Accurate Local Climate Zone (LCZ) classification is essential for urban climate studies, environmental monitoring, and sustainable city planning. Recent advances in Deep Learning (DL) have significantly improved LCZ mapping, but challenges remain in capturing spatial position features and distinguishing spectrally similar land cover types. This letter proposes multi-scale Coordinate Attention-based Multi-Stream Local Climate Zone Network (MSCA-MSLCZNet), a multi-stream DL framework integrating multi-scale feature processing, attention mechanisms, and rule-based refinement to enhance LCZ classification performance. The model is evaluated on the So2Sat LCZ42 dataset, outperforming baseline methods in overall accuracy (OA), OA of built-up classes (OAbu), OA of natural classes (OAn), and Kappa. Further validation on Milan LCZ mapping confirms its generalization capability, demonstrating strong classification performance in built-up areas and improved urban structure delineation. Comparative experiments highlight the model’s ability to better differentiate urban structures and built-up zones from natural landscapes. MSCA-MSLCZNet proves effective for large-scale LCZ mapping, offering improved classification accuracy and adaptability to diverse geographic regions.

Panax notoginseng is a widely recognized medicinal herb in Chinese traditional medicine. Investigating the cultivation of P. notoginseng is crucial for ecological preservation and effective land management. In our study, we conducted an analysis of the spectral properties of P. notoginseng plantations along with various other land cover types. As a result, we have introduced a novel index called the signed normalized range index (SNRI), based on the maximum and minimum reflectance values across all bands of the multispectral imagery. Through experiments conducted on Landsat-8 operational land imager (OLI) images obtained from Yunnan, China, we performed quantitative assessments of separability measurements. SNRI has shown great potential in enhancing the identification of P. notoginseng, with an average Jeffries–Matusita (J–M) separability of 1.378 compared with other land covers. Furthermore, we conducted a comparative analysis of the support vector machine (SVM) classification results using several spectral indices for dark target extraction. The comparison affirmed the superior performance of SNRI in accurately distinguishing P. notoginseng plantations from other land cover types. It is promising to explore the application of SNRI in remote sensing estimation and change monitoring of the P. notoginseng planting area, as well as other land covers with similar lower reflectance ranges.

As the basic and essential component of most object detectors, a feature pyramid network (FPN) can effectively extract multiscale features to recognize objects at different scales. Nevertheless, due to the cross-scale fusion and upsampling operations in FPN, current detectors still suffer from information loss and feature misalignment. To alleviate these problems, a flow-guided upsampling module (FGUM) and a multifeature attention module (MFAM) are proposed to improve the FPN. Specifically, FGUM uses a novel flow warp in the upsampling operation to align features, resulting in better cross-scale fusion. At the same time, the MFAM module fully considers the integrity of multiscale features and reduces the aliasing effect by optimizing the weight of each level of features. To verify the effectiveness of the improved FPN, it is applied to three state-of-the-art models for experiments, and all of them achieve better detection accuracy compared to the original FPN.

Remote sensing (RS) scene classification is challenging due to changes in the scale and direction of scenes within a category. Bilinear pooling method can extract higher-order and spatial orderless information and has been shown to achieve impressive performance on various visual tasks. However, bilinear pooled features are high dimensional, which makes them impractical for subsequent processing, especially for the convolutional neural network (CNN) models with more channels in the final convolutional layer. To alleviate this shortcoming, an improved bilinear pooling method is proposed to build the compact bilinear CNN model in this work. Specifically, a joint pooling method is proposed to reduce the high-dimensional bilinear features, and it can be embedded in a bilinear CNN architecture for end-to-end optimization. Through the experimental evaluation of three real RS scene image data sets, it is proved that the improved bilinear pooling method can obtain features with higher discriminative power than the bilinear pooling method but with lower dimensionality. In addition, it also reduces the running time of model training.

Deep convolutional networks have been the most competitive method in remote sensing scene classification. Due to the diversity and complexity of scene content, remote sensing scene classification still remains a challenging task. Recently, the second-order pooling method has attracted more interest because it can learn higher-order information and enhance the nonlinear modeling ability of the networks. However, how to effectively learn second-order features and establish the discriminative feature representation of holistic images is still an open question. In this letter, we propose a first and second-order information fusion network (FSoI-Net) that can learn the first-order and second-order features at the same time, and construct the final feature representation by fusing the two types of features. Specifically, a self-attention-based second-order pooling (SaSoP) method based on covariance matrix is proposed to extract second-order features, and a fusion loss function is developed to jointly train the model and construct the final feature representation for the classification decision. The proposed network has been thoroughly evaluated on three real remote sensing scene datasets and achieved better performance than the counterparts.

In this letter, CatBoost was first introduced and investigated for remote sensing (RS) image classification using diverse features. To improve the classification performance by fostering the effective and efficient spatial feature extraction, a new pseudo label features (PLFs) extraction method was proposed via multisize neighboring patches-based multiclustering. Experimental results on two hyperspectral and one PolSAR benchmarks showed that: 1) CatBoost is an advanced ensemble learning (EL) algorithm for classification of RS images using diverse features; 2) CatBoost has better capability of reducing the overfitting issue at large number of boosting iteration; and 3) proposed PLFs can result in compatible and even better classification results than using morphological profiles (MPs) and MPs with partial reconstruction (MPPR) spatial features.

Sand and dust storms (SDS) are both symptoms and causes of desertification. As one of the essential parts of desertification control, SDS source identification can be readily carried out using remote sensing data. This letter proposes an automatic SDS source identification method based on ERA5 surface wind direction and MODIS daily surface reflectance. This is also the first time Google Earth Engine (GEE) has been used to fully automate SDS source mapping, from spatial data processing to results visualization. In this study, we use the zero-crossing edge detection algorithm to extract the dust plume edge based on the Enhanced Dust index (EDI), and then trace the point sources through the upwind direction. We evaluate the model performance based on 12 SDS events in Arid Central Asia (ACA) and validate against manually labeled SDS point sources. The results showed that the mean accuracy of SDS sources estimation was greater than 67%. To demonstrate the geographic scalability of the method, we also investigate the spatial pattern of SDS point sources in ACA from 2000 to 2021. Last, we adopt land cover data to discuss its applicability in time-series studies. Experimental results have demonstrated that our proposed method has the ability to identify SDS source points accurately and efficiently. We anticipate that this method will play an essential role in dust risk assessment and desertification control.

With the increasing availability and resolution of satellite sensor data, multispectral (MS) and panchromatic (PAN) images are the most popular data that are used in remote sensing among applications. This article proposes a novel cross-resolution hidden layer feature fusion (CRHFF) approach for joint classification of multiresolution MS and PAN images. In particular, shallow spectral and spatial features at a global scale are first extracted from an MS image. Then, deep cross-resolution hidden layer features extracted from MS and PAN are fused from patches at a local scale according to an autoencoder (AE)-like deep network. Finally, the selected multiresolution hidden layer features are classified in a supervised manner. By taking advantage of integrated shallow-to-deep and global-to-local features from the high-resolution MS and PAN images, the cross-resolution latent information can be extracted and fused in order to better model imaged objects from the multimodal representation and finally increase the classification accuracy. Experimental results obtained on three real multiresolution datasets covering complex urban scenarios confirm the effectiveness of the proposed approach in terms of higher accuracy and robustness with respect to literature methods.

With more detailed spatial information being represented in very-high-resolution (VHR) remote sensing images, stringent requirements are imposed on accurate image classification. Due to the diverse land-objects with intraclass variation and interclass similarity, efficient and fine classification of VHR images especially in complex scenes is challenging. Even for some popular deep learning (DL) frameworks, geometric details of land-object may be lost in deep feature levels, so it is difficult to maintain the highly-detailed spatial information (e.g., edges, small objects) only relying on the last high-level layer. Moreover, many of the newly developed DL methods require massive well-labeled samples, which inevitably deteriorates the model generalization ability under the few-shot learning. Therefore, in this paper, a lightweight shallow-to-deep feature fusion network (SDF2N) is proposed for VHR image classification, where the traditional machine learning (ML) and DL schemes are integrated to learn rich and representative information to improve the classification accuracy. In particular, the shallow spectral-spatial features are first extracted, and then a novel triple-stage fusion (TSF) module is designed to learn the saliency and discriminative information at different levels for classification. The TSF module includes three feature fusion stages, i.e., low-level spectral-spatial feature fusion, middle-level multi-scale feature fusion, and high-level multi-layer feature fusion. The proposed SDF2N takes advantages of the shallow-to-deep features, which can extract representative and complementary information of crossing layers. It is important to note that even with limited training samples, the SDF2N still can achieve satisfying classification performance. Experimental results obtained on three real VHR remote sensing data sets including two multispectral and one airborne hyperspectral images covering complex urban scenarios confirm the effectiveness of the proposed approach compared with the state-of-the-art methods.

In active learning (AL)-based remote sensing (RS) image classification tasks, the acquisition of labeled data depends not only on the informativeness and representativeness measured in feature space but also on the spatial distributions and relations in an image plane. However, very few studies have investigated the advantages of integrating spatial constraints into the AL paradigm. Hence, under the basic assumption “instances that are difficult to classify are usually located around edges between different objects or land-cover types,” edge gradient information was integrated into the conventional AL paradigm using popular uncertainty and diversity measurements. The experimental results with two real hyperspectral images confirmed the advantages of the proposed edge gradient-based AL (EGAL) approach from the aspects of fast convergence and computationally efficient operation.

This paper presents a novel multiscale superpixel-guided filter (MSGF) approach for very high resolution (VHR) remote sensing image classification. Different from the traditional guided filter (GF) classification method, the proposed method utilizes a guidance image that constructed from the superpixel segmentation image, which is capable to provide more abundant and accurate edge information of land objects presented in the image. Multiscale features are extracted by the superpixel-guided filter in order to properly model the spatial information of these objects at different scales thus to improve the classification accuracy. Experimental results obtained on a real QuickBird VHR image of Zurich urban scene confirmed the effectiveness of the proposed method.

This paper focuses on solving the multi-class change detection problem in bitemporal multispectral remote sensing images. In that case, information that represented in a small number (e.g., two) of the original bands may be insufficient for the accurate identification of a few of multi-class changes. In particular, this problem becomes more difficult in unsupervised change detection cases when ground reference data is not available. In this paper, a solution is proposed by using the potential information represented in expanded features that constructed from the original spectral bands. Experimental results obtained on a real bitemporal remote sensing data set confirm the effectiveness of the proposed approach.

The possibility theory, which is an extension of fuzzy sets and fuzzy logic, has shown considerable potential for solving active learning (AL) problems, particularly for multiclass scenarios’ classification. Hence, two recently proposed fuzzy multiclass AL algorithms (classification ambiguity (CA) and fuzzy C‐order ambiguity (FCOA)) are investigated to properly generalise them for classifying hyperspectral images, and two improved versions of the CA and FCOA are proposed. In addition to comparing the performances of the original and improved algorithms, several other state‐of‐the‐art AL methods are evaluated, such as breaking ties, margin sampling, and multi‐class level uncertainty, with or without diversity criteria such as angle‐based diversity (ABD), clustering‐based diversity (CBD), and enhanced clustering‐based diversity (ECBD). Tests on two benchmark hyperspectral images confirm that the proposed improved algorithms are superior to and more effective than the original ones.

A novel spectral-spatial joint multiscale approach is developed to address the multi-class change detection problem in bitemporal multispectral remote sensing images. The proposed approach is based on a multiscale morphological compressed change vector analysis (M2C2VA), which extend the state-of-the-art spectrum-based compressed change vector analysis (C2VA) while preserving more geometrical details of change targets. In particular, spectral change features are reconstructed according to the morphological analysis which exploiting the interaction of a pixel with its adjacent regions. Two multiscale ensemble strategies are proposed to integrate the change information represented at multiple scales in order to enhance the CD performance. The proposed approach is designed in an unsupervised fashion thus can be implemented without using ground reference data. A pair of real bitemporal remote sensing images is used to test the proposed approach and the obtained experimental results confirm its effectiveness.

Oil spill monitoring in optical remote sensing (RS) images is a challenging task due to the complexity of target discrimination in an oil spill scenario. Differently from traditional oil spill detection methods that are mainly carried out in a monotemporal image, in this letter, a novel solution is given in a multitemporal domain by investigating potential capability of change detection (CD) techniques, and it mainly contributes to an unsupervised, semiautomatic, and efficient approach. It opens a new perspective for solving an oil spill detection problem. In particular, a coarse-to-fine multitemporal change analysis procedure is designed to investigate the spectral–temporal variation of change targets present in the scenario. Changes relevant and irrelevant to suspected oil spills are identified and discriminated according to a binary and a multiple CD process, respectively. The proposed approach provides a quick yet effective oil spill detection solution, which is valuable and important in practical applications. The proposed method was validated on two real multitemporal RS data sets presenting the oil spill event in northern Gulf of Mexico in 2010. Experimental results confirmed its effectiveness.

Scene classification from remote sensing images provides new possibilities for potential application of high spatial resolution imagery. How to efficiently implement scene recognition from high spatial resolution imagery remains a significant challenge in the remote sensing domain. Recently, convolutional neural networks (CNN) have attracted tremendous attention because of their excellent performance in different fields. However, most works focus on fully training a new deep CNN model for the target problems without considering the limited data and time-consuming issues. To alleviate the aforementioned drawbacks, some works have attempted to use the pretrained CNN models as feature extractors to build a feature representation of scene images for classification and achieved successful applications including remote sensing scene classification. However, existing works pay little attention to exploring the benefits of multilayer features for improving the scene classification in different aspects. As a matter of fact, the information hidden in different layers has great potential for improving feature discrimination capacity. Therefore, this paper presents a fusion strategy for integrating multilayer features of a pretrained CNN model for scene classification. Specifically, the pretrained CNN model is used as a feature extractor to extract deep features of different convolutional and fully connected layers; then, a multiscale improved Fisher kernel coding method is proposed to build a mid-level feature representation of convolutional deep features. Finally, the mid-level features extracted from convolutional layers and the features of fully connected layers are fused by a principal component analysis/spectral regression kernel discriminant analysis method for classification. For validation and comparison purposes, the proposed approach is evaluated via experiments with two challenging high-resolution remote sensing data sets, and shows the competitive performance compared with fully trained CNN models, fine-tuning CNN models, and other related works.

This paper develops a novel oil spill detection approach by using the multitemporal optical remote sensing images. Differently from the traditional oil spill detection methods that mainly carried out on a monotemporal image, the proposed approach opens a new perspective to solve the considered oil spill detection problem in a multitemporal domain by investigating the potential capability of change detection (CD) techniques. A coarse to fine multitemporal change analysis is defined to analyze the spectral-temporal variation of change targets that present in the oil spill scenario. Suspected oil spills and non-relevant changes are identified and discriminated according to a multiple-change detection in the proposed technique. The proposed approach provides a quick, yet effective oil spill detection solution in an unsupervised way, which is valuable and important in practical oil spill detection applications. Experimental results obtained on real HJ-1 satellite images presenting the oil spill event in northern Gulf of Mexico in 2010 confirmed the effectiveness of the proposed method.

Active learning (AL) methods that select unlabeled samples only querying by informative measures (i.e., uncertainty and/or diversity criteria) have been extensively investigated. However, these methods usually do not exploit the manifold structure of the unlabeled data from the geometrical point of view, a choice that might lead to a sample bias and consequently undesirable performances. To control and possibly overcome such drawbacks, this paper explores AL methods based on joint informative and manifold structure representative sampling (JI-MSRS). In JI-MSRS, a portion of the unlabeled samples that are added at each iteration is selected according to the informative measures, whereas another portion is selected according to their capability to represent the data cluster structure. Four popular manifold learning methods, namely, principle component analysis (PCA), linear discriminant analysis, kernel PCA, and neighborhood preserving embedding, are used to model the data structure. Then, Delaunay triangulation nets are used to build a discrete approximation of the geometrical structure of the unlabeled data cloud in a low-dimensional space. To show the effectiveness of this novel sampling strategy, results on three real multi-/hyperspectral data sets are presented, adding a thorough comparison with other state-of-the-art AL techniques. In comparison to conventional AL heuristics, the proposed techniques are able to obtain competitive or even better classification accuracy values.