Speckle reduction is a longstanding topic in synthetic aperture radar (SAR) images. Many different schemes have been proposed for the restoration of intensity SAR images. Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. CNN training requires good training data: many pairs of speckle-free/speckle-corrupted images. This is an issue in SAR applications, given the inherent scarcity of speckle-free images. To handle this problem, this paper analyzes different strategies one can adopt, depending on the speckle removal task one wishes to perform and the availability of multitemporal stacks of SAR data. The first strategy applies a CNN model, trained to remove additive white Gaussian noise from natural images, to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channel LOgarithm with Gaussian denoising). No training on SAR images is performed, the network is readily applied to speckle reduction tasks. The second strategy considers a novel approach to construct a reliable dataset of speckle-free SAR images necessary to train a CNN model. Finally, a hybrid approach is also analyzed: the CNN used to remove additive white Gaussian noise is trained on speckle-free SAR images. The proposed methods are compared to other state-of-the-art speckle removal filters, to evaluate the quality of denoising and to discuss the pros and cons of the different strategies. Along with the paper, we make available the weights of the trained network to allow its usage by other researchers.

Unsupervised classification plays an important role in understanding polarimetric synthetic aperture radar (PolSAR) images. One of the typical representations of PolSAR data is in the form of Hermitian positive definite (HPD) covariance matrices. Most algorithms for unsupervised classification using this representation either use statistical distribution models or adopt polarimetric target decompositions. In this paper, we propose an unsupervised classification method by introducing a sparsity-based similarity measure on HPD matrices. Specifically, we first use a novel Riemannian sparse coding scheme for representing each HPD covariance matrix as sparse linear combinations of other HPD matrices, where the sparse reconstruction loss is defined by the Riemannian geodesic distance between HPD matrices. The coefficient vectors generated by this step reflect the neighborhood structure of HPD matrices embedded in the Euclidean space and hence can be used to define a similarity measure. We apply the scheme for PolSAR data, in which we first oversegment the images into superpixels, followed by representing each superpixel by an HPD matrix. These HPD matrices are then sparse coded, and the resulting sparse coefficient vectors are then clustered by spectral clustering using the neighborhood matrix generated by our similarity measure. The experimental results on different fully PolSAR images demonstrate the superior performance of the proposed classification approach against the state-of-the-art approaches.

The covariance/coherence matrices are the most common way of representing polarimetric information in the polarimetric synthetic aperture radar (PolSAR) data and have been extensively used in PolSAR classification. Since PolSAR covariance and coherence matrices are Hermitian positive-definite, they form a nonlinear manifold, rather than Euclidean space. Though the geodesic distance measures defined on a manifold are suitable for describing similarities of PolSAR matrix data, the nonlinearity of the manifold often makes the involved optimization problems awkward. To address this problem, we propose to embed the manifold-based PolSAR data into a high (infinite)-dimensional reproducing kernel Hilbert space by Stein kernel and log-Euclidean kernel. Besides, we introduce the composite kernel into the sparse representation classification in order to exploit the spatial context information of PolSAR data. The proposed method is assessed using different PolSAR datasets. Experimental results demonstrate the superior performance compared with the methods without the use of contextual information.

The main aim of this study was to utilize remote sensing data to establish regression models through machine learning to predict locust density in the upcoming year. First, a dataset for monitoring grassland locust density was constructed based on meteorological data and multi-source remote sensing data in the study area. Subsequently, an SVR (support vector regression) model, BP neural network regression model, random forest regression model, BP neural network regression model with the PCA (principal component analysis), and deep belief network regression model were built on the dataset. The experimental results show that the random forest regression model had the best prediction performance among the five models. Specifically, the model achieved a coefficient of determination (R²) of 0.9685 and a root mean square error (RMSE) of 1.0144 on the test set, which were the optimal values achieved among all the models tested. Finally, the locust density in the study area for 2023 was predicted and, by comparing the predicted results with actual measured data, it was found that the prediction accuracy was high. This is of great significance for local grassland ecological management, disaster warning, scientific decision-making support, scientific research progress, and sustainable agricultural development.

As one of the important lakes in the “One Lake and Two Seas” of the Inner Mongolia Autonomous Region, the monitoring of water quality in Lake Daihai has attracted increasing attention, and the concentration of chlorophyll-a directly affects the water quality, making the monitoring of chlorophyll-a concentration in Lake Daihai particularly crucial. Traditional methods of monitoring chlorophyll-a concentration are not only inefficient but also require significant human and material resources. Remote sensing technology has the advantages of wide coverage and short update cycles. For lakes such as Daihai with a high salinity content, salinity is considered a key factor when inverting the concentration of chlorophyll-a. In this study, machine learning models, including model stacking from ensemble learning, a ridge regression model, and a random forest model, were constructed. After comparing the training accuracy of the three models on Zhuhai-1 satellite data, the random forest model, which had the highest accuracy, was selected as the final training model. By comparing the accuracy changes before and after adding salinity factors to the random forest model, a high-precision model for inverting chlorophyll-a concentration in hypersaline lakes was obtained. The research results show that, without considering the salinity factor, the root mean square error (RMSE) of the model was 0.056, and the coefficient of determination (R²) was 0.64, indicating moderate model performance. After adding the salinity factor, the model accuracy significantly improved: the RMSE decreased to 0.047, and the R² increased to 0.92. This study provides a solid basis for the application of remote sensing technology in hypersaline aquatic environments, confirming the importance of considering salinity when estimating chlorophyll-a concentration in hypersaline waters. This research helps us gain a deeper understanding of the water quality and ecosystem evolution in Daihai Lake.

Change detection is an important application of remote sensing image interpretation, which identifies changed areas of interest from a pair of bi-temporal remote sensing images. Various deep-learning-based approaches have demonstrated promising results and most of these models used an encoder–decoder shape such as U-Net for segmentation of changed areas. In order to obtain more refined features, this paper introduces a change detection model with cascaded U-Net. The proposed network architecture contains four cascaded U-Nets with ConvNeXT blocks. With a patch embedding layer, the cascaded structure can improve detection results with acceptable computational overhead. To facilitate the training of the cascaded N-Nets, we proposed a novel attention mechanism called the Training whEel Attention Module (TEAM). During the training phase, TEAM aggregates outputs from different stages of cascaded structures and shifts attention from outputs from shallow stages to outputs from deeper stages. The experimental results show that our cascaded U-Net architecture with TEAM achieves state-of-the-art performance in two change detection datasets without extra training data.