRNet) model, which preserves detailed boundary features for accurate building segmentation. The boundary refinement module (BRM) enhances the accuracy of small buildings and boundary extraction in the building segmentation network by integrating edge information learning into a separate branch. Additionally, the multi-scale context fusion module integrates feature information of different scales, enhancing the accuracy of the final predicted image. Experiments on WHU and Massachusetts building datasets have shown that MBR-HRNet outperforms other advanced semantic segmentation models, achieving the highest intersection over union results of 91.31% and 70.97%, respectively.

No abstract