Zhiying Liao

Island coastline segmentation plays a crucial role in remote sensing image processing, especially when the island environment is complex and the scale is small, making segmentation challenging. The complex morphology of the islands and the small islands are the main causes of boundary blurring and topological discontinuity in the segmentation of the island coast. Therefore, this study proposes GTSegNet, an island coastline segmentation method designed to address the issues of boundary blurring and topological discontinuity in complex backgrounds. First, by introducing the Graph Contextual Modeling Module (GCB), the model captures global information and addresses the issue of neglected local features due to complex backgrounds and scale differences, thereby improving the model’s ability to discern blurry boundaries. Secondly, the Morphological Topology-Aware Refinement Module (TARM) is used for boundary sharpening and false response suppression, specifically addressing the issue of topological discontinuity, thus improving the accuracy of boundary localization and the continuity of topological structures. The two modules work synergistically, significantly improving the accuracy of the boundaries and topological continuity of the island coastline. Training and comparative experiments conducted on the newly constructed island coastline dataset demonstrate that GTSegNet achieves an outstanding performance with an mIoU of 96.96% and a Recall of 98.54%. Compared to other remote sensing semantic segmentation methods, GTSegNet consistently exhibits stable advantages in both quantitative and qualitative assessments, showcasing its great potential for large-scale marine mapping and macro-scale monitoring tasks.

In light of global climate change and accelerated urbanization, preserving and restoring island ecosystems has become critically important. This study focuses on Changxing Island in Dalian, China, evaluating the quality of its ecological environment. The research aims to quantify ecological changes since 2000, with an emphasis on land use transformations, coastline evolution, and the driving factors behind these changes. Using the Google Earth Engine (GEE) platform and remote sensing technology, an island remote sensing ecological index (IRSEI) was developed. The development of the IRSEI was grounded in several key ecological parameters, including the normalized difference vegetation index (NDVI), wetness index (WET), land surface temperature index (LST), multiband drought stress index (M-NDBSI), and land use intensity index (LUI). The research results show that, since 2002, land use types on Changxing Island have undergone significant changes, with a notable decrease in arable land and a significant increase in built-up areas, reflecting the ongoing urbanization process. With respect to coastline changes, the total coastline length of Changxing Island steadily increased from 2002 to 2022, with an average annual growth rate of 2.15 km. This change was driven mainly by reclamation and infrastructure construction. The IRSEI analysis further revealed a clear deterioration in the quality of the ecological environment of Changxing Island during the study period. The proportion of excellent ecological area decreased from 39.3% in 2002 to 8.89% in 2022, whereas the areas classified as poor and very poor increased to 56.23 km² and 129.84 km², both of which set new historical records. These findings suggest that, as urbanization and coastline development intensify, the ecosystem of Changxing Island is at significant risk of degradation. The optimized IRSEI effectively captured the ecological environment quality of the island, improved the long-term stability of the index, and adequately met the requirements for large-scale and long-term ecological environment quality monitoring.