Water body extraction techniques from remotely sensed images are crucial in water resources distribution studies, climate change studies and other work. The traditional remote sensing water body extraction has the problems of low accuracy and being time-consuming and laborious, and the water body recognition technique based on deep learning is more efficient and accurate than the traditional threshold method; however, there is the problem that the basic model of semantic segmentation is not well-adapted to complex remote sensing images. Based on this, this study adopts an OCNet feature extraction network to modify the base model of semantic segmentation, and the resulting model achieves excellent performance on water body remote sensing images. Compared with the traditional water body extraction method and the base network, the OCNet modified model has obvious improvement, and is applicable to the extraction of water bodies in true-color remote sensing images such as high-score images and unmanned aerial vehicle remote sensing images. The results show that the model in this study can realize automatic and fast extraction of water bodies from remote sensing images, and the predicted water body image accuracy (ACC) can reach 85%. This study can realize fast and accurate extraction of water bodies, which is of great significance for water resources acquisition and flood disaster prediction.

Identifying the spatial changes in farming–pastoral ecotone (FPE) is of utmost importance for the development of strategies for ecological protection in ecologically fragile areas. This study employed spatial autocorrelation and spatial clustering techniques to map FPE at the pixel scale using CLCD data with a spatial resolution of 30 × 30 m in the years 1985, 2000, and 2021, and then analyzed the changes of the FPE in northern China. The results showed that the FPE is mainly located at the border between the Inner Mongolia Autonomous Region and the adjacent provinces, which is along the Hu-line and the 400-mm isohyetal line. The area of the FPE was 63.94 × 10⁴ km², 62.90 × 10⁴ km², and 53.81 × 10⁴ km² in 1985, 2000, and 2021, respectively, accounting for 6.7%, 6.6%, 5.6% of the total land area in China. The FPE boundary moved northwestward during 1985–2021, demonstrating retreating, fragmenting, and shrinking tendencies. The decreased areas and the moving distances of the gravity center are six times and four times greater during 2000–2021 than that during 1985–2000, respectively. Moreover, the discontinuous change in FPE was mainly due to the increase in forest land, especially for the conversion of grassland to forest land. Our findings provide guidance for the construction of ecological civilization and the optimization of ecosystem structure in the farming–pastoral ecotone.

The interactions between economic development, environmental sustainability, population growth, and urbanization are vital in assessing the ecological dynamics of urban agglomerations. This study explores the relationship between economic development, environmental sustainability, population growth, and urbanization within the Xia-Zhang-Quan urban agglomeration in Fujian Province from 1989 to 2022. Utilizing Landsat remote sensing images, we calculated the Remote Sensing Ecological Index (RSEI) to evaluate changes in ecological quality. The results show that the average RSEI values for 1989, 2000, 2010, and 2022 were 0.5829, 0.5607, 0.5827, and 0.6195, respectively, indicating an initial decline followed by a significant increase, culminating in an overall upward trend. The spatial distribution of RSEI classification shows that the study area has the largest proportion of mainly “good” ecological quality. The proportion of areas with “excellent” ecological environmental quality has increased (13.41% in 1989 and 25.12% in 2022), while those with “general” quality has decreased (28.03% in 1989 and 21.21% in 2022). Over the past three decades, Xiamen experienced substantial ecological degradation (RSEI change of −0.0897), Zhangzhou showed marked improvement (RSEI change of 0.0519), and Quanzhou exhibited slight deterioration (RSEI change of −0.0396). Central urban areas typically had poorer ecological conditions but showed signs of improvement, whereas non-central urban regions demonstrated significant environmental enhancement. The factor detector analysis identified land use as the dominant factor influencing ecological environmental quality, with precipitation having a relatively minor impact. Interaction analysis revealed that all other factors demonstrated bi-variable enhancement or nonlinear enhancement, suggesting that the interactive effects of these factors are greater than the effects of individual factors alone. Land use consistently showed solid explanatory power. Temperature also exhibited significant influence in 2022 when interacting with other factors. Due to urban planning that can plan for land use, these findings suggest that effective urban planning can harmonize economic development with ecological protection within the Xia-Zhang-Quan urban agglomeration.