Deep convolutional networks often encounter information bottlenecks when extracting land object features, resulting in critical geometric information loss, which impedes semantic segmentation capabilities in complex geospatial backgrounds. We developed LULC-SegNet, a semantic segmentation network for land use and land cover (LULC), which integrates features from the denoising diffusion probabilistic model (DDPM). This network enhances the clarity of the edge segmentation, detail resolution, and the visualization and accuracy of the contours by delving into the spatial details of the remote sensing images. The LULC-SegNet incorporates DDPM decoder features into the LULC segmentation task, utilizing machine learning clustering algorithms and spatial attention to extract continuous DDPM semantic features. The network addresses the potential loss of spatial details during feature extraction in convolutional neural network (CNN), and the integration of the DDPM features with the CNN feature extraction network improves the accuracy of the segmentation boundaries of the geographical features. Ablation and comparison experiments conducted on the Circum-Tarim Basin Region LULC Dataset demonstrate that the LULC-SegNet improved the LULC semantic segmentation. The LULC-SegNet excels in multiple key performance indicators compared to existing advanced semantic segmentation methods. Specifically, the network achieved remarkable scores of 80.25% in the mean intersection over union (MIOU) and 93.92% in the F1 score, surpassing current technologies. The LULC-SegNet demonstrated an IOU score of 73.67%, particularly in segmenting the small-sample river class. Our method adapts to the complex geophysical characteristics of remote sensing datasets, enhancing the performance of automatic semantic segmentation tasks for land use and land cover changes and making critical advancements.

With increasing research on geological hazards and the development of geographic information technology, slope units play an increasingly important role in landslide susceptibility assessment and prevention work. The scientific and reasonable division of slope units directly impacts the accuracy and practicality of analysis results. Despite the significant progress in slope unit division techniques, most existing methods still have certain limitations, such as a strong dependence on manually set thresholds during the division process, resulting in low levels of automation and efficiency. To address this issue, a new parameter-free slope unit extraction algorithm that integrates terrain factors, called Terrain Factor Parameter-Free Slope Unit Division (TFPF-SU), is introduced. This eliminates the issue of manually setting parameter thresholds during the slope unit division process. This algorithm fully utilizes the terrain information provided by digital elevation models (DEMs) to accurately calculate the curvature, slope, and aspect data for each point. On the basis of the inherent consistency principles among slope, aspect, and curvature, object-oriented image segmentation technology is used to achieve slope unit division. We select Dongchuan District in Yunnan Province, China, as a test area to verify the TFPF-SU algorithm and conduct a detailed comparative analysis and validation of the results with those obtained via traditional hydrological analysis methods from both qualitative and quantitative perspectives. In the quantitative analysis, we utilize the size and shape of the slope units. The results indicate the following: ① the slope units obtained with the TFPF-SU method are more uniform in size, avoiding issues with oversized or irregularly shaped units; ② the slope unit shapes obtained with the TFPF-SU method are more reasonable, with about 70% of the units falling within a reasonable shape index range, compared to only about 32% with the hydrological method; and ③ the slope units produced by the TFPF-SU method align more closely with terrain authenticity, exhibiting a higher degree of topographical conformity.

Semantic segmentation of land use and land cover (LULC) in arid regions remains challenging due to severe class imbalance, fragmented spatial distributions, and high spectral similarity among different land cover types. These characteristics often lead to an information bottleneck in deep segmentation networks and hinder the extraction of discriminative semantic representations. To address these issues, we propose SDS-Former, a lightweight semantic segmentation network specifically designed for remote sensing imagery in arid environments. SDS-Former incorporates an SSM-inspired Lightweight Semantic Enhancement (LSE) module to strengthen contextual modeling and alleviate the loss of discriminative information in deep features. To tackle scale variations, a Dynamic Selective Feature Fusion (DSFF) module is employed in the decoder to adaptively weight and fuse high-level semantics with low-level spatial details. Furthermore, a Feature Refinement Head (FRH) is introduced to enhance boundary localization and improve the recognition of small-scale and sparsely distributed land cover objects. Extensive ablation and comparative experiments demonstrate that SDS-Former consistently outperforms representative semantic segmentation methods across multiple evaluation metrics. On the Tarim Basin dataset, the proposed network achieves a mean Intersection over Union (mIoU) of 82.51% and an F1 score of 86.47%, indicating its superior effectiveness and robustness. Qualitative results further verify that SDS-Former exhibits clear advantages in distinguishing spectrally similar land cover types and preserving the spatial continuity of ground objects in complex arid-region scenes.