Band selection is an effective method to reduce the dimensionality of hyperspectral images (HSIs). However, most existing band selection methods usually consider each band as an overall feature and neglect to analyze the intrinsic discriminative components of each band. Worse still, these methods also assume that the spatial features of bands in HSIs are distributed only in Euclidean or non-Euclidean space, which may lead to the limited discriminability of the selected bands. To address these problems, a novel multi-granularity manifold hybrid adaptive near-neighbor preserved (MMANP) clustering method is proposed for band selection. Specifically, we first transform the problem of analyzing the intrinsic discriminative components of bands into a feature decoupling problem and propose a fine-grained manifold collaborative (FGMC) feature decoupling model, which can obtain spatially discriminative features and important features with the fine-grained manifold structures in each band. Then, the hybrid adaptive local neighborhood (HALN) block clustering model is proposed to interact with the spatial effective information of the obtained fine-grained important features of each band in the Euclidean and non-Euclidean spaces, which helps to improve the HSI’s adaptive clustering of similar bands. Next, multi-view cross-granularity learning (MVCL) feature selection model is proposed to harmoniously integrate information at different levels of granularity in HSIs into a unified framework to perform adaptive band selection for each cluster from the perspectives of both the different subsets and the whole HSI. Extensive experimental results on four datasets demonstrate that MMANP outperforms other state-of-the-art comparative methods.

As urbanization accelerates, more and taller buildings and less greenery are closely related to changes in the urban thermal environment (UTE). Knowledge of spatial and temporal variations of UTE is becoming increasingly concerning, and this can be measured with the land surface temperature (LST). Satellite observation of LST is an important tool for monitoring; the strong thermal anisotropy limits the use of satellite thermal infrared (TIR) data. Hitherto, the poor investigation was focused on the modeling and analysis of urban thermal anisotropy (UTA), especially in mountainous urban areas with multi-slope environments. These areas exhibit a distinctive “roof effect”, which is defined as the radiative transfer effect between the roof and the adjacent wall due to the slope that results in different heights between the roofs; multiple scattering has also been changed. Although an analytical thermal anisotropy model for the urban canopy over sloping terrain (AU3SM) has been proposed, its inability to effectively account for roof effects and multi-scattering mechanisms limits its daytime TIR observation applicability. To address these limitations, we developed an enhanced AU3SM that considers the roof effect and multiple scattering, which is labeled AU3SM-RS. The model was evaluated using measurements based on unmanned aerial vehicles (UAVs) in the mountainous city of Chongqing, China, with values of the root mean square error (RMSE) and coefficient of determination (R2) of 0.83 K and 0.93 in UTA. Comparison with a graphic processing unit-based solution for the faster 3-D radiative transfer model (GRay) further validates the model’s reliability with RMSE and R2values of 0.12 K and 0.96, respectively. Simulations in a certain scenario reveal that as the slope increases, the roof effect increases and the multiple scattering effect decreases in UTA and brightness temperature (BT), ignoring the roof effect and multiple scattering can result in maximum UTA biases of approximately 0.54, 0.48, and 0.72 K, BT biases approximately 1.02, 1.62, and 2.4 K at 5°, 15°, and 30° slopes, the biases due to neglecting the second scattering are very slight compared to the first scattering. Under certain conditions with a slope of 10°, the wider roof and narrower roadway, a related more dramatic roof effect; the narrower and deeper street canyon, a related more dramatic scattering effect. The proposed model is an efficient computational tool to assess UTA in mountainous areas quickly.

Accurate and complete extraction of buildings from very high-resolution (VHR) remote sensing (RS) images is highly important for urban planning and land management. However, owing to the limited information available for small buildings and building boundaries, as well as challenges such as the spectral similarity of ground objects, tree occlusions, and shadow interference, automatically extracting buildings from VHR images remains challenging. These issues may result in building extraction errors such as misclassification, small building omissions, blurred boundaries, and incorrect segmentation. To address these challenges, we propose a multiscale hybrid transformer (MSHFormer) with boundary enhancement. This approach incorporates a hybrid encoder that combines a multiscale local perception (MSLP) module and a global perception module (GPM), combining the strengths of convolutional neural networks (CNNs) and transformers to achieve efficient synergy between global modeling and local feature extraction. In addition, we developed an edge enhancement module (EHM) to enhance boundary information, significantly improving building boundary segmentation accuracy. Finally, we design a group alignment feature fusion module (GAFFM) to efficiently integrate low-level features from the encoder with high-level features from the decoder, reducing feature space misalignment. The experimental results on three public datasets demonstrate the effectiveness of MSHFormer. Specifically, the proposed method achieves intersection-over-union (IoU) values of 89.1%, 73.6%, and 89.5% on the Potsdam, Massachusetts, and WHU datasets, respectively.

Traditional deep semantic segmentation methods rely heavily on large-scale, densely labeled data, which is costly and time-consuming to obtain. Semi-supervised frameworks have emerged as a promising alternative, reducing the dependency on pixel-level annotations while enhancing segmentation performance. However, these methods still face challenges in data augmentation and class imbalance. For instance, traditional augmentation techniques such as CutMix are limited by their reliance on single random local contexts, which restricts perturbation strength and hinders model generalization. Moreover, the long-tailed class distribution in remote sensing (RS) images is often overlooked, leading to pseudo-labels that are biased toward majority classes, further exacerbating class imbalance. To address these challenges,we propose a novel semi-supervised framework for RS semantic segmentation, named APRW, which incorporates adaptive patch augmentation and class rank weighting. The adaptive patch augmentation module dynamically generates adaptive patch masks by comparing the predictions of weakly and strongly augmented inputs. These masks focus on high-confidence regions while preserving diverse boundary structures, effectively expanding the perturbation space and enhancing the model’s adaptability to varied inputs. The class rank weighting module maintains memory banks for both labeled and unlabeled data, dynamically calculates class weights based on the relative ranking of pixel confidences, and adaptively fuses these weights. This design mitigates biases caused by long-tailed distributions, improves the segmentation of rare classes, and enhances overall segmentation accuracy. Extensive experiments demonstrate that our method consistently outperforms existing approaches across multiple RS datasets, including DFC22, iSAID, MER, MSL, Vaihingen, and GID-15, showcasing superior generalization and higher segmentation precision. Implementation is released at https://github.com/135az/APRW.

Land surface temperature (LST) is an important parameter in many research fields. As a temperature characteristic, thermal radiation has an obvious directionality. In urban areas, the directional anisotropy (DA) in surface temperatures can reach 10 K during airborne measurements, limiting the applicability of urban surface temperature products. Notably, the intricate 3-D structures and heterogeneous temperature distributions in urban environments significantly influence this anisotropy. In recent decades, numerous models have been developed for urban thermal anisotropy (UTA) analysis; however, most of these models predominantly focus on horizontal surfaces, with little consideration of mountainous architectures. To balance the calculation efficiency and model complexity, this study introduces an analytical thermal anisotropy model applicable to urban areas. This model considers the effects of 3-D structures and slopes and is labeled as the AU3SM. The multiangle data used for the analysis are recorded by an unmanned aerial vehicle (UAV) with a multicircle observation scheme in Chongqing, China. Comparisons of the AU3SM simulated data with these measurement data yield root mean square error (RMSE) and coefficient of determination ($R^{2}$) values of 0.57 K and 0.89, respectively. Furthermore, similar comparisons with the discrete anisotropic radiative transfer (DART) model yield$R^{2}$and RMSE values of 0.98 and 0.12 K, respectively. Simulations reveal that slope influences the UTA, and the hotspot lies on the opposite side of the solar direction; ignoring slope values of 5°, 10°, 15°, and 25° results in UTA maximum biases of approximately 1.2, 3.5, 7, and 7.5 K, respectively, under certain conditions. These findings demonstrate that the proposed model can accomplish rapid UTA assessments in mountainous areas.

Tradeoffs between the spatial and temporal resolutions of current satellite instruments limit our ability to conduct high-quality and continuous monitoring of the earth’s surface dynamics. Spatiotemporal image fusion has become increasingly necessary to obtain remote sensing images with high spatiotemporal resolution. However, current learning-based methods concentrate on predicting images only from spatial similarity and neglect spectral correlations of remote sensing images, leading to significant spectral information loss. In this article, we develop a novel nonlocal tensor sparse representation-based semicoupled dictionary learning approach (SCDNTSR) for spatiotemporal fusion. In the SCDNTSR method, the spectral correlation and the spatial similarity of the nonlocal similar cubes are simultaneously exploited through the tensor–tensor product-based tensor sparse representation. Furthermore, the semicoupled mapping prior knowledge of sparse coefficients across the high- and low-spatial resolution (HSR\LSR) image spaces is exploited with the coupled dictionary to constrain the similarity of sparse coefficients to improve the prediction performance. In addition, to capture additional prior spatial information, the SCDNTSR provides a new method to determine the degradation relationship between the target HSR and LSR difference images with the help of the known HSR and LSR difference images. The proposed SCDNTSR method was tested on real datasets at both the Coleambally Irrigation Area study site and the Lower Gwydir Catchment study site. Results show that the proposed method outperforms five state-of-the-art methods, especially in maintaining the spectral information, proving the feasibility of integrating the degradation relationship, spatio-spectral-nonlocal correlation, and semicoupled mapping priors of the multisource data into the proposed model.

In recent years, leaps and bounds have developed spatiotemporal fusion (STF) methods for remote sensing (RS) images based on deep learning. However, most existing methods utilize 2D convolution (Conv) to explore features. 3D Conv can explore time-dimensional features, but it requires more memory footprint and is rarely used. In addition, the current STF methods based on convolutional neural networks (CNNs) are mainly the following two: 1) Use 2D Conv to extract features from multiple bands of the input image together and fuse the features to predict the multiband image directly; 2) Use 2D Conv to extract features from individual bands of the image, predict the reflectance data of individual bands, and finally stack the predicted individual bands directly to synthesize the multiband image. The former method does not sufficiently consider the spectral and reflectance differences between different bands, and the latter does not consider the similarity of spatial structures between adjacent bands and the spectral correlation. To solve these problems, we propose a 2D/3D hybrid convolution neural network (CNN) called HCNNet, in which the 2D-CNN branch extracts the spatial information features of single-band image, and the 3D-CNN branch extracts spatiotemporal features of single-band images. After fusing the features of the dual branches, we introduce neighboring band features to share spatial information so that the information is complementary to obtain single-band features and images, and finally stack each single-band image to generate multiband images. Visual assessment and metric evaluation of the three publicly available datasets showed that our method predicted better images compared to the five methods.

With the advent of a large number of remote sensing images (RSIs), scene classification of RSI is widely applied to many fields such as urban planning, natural disaster detection, and environmental monitoring. Compared with the natural image field, the lack of labeled RSI is a bottleneck of supervised scene classification methods based on deep learning. Meanwhile, unsupervised scene classification is difficult to meet actual needs. To this end, we propose a novel semisupervised scene classification method for RSI using generative adversarial nets (GANs), in which a gating unit, a self-attention gating (SAG) module, and a pretrained Inception V3 branch are introduced into discriminative network to enhance the feature representation capability for facilitating semisupervised classification. To be specific, the gating unit aims to learn the weights of each feature map and capture the dependence relationship between features. The SAG module aims to capture a long-range dependence for adaptively focusing on important scene regions. The Inception V3 branch aims to extract the high-level semantic representation of input images and further enhance the discriminant ability by gating unit and SAG module. Furthermore, a new optimization term is incorporated into the generator loss to indirectly drive discriminator to correctly classify scene images. To verify the effectiveness of the proposed method, extensive experimental results on UC Merced and EuroSAT data sets demonstrate that the method surpasses most of the state-of-the-art semisupervised image classification methods significantly, especially when only few samples are tagged.

Traditional radio monitoring and management largely depend on radio spectrum data analysis, which requires considerable domain experience and heavy cognition effort and frequently results in incorrect signal judgment and incomprehensive situation awareness. Faced with increasingly complicated electromagnetic environments, radio supervisors urgently need additional data sources and advanced analytical technologies to enhance their situation awareness ability. This paper introduces a visual analytics approach for electromagnetic situation awareness. Guided by a detailed scenario and requirement analysis, we first propose a signal clustering method to process radio signal data and a situation assessment model to obtain qualitative and quantitative descriptions of the electromagnetic situations. We then design a two-module interface with a set of visualization views and interactions to help radio supervisors perceive and understand the electromagnetic situations by a joint analysis of radio signal data and radio spectrum data. Evaluations on real-world data sets and an interview with actual users demonstrate the effectiveness of our prototype system. Finally, we discuss the limitations of the proposed approach and provide future work directions.

The fine spatial resolution (~100 m) land surface temperature (LST) is a key variable of great concern in various environmental studies over urban heterogeneous regions. An improvement in the spatial resolution of the coarse spatial resolution LST is an effective way to extend its potential uses in applications that have strict requests on both the spatial and temporal resolutions. However, previous statistical downscaling algorithms were proposed mainly by addressing the spatial variability in the LST while neglecting the temporal variability. In this paper, we propose a new algorithm based on a geographically and temporally weighted regression (GTWR) model for spatial downscaling of the Moderate Resolution Imaging Spectroradiometer LST data from 1000 to 100 m. The GTWR-based algorithm with temporally and geographically varying regression coefficients can capture both the spatial and temporal variabilities in the LST from the time series data at a coarse spatial resolution for effectively reconstructing the subpixel variability in the LST at fine spatial resolution. In addition, because of a better ability to explain the LST variability over urban heterogeneous regions, a normalized difference built-up index and a digital elevation model were selected as auxiliary variables. Taking Beijing and Lanzhou as examples, the performance of the GTWR-based algorithm was assessed by comparing the results with the TsHARP and GWR-based algorithms and the Landsat-8 LST. The results indicate that the GTWR-based algorithm outperforms the above-mentioned algorithms with lower mean root mean square error (1.62 °C) and mean absolute error (1.28 °C) and better agreement between the GTWR downscaled LST and the Landsat-8 LST.

Fuzzy clustering analysis is an effective method to describe the uncertainty relationship between data objects and clusters. However, fuzzy clustering results will become complex and high-dimensional membership degree matrixes when they contain a large number of data points and multiple clusters. In this paper, we propose a Radviz-based interactive visualization to help users understand fuzzy clustering results. Firstly, we utilize the projection mechanism of Radviz to map the membership degree matrixes onto planar and radial pictures, in which data points with low membership uncertainty are located near Radviz circumference, while the others are scattered in the center of Radviz circle. To provide an informative interactive visualization, we then improve traditional Radviz visualization in many aspects, including implementing an optimal and uneven placement of dimension anchors by using the Prim algorithm, designing visual codings of data points and dimension arcs to express statistical information, combining chord diagram to depict the sharing relationship between clusters, and offering a set of interactions to support deeper exploration. Finally, we use a case study to illustrate the effectiveness and usefulness of our visualization.

High accuracy classification results are very important for quantitative remote sensing research and the effect of remote sensing application. There are a variety of free global classification products available currently. However these products are mostly developed by foreign research institutions and personnel, and there is no adequate research on the complex terrain , vegetation structure differences and crop planting structure differences in China, which caused low classification accuracy in China, especially the classification accuracy of vegetation types. Therefor, it is necessary to develop a classification production of vegetation types in China. In this paper, we developed a classification method for vegetation types in China based on existing vegetation zoning. And we complete the 2012 national land cover classification using the method. The classification results are evaluated by the method of stratified random sampling, and the overall accuracy and Kappa coefficient are found to be greatly improved.