Remote sensing change detection (CD) has garnered extensive research and application due to its ability to identify changes in land features within the same area across different periods. CD tasks require features with strong intraclass distinctions and precise spatial boundary details. Existing methods enhance the extraction of difference features but significantly increase computational complexity in high-resolution remote sensing imagery. Moreover, these methods focus on pixel-level difference extraction while neglecting feedback from the overall change object. As a result, they lack global information perception, leading to blurred edges and fragmented interiors in the change areas. To address these challenges, we propose a feature enhancement and feedback network (FEFNet) for CD. First, we designed a multilevel dual-feature fusion enhancement module (DFFM) to improve the representation of latent features between the bitemporal images. Second, we developed a feature coupling feedback module (FCFM) that efficiently decodes multiscale change features to generate extraction results. The experimental results show that FEFNet outperforms recent models in both computational efficiency and detection performance. With only 10.56G FLOPs and 2.26M parameters, FEFNet achieves an${F}_{1}$score of 92.32% on the LEVIR-CD dataset and 93.77% on the WHU-CD dataset. The code will be available athttps://github.com/XiaoJ058/RS-CD.

Deep learning-based high-resolution remote sensing for farmland extraction is a crucial method for obtaining large-scale farmland information. However, variations in crop types, growth conditions, and factors such as narrow edges in farmland lead to lower extraction accuracy and inaccurate boundaries in high-resolution remote sensing. Therefore, this letter proposes a multibranch convolutional neural network (FFENet) that employs a dense-feature overlay fusion module (FFM) and an information homogeneity enhancement module. This network facilitates rapid extraction and dense fusion of information at various scales through the implementation of the dense FM, thereby enhancing the model’s representation of global consistency and local features. The information homogeneity enhancement module further strengthens the information exchange between the bottom and top layers, improves the fusion of feature information across branches, and ensures consistent representation of internal farmland features while enhancing differentiation at the edges. The experimental results demonstrate that the proposed method effectively considers both internal global consistency and local variations in edge information, thereby ensuring the integrity of farmland plots and the continuity of the farmland edges. The quantitative evaluation of the dataset shows that the model performs well in farmland extraction, with overall accuracy (OA) and intersection over union (IoU) reaching 95.41% and 93.74% on the GF-2 dataset and 94.75% and 88.28% on the JL-1 dataset.

Utilizing deep learning techniques to extract high-precision features from point clouds is essential for accurately capturing land cover information, which is instrumental in urban planning and environmental conservation. Despite delivering high-accuracy outcomes in the semantic segmentation of extensive terrestrial point clouds, prevalent methodologies encounter considerable hurdles, particularly in training and inference duration, as well as the associated hardware expenses. To solve these issues, this paper introduces an efficient and lightweight deep learning network called Uniform Voxelization Geometric Enhancement and Local-Global Feature Fusion Network (VEF-Net). VEF-Net is designed to improve the training and inference efficiency of large-scale point cloud semantic segmentation while maintaining accuracy. Uniform voxel down-sampling is employed to discretize point clouds, resulting in a substantial enhancement in computational and memory performance. To counteract potential information loss due to voxel down-sampling, VEF-Net integrates a mechanism unit to enhance local geometric features, enriching point cloud data. Furthermore, it incorporates a Local-global feature fusion module, adeptly capturing the global contextual relationships within the point cloud. Experimental results show that VEF-Net achieved excellent performance on both the proprietary Bengbu dataset and the publicly available Toronto-3D dataset. VEF-Net maintained comparable segmentation accuracy to mainstream models while operating at a lower computational cost, and it demonstrated significant advantages in certain key tasks. On the Toronto3D dataset, VEF-Net achieved an IoU of 20.4% in the road marking category. Additionally, VEF-Net demonstrated lower model parameters and computational complexity (FLOPs), achieving training speeds 12 times faster and inference speeds 16.8 times faster than Point Transformer.

Rapid and accurate retrieval of vertical water vapor distributions is important for numerical weather forecasting, climate research, and disaster management. Traditional methods, such as radiosondes and microwave radiometers, often suffer from limited spatial and temporal resolution, high operational costs, and delayed data availability, leading to variable accuracy. The FY-4A meteorological satellite has introduced the Infrared Hyperspectral Atmospheric Vertical Sounder sensor to geostationary orbit for the first time, which offers significant advantages in terms of observational efficiency and cost compared to ground-based GNSS. This study employs a 1-D convolutional neural network (1D-CNN) to reconstruct specific humidity at 21 pressure levels, ranging from 1000 to 100 hPa. The 1D-CNN integrates two data sources: radiative data from 560 water vapor channels on FY-4A/geostationary interferometric infrared sounder (GIIRS) and ground-based GNSS-derived precipitable water vapor (GNSS-PWV) data. The combined use of FY-4A/GIIRS and GNSS-PWV data significantly improves the accuracy of water vapor vertical profile retrievals compared to radiosonde data from Hong Kong. Under clear-sky conditions, this combination achieves a root mean square error (RMSE) reduction of 25.64% overall, with a 30.68% reduction at heights from the surface to 600 hPa, as well as an average bias (BIAS) reduction of 32.98%, compared to retrievals using FY-4A/GIIRS data alone. Under cloudy conditions, the results showed an average reduction of 23.66% in RMSE and 50% in BIAS. The results demonstrate that integrating ground-based GNSS-derived PWV data can effectively increase the accuracy of FY-4A/GIIRS water vapor vertical profile retrieval.

Multispectral information is crucial for remote sensing crop monitoring, but current methods struggle with inadequate feature extraction, leading to poor generalization and incomplete segmentation. The segment anything model (SAM) shows significant potential for generalization across fields, offering a promising solution for crop monitoring. This article introduces a crop segmentation method based on SAM using multistage adaptation fine-tuning, namely MAF-SAM, effectively utilizing information from multispectral remote sensing and the transfer and generalization abilities of SAM. In its first stage, MAF-SAM employs a prefix adapter to extract primary low-level multispectral features and compresses them into three channels to meet the requirements of subsequent stages. The second stage introduces a low-rank adaptation (LoRA) fine-tuning strategy to inject crop-specific knowledge into the image encoder, enhancing MAF-SAM’s adaptability in particular crop segmentation tasks. In the third stage, it utilizes a mask decoder with no-prompt embedding to automatically generate masks with accurate class information. MAF-SAM achieves F1 scores and Intersection over Union (IoU) for soybean and corn of 0.9294, 0.8680, 0.8760, and 0.7723, respectively, along with a Kappa coefficient of 0.9543. It demonstrates superior temporal and spatial transfer capabilities relative to five other advanced segmentation methods in our study area.

Super-resolution mapping (SRM) is an effective way to alleviate the mixed pixel problem of remotely sensed imagery, by transforming the coarse-resolution fraction image originated from spectral unmixing into a fine-resolution land-cover map. Deep learning has been widely used in SRM since it has a powerful ability to represent the complex heterogeneous spatial distribution patterns of land-cover patches. However, the accuracy of existing deep learning-based SRM models is compromised by the fact that the fraction images used in SRM always contain errors. In this paper, we propose an end-to-end convolutional neural network (CNN)-based fraction error eliminating SRM (DeepNESRM) method to overcome the negative effect of fraction errors in SRM. In DeepNESRM, to better learn the complex nonlinear relationship between the actual coarse-resolution fraction image and the fine-resolution land-cover map by the CNN, a practical error simulation method that considers the characteristics of fraction errors is introduced to produce training samples. In addition, a multi-level feature fusion CNN is adopted to eliminate fraction errors and simultaneously implement SRM. Experiments using Sentinel-2 and Landsat 8 images were conducted to test the performance of the proposed method. Two conventional SRM methods, namely the pixel swapping method and the spatial dependence and L2 norm combined SRM (L2_SRM) method, and also a stacked very deep CNN based SRM (VDSRM) method, were used as the comparison methods. The results show that DeepNESRM can deal with fraction errors and preserve the spatial detail information, and achieve higher average overall accuracies than the other methods.

This letter proposes a trilateral filtering algorithm for speckle reduction in video synthetic aperture radar (video SAR). The novel filter takes traditional bilateral filter as the basic framework, so as to fully exploit the similarities of gray levels and the spatial location of neighboring pixels. Moreover, the proposed trilateral filter additionally exploits the temporal correlation information among adjacent image frames of the SAR videos and effectively reduces the interference of redundant information by using an adaptive similar frame selection technology. Comprehensively considering the three-dimensional correlation information of spatial, temporal, and gray-scale, a triple-similarity kernel is specifically developed for video-SAR de-speckling. The proposed trilateral filter can effectively smooth the speckle noise while greatly sustain the details of each image frame of the SAR videos. Experiments show that the proposed algorithm has better de-speckling performance compared with other algorithms.

In order to more efficiently mine the features of polarimetric synthetic aperture radar (PolSAR) and establish a more appropriate classification model, this article proposes an improved convolutional autoencoder (ICAE) based on texture feature fusion (TFF-ICAE) for PolSAR terrain classification. First, TFF-ICAE specifically designs a multi-indicator squeeze-and-excitation (MI-SE) block and incorporates it into the CAE network. MI-SE can enhance the essential feature information while suppressing the interference information as much as possible, and it can effectively increase the between-class distance while reducing the within-class distance. Then, TFF-ICAE uses gray level co-occurrence matrix (GLCM) to capture the texture features, and it optimally fuses these texture features and the deep features extracted by ICAE to complete the multilevel feature fusion, elevating the feature representation completeness of the terrain. That is, TFF-ICAE effectively enhances the feature separation capability of different categories while greatly elevating the feature representation completeness. Experiments on the datasets of San Francisco, Oberpfaffenhofen, and Flevoland show that the proposed TFF-ICAE, respectively, achieves overall accuracies of 93.44%, 97.61%, and 97.78%, which are at least 0.92%, 1.52%, and 0.97% higher than other algorithms. Undoubtedly, the superiority of TFF-ICAE is verified on these datasets.

Due to the tradeoff between spatial and temporal resolutions commonly encountered in remote sensing, no single satellite sensor can provide fine spatial resolution land surface temperature (LST) products with frequent coverage. This situation greatly limits applications that require LST data with fine spatiotemporal resolution. Here, a deep learning-based spatiotemporal temperature fusion network (STTFN) method for the generation of fine spatiotemporal resolution LST products is proposed. In STTFN, a multiscale fusion convolutional neural network is employed to build the complex nonlinear relationship between input and output LSTs. Thus, unlike other LST spatiotemporal fusion approaches, STTFN is able to form the potentially complicated relationships through the use of training data without manually designed mathematical rules making it is more flexible and intelligent than other methods. In addition, two target fine spatial resolution LST images are predicted and then integrated by a spatiotemporal-consistency (STC)-weighting function to take advantage of STC of LST data. A set of analyses using two real LST data sets obtained from Landsat and moderate resolution imaging spectroradiometer (MODIS) were undertaken to evaluate the ability of STTFN to generate fine spatiotemporal resolution LST products. The results show that, compared with three classic fusion methods [the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM), the spatiotemporal integrated temperature fusion model (STITFM), and the two-stream convolutional neural network for spatiotemporal image fusion (StfNet)], the proposed network produced the most accurate outputs [average root mean square error (RMSE)0.971].

Lake are sensitive to both climate change and human activities, and therefore serves as an excellent indicator of environmental changes. Based on series Landsat images, this paper provides a first picture of the annual variations in area of nine plateau lakes in Yunnan province, China using the Modified Normalized Difference Water Index (MNDWI) and Object-based image analysis (OBIA) method. A spatiotemporal analysis had carried out for these lakes. The results showed that water area annual variations of nine plateau lakes are inferenced by both climate change and human activities in different degrees. For Qilu and Yilong Lakes, the human activities paly more important role.