Semantic segmentation of Polarimetric SAR (PolSAR) images is an important research topic in remote sensing. Many deep neural network-based semantic segmentation methods have been applied to PolSAR image segmentation tasks. However, a lack of effective means to deal with the similarity of object features and speckle noise in PolSAR images exists. Thisstudy aims to improve the discriminative capability of neural networks for various intensities of backscattering coefficients while reducing the effects of noise in PolSAR semantic segmentation tasks. Firstly, we propose pre-processing methods for PolSAR image data, which consist of the fusion of multi-source data and false color mapping. Then, we propose a Multi-axis Sequence Attention Segmentation Network (MASA-SegNet) for semantic segmentation of PolSAR data, which is an encoder–decoder framework. Specifically, within the encoder, a feature extractor is designed and implemented by stacking Multi-axis Sequence Attention blocks to efficiently extract PolSAR features at multiple scales while mitigating inter-class similarities and intra-class differences from speckle noise. Moreover, the process of serialized residual connection design enables the propagation of spatial information throughout the network, thereby improving the overall spatial awareness of MASA-SegNet. Within the decoder, it is used to accomplish the semantic segmentation task. The superiority of this algorithm for semantic segmentation will be explored through feature visualization. The experiments show that our proposed spatial sequence attention mechanism can effectively extract features and reduce noise interference and is thus able to obtain the best results on two large-scale public datasets (the AIR-POlSAR-Seg and FUSAR-Map datasets).

In this paper, we propose a knowledge distillation framework specifically designed for semantic segmentation tasks in agricultural scenarios. This framework aims to address several prevalent challenges in smart agriculture, including limited computational resources, strict real-time constraints, and suboptimal segmentation accuracy on cropped images. Traditional single-level feature distillation methods often suffer from insufficient knowledge transfer and inefficient utilization of multi-scale features, which significantly limits their ability to accurately segment complex crop structures in dynamic field environments. To overcome these issues, we propose a multi-level distillation strategy that leverages feature and embedding patch distillation, combining high-level semantic features with low-level texture details for joint distillation. This approach enables the precise capture of fine-grained agricultural elements, such as crop boundaries, stems, petioles, and weed clusters, which are critical for achieving robust segmentation. Additionally, we integrated an enhanced attention mechanism into the framework, which effectively strengthens and fuses key crop-related features during the distillation process, thereby further improving the model’s performance and image understanding capabilities. Extensive experiments on two agricultural datasets (sweet pepper and sugar) demonstrate that our method improves segmentation accuracy by 7.59% and 6.79%, without significantly increasing model complexity. Further validation shows that our approach exhibits strong generalization capabilities on two widely used public datasets, proving its applicability beyond agricultural domains.

Long-term stability is crucial in cropland for maintaining stable agricultural production and ensuring national food security. However, relatively few studies have been conducted on the long-term stability of cropland at the national level. This study assessed the long-term stability of cropland in China from 1990 to 2018 using a fine-resolution land use dataset. The experimental results indicated that the average area of unstable cropland in China from 1990 to 2018 amounted to 2.08 $\times {10}^6$ km², 47.31% of the total. The Qinghai–Tibet Plateau exhibited the highest average proportion of unstable cropland at 65.9%, followed by the northern arid and semiarid region, Southern China, and the Yunnan–Guizhou Plateau. The quantity of unstable cropland in China initially declined before increasing, reaching a final growth rate of 5.09%. Furthermore, this study explored the relevant driving factors of cropland’s long-term stability from both natural factors and human activities based on artificial neural networks. The relative importance of distance to vegetation reached a value of 0.30, indicating that it had the most significant influence on the long-term stability of cropland, followed by relief amplitude and soil type. This phenomenon may be attributed to the inadequate execution of the Grain for Green Policy and the requisition–compensation balance of cropland policy, along with the depletion of young and middle-aged laborers due to urban migration from rural areas. Local governments should focus on addressing the unsustainable exploitation of sloped land in rural mountainous or hilly regions while preventing urban developers from appropriating fertile cropland to compensate for less fertile areas.

Precise identification of water bodies in agricultural watersheds is crucial for irrigation, water resource management, and flood disaster prevention. However, the spectral noise caused by complex light and shadow interference and water quality differences, combined with the diverse shapes of water bodies and the high computational cost of image processing, severely limits the accuracy of water body recognition in agricultural watersheds. This paper proposed a lightweight and efficient learnable Kalman filter and Deformable Convolutional Attention Network (LKF-DCANet). The encoder is built using a shallow Channel Attention-Enhanced Deformable Convolution module (CADCN), while the decoder combines a Convolutional Additive Token Mixer (CATM) and a learnable Kalman filter (LKF) to achieve adaptive noise suppression and enhance global context modeling. Additionally, a feature-based knowledge distillation strategy is employed to further improve the representational capacity of the lightweight model. Experimental results show that LKF-DCANet achieves an Intersection over Union (IoU) of 85.95% with only 0.22 M parameters on a public dataset. When transferred to a self-constructed UAV dataset, it achieves an IoU of 96.28%, demonstrating strong generalization ability. All experiments are conducted on RGB optical imagery, confirming that LKF-DCANet offers an efficient and highly versatile solution for water body segmentation in precision agriculture.