Exploring impacts of urban expansion on ecosystem services has become a hot topic for regional sustainable development, while analyzing the ecological effects of urban expansion forms under different expansion intensities and city sizes is relatively rare. Therefore, taking a typical urban agglomeration, Shanghai-Hangzhou Bay Urban Agglomeration, as a case study, this study first analyzed the dynamics of urban expansion forms (leapfrogging, edge-expansion, and infilling) and four critical ecosystem services (carbon sequestration, food supply, habitat quality, and soil retention) in three periods from 1990 to 2019. The multiple linear regression model and zonal statistics analysis model were used to quantitatively identify the impacts of urban expansion forms on ecosystem services, taking into account different expansion intensities and city sizes. The results showed that the urban expansion trend in the study area experienced a morphological change from integration to diffusion and then to integration in 1990–2019; edge-expansion was the dominant expansion form. Food supply decreased continuously while other ecosystem services had fluctuating changes, and they all had spatial heterogeneity. The leapfrogging, edge-expansion, and infilling all had negative impacts on ecosystem services, and among them, the edge-expansion intensity had the highest influence degree in the early expansion, and the leapfrogging intensity occupied the dominant position in all influences with the expansion of urban scales. For different city sizes, the impact of edge-expansion in large-scale cities was greater than in small-scale cities in the early expansion, and the impact of leapfrogging in large-scale cities exceeded the edge-expansion in the subsequent expansion. These findings will help further understand the influential mechanisms between urban expansion and ecosystem services and provide a scientific basis for formulating reasonable urban planning.

Semantic segmentation forms the foundation for understanding very high resolution (VHR) remote sensing images, with extensive demand and practical application value. The convolutional neural networks (CNNs), known for their prowess in hierarchical feature representation, have dominated the field of semantic image segmentation. Recently, hierarchical vision transformers such as Swin have also shown excellent performance for semantic segmentation tasks. However, the hierarchical structure enlarges the receptive field to accumulate features and inevitably leads to the blurring of object boundaries. We introduce a novel object-aware network, Embedding deep SuperPixel, for VHR image semantic segmentation called ESPNet, which integrates advanced ConvNeXt and the learnable superpixel algorithm. Specifically, the developed task-oriented superpixel generation module can refine the results of the semantic segmentation branch by preserving object boundaries. This study reveals the capability of utilizing deep convolutional neural networks to accomplish both superpixel generation and semantic segmentation of VHR images within an integrated end-to-end framework. The proposed method achieved mIoU scores of 84.32, 90.13, and 55.73 on the Vaihingen, Potsdam, and LoveDA datasets, respectively. These results indicate that our model surpasses the current advanced methods, thus demonstrating the effectiveness of the proposed scheme.

Deep learning-based methods for land cover semantic change detection utilizing high-resolution, multi-temporal remote sensing imagery have emerged as a research hotspot. However, traditional CNN methods often struggle to preserve long-range spatial context information and face challenges in detecting land cover types with complex semantic change patterns in natural scenes. To address these issues, this study proposes a novel network architecture that integrates a Siamese network with differential structures and a Transformer. First, we introduce residual learning modules to improve the extraction of differential features and strengthen the representation of local features. Second, we integrate the Cross-Shaped Window (CSWin) Transformer into a differential-based Siamese network to enhance global feature extraction. To promote model training and evaluation, we propose a rural land cover change detection dataset—a high-precision dataset comprising 6 main rural land cover types. Ablation and comparative experiments were conducted on the publicly available SECOND datasets and the self-built RLCD dataset. Ablation studies on the RLCD dataset demonstrate that DSTNet achieves significant improvements over the baseline, with increases of 1.77%, 1.95%, 2.57%, and 0.92% in mIoU, Sek, Fscd, and OA. Comparative experiments on the SECOND datasets reveal that the mIoU, Sek, Fsd, and OA scores of DSTNet surpassed the second-best accuracy by 1.04%, 2.15%, 2.28%, and 0.72%.