Search

The optical remote sensing images not only have to make a fundamental tradeoff between the spatial and spectral resolutions, but also are inevitable to be polluted by the clouds; however, the existing pansharpening methods mainly focus on the resolution enhancement of the optical remote sensing images without cloud contamination. How to fuse the cloud-contaminated images to achieve the joint resolution enhancement and cloud removal is a promising and challenging work. In this paper, a pansharpening method for the challenging cloud-contaminated very high-resolution remote sensing images is proposed. Furthermore, the cloud-contaminated conditions for the practical observations with all the thick clouds, the thin clouds, the haze, and the cloud shadows are comprehensively considered. In the proposed methods, a two-step fusion framework based on multisource and multitemporal observations is presented: 1) the thin clouds, the haze, and the light cloud shadows are proposed to be first jointly removed and 2) a variational-based integrated fusion model is then proposed to achieve the joint resolution enhancement and missing information reconstruction for the thick clouds and dark cloud shadows. Through the proposed fusion method, a promising cloud-free fused image with both high spatial and high spectral resolutions can be obtained. To comprehensively test and verify the proposed method, the experiments were implemented based on both the cloud-free and cloud-contaminated images, and a number of different remote sensing satellites including the IKONOS, the QuickBird, the Jilin (JL)-1, and the Deimos-2 images were utilized. The experimental results confirm the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we revisit the pulse-to-pulse correlation properties of nadir-looking pulse-limited altimeters, with the objective of determining the effect of the partial correlation of radar echoes transmitted at much higher rate than the conventional pulse repetition frequency (PRF). This is particularly relevant for the Sentinel-6/Jason-CS mission. The pulse-to-pulse echo power autocorrelation shows much shorter decorrelation times toward the trailing edge of the waveform than those observed for range gates close to the leading edge. At high PRFs this creates a significant variability in the statistical properties of the range gates in the 20-Hz multilooked waveforms. By processing an extensive data set of CryoSat-2 Synthetic Aperture Radar mode data in a pseudo-low resolution mode fashion, we determined that despite the fact that at higher PRFs the noise in the estimation of geophysical parameters is reduced, significant sea-state-dependent biases are also introduced during the retracking process, which are particularly relevant for sea surface height and significant wave height. Those biases will need to be appropriately accounted for when integrating Sentinel-6/Jason-CS data in a climatological data record. [ABSTRACT FROM AUTHOR]

The electromagnetic scattering generated by agricultural tilled soils can be affected by a strong anisotropic component of the rough-surface profile. An accurate and reliable modeling of the normalized radar cross section, under both monostatic and bistatic geometries, is particularly important and desirable, especially for the correct estimation of the soil moisture content by means of satellite-based observations. In this paper, moving from the modeling so far proposed in the literature, we present and discuss a novel, more general (i.e., 2-D), spectral representation of an agricultural tilled soil, implementing a solution of the scattering based on the first-order small-slope approximation. Comparisons are given with a well-established model based on a 1-D representation of the soil correlation function, accounting for the radiation pattern of the illuminating antenna. The investigation gives new insight on the phenomenology of the bistatic scattering from the anisotropic soil, providing interesting information for the next generation of satellite missions, which foresees the possibility of launching companion satellites carrying aboard a passive receiver collecting the signal transmitted by active SAR-based platforms. [ABSTRACT FROM AUTHOR]

The accurate estimation of the terrestrial latent heat flux (LE) from satellite observations at high spatial and temporal scales plays an important role in the assessment of the water and heat exchange between the earth’s surface and the atmosphere. Although a variety of data fusion methods have been proposed to merge different LE products for more reliable estimates, most of them have ignored the spatiotemporal consistency of LE products across different resolutions. In this paper, we apply the multiresolution tree (MRT) method to improve the accuracy and reduce the inconsistency between the Moderate Resolution Imaging Spectroradiometer (MODIS) LE (MOD16) product and the Landsat-based LE product at different resolutions. Eddy covariance (EC) ground measurements at five sites, MODIS and Landsat images from January 2005 to December 2005 in the north central USA, are used to evaluate the performance of the MRT method. The results show that the MRT method can improve the accuracy of the original LE products (MOD16 and Landsat), and it has the potential to significantly reduce the uncertainty and inconsistency of these products. The bias decreased by 38.3% on average, and the root-mean-square error (RMSE) decreased by approximately 49.2% after the MRT was applied at each scale. Further studies are still required to make the MRT method more universal on a variety of land cover types for long-time periods. [ABSTRACT FROM AUTHOR]

In classifier (or regression) fusion, the aim is to combine the outputs of several algorithms to boost overall performance. Standard supervised fusion algorithms often require accurate and precise training labels. However, accurate labels may be difficult to obtain in many remote sensing applications. This paper proposes novel classification and regression fusion models that can be trained given ambiguously and imprecisely labeled training data in which the training labels are associated with sets of data points (i.e., “bags”) instead of individual data points (i.e., “instances”) following a multiple-instance learning framework. Experiments were conducted based on the proposed algorithms on both synthetic data and applications such as target detection and crop yield prediction given remote sensing data. The proposed algorithms show effective classification and regression performance. [ABSTRACT FROM AUTHOR]

Coherent imaging systems are greatly affected by speckle noise, which makes visual analysis and features extraction a difficult task. In this paper, we propose a speckle suppression algorithm based on weighted nuclear norm minimization (WNNM) and Grey theory. First, we use logarithmic transformation to the noisy images such that the speckle noise is transformed into additive noise. Second, by matching the local blocks based on Grey theory, we will get approximate low-rank matrices grouped by the similar blocks of the reference patches. We then estimate the noise variance of the noisy images with the wavelet transform. Finally, we use WNNM method to denoise the image. The results show that our algorithm not only effectively improves the visual effect of the denoised image and preserves the local structure of the image better but also improves the objective indexes values of the denoised image. [ABSTRACT FROM AUTHOR]

In multiclass classification, convolutional neural network (CNN) is generally coupled with the cross-entropy (CE) loss, which only penalizes the predicted probability corresponding to a ground truth class and ignores the interclass relationship. We argue that CNN can be improved by using a better loss function. On the other hand, the Wasserstein distance (WD) is a well-known metric used to measure the distance between two distributions. Directly solving the WD problem requires a prohibitively large amount of computation time, whereas the cheaper iterative algorithms have a variety of shortcomings such as computational instability and difficulty in selecting parameters. In this paper, we address these issues by giving an analytical solution to the WD problem—for the first time, we find that for two distributions in hierarchically organized data space, WD has a closed-form solution, which we call “hierarchical WD (HWD).” We use this theory to construct novel loss functions that overcome the shortcomings of CE loss. To this end, multi-CNN information fusion that provides the basis for building category hierarchies is carried out first. Then, the semantic relationship among classes is modeled as a binary tree. Then, CNN coupled with an HWD-based loss, i.e., hierarchical Wasserstein CNN (HW-CNN), is trained to learn deep features. In this way, prior knowledge about the interclass relationship is embedded into HW-CNN, and information from several CNNs provides guidance in the process of training individual HW-CNNs. We conducted extensive experiments over two publicly available remote sensing data sets and achieved a state-of-the-art performance in scene classification tasks. [ABSTRACT FROM AUTHOR]

Clustering of remote sensing imagery is a tough task due to the particular and complex structure of remote sensing images and the shortage of known information. In this paper, we propose a fully automatic spectral–spatial fuzzy clustering method using an adaptive multiobjective memetic algorithm (AMOMA) for multispectral remote sensing imagery. This approach is made up of two automatic layers: an automatic determination layer and an automatic clustering layer. The first layer seeks the optimal number of clusters through a self-adaptive differential evolution algorithm. The second layer then takes advantage of the AMOMA for spectral–spatial clustering using the optimal number of clusters. The knee point from the Pareto front is then selected through the angle-based method in every generation, and we then compare the knee points between generations to output the final optimal solution. The effectiveness of the proposed method is verified by the experimental results obtained with three remote sensing data sets. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing decomposes a hyperspectral imagery (HSI) into a number of constituent materials and associated proportions. Recently, nonnegative tensor factorization (NTF)-based methods have been proposed for hyperspectral unmixing thanks to their capability in representing an HSI without any information loss. However, tensor factorization-based HSI processing approaches often suffer from low-signal-to-noise ratio condition of HSI and nonuniqueness of the solution. This problem can be effectively alleviated by introducing various spatial constraints into tensor factorization to suppress the noise and decrease the number of extreme, stationary, and saddle points. On the other hand, total variation (TV) adaptively promotes piecewise smoothness while preserving edges. In this paper, we propose a TV regularized matrix–vector NTF method. It takes advantage of tensor factorization in preserving global spectral–spatial information and the merits of TV in exploiting local spatial information, thus generating smooth abundance maps with preserved edges. Experimental results on synthetic and real-world data show that the proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Aiming at improving the classification accuracy with limited numbers of labeled pixels in polarimetric synthetic aperture radar (PolSAR) image classification task, this paper presents a graph-based semisupervised deep learning model for PolSAR image classification. It models the PolSAR image as an undirected graph, where the nodes correspond to the labeled and unlabeled pixels, and the weighted edges represent similarities between the pixels. Upon the graph, we design an energy function incorporating a semisupervision term, a convolutional neural network (CNN) term, and a pairwise smoothness term. The employed CNN extracts abstract and data-driven polarimetric features and outputs class label predictions to the graph model. The semisupervision term enforces the category label constraints on the human-labeled pixels. The pairwise smoothness term encourages class label smoothness and the alignment of class label boundaries with the image edges. Starting from an initialized class label map generated based on $K$ -Wishart distribution hypothesis or superpixel segmentation of PauliRGB images, we iteratively and alternately optimize the defined energy function until it converges. We conducted experiments on two real benchmark PolSAR images, and extensive experiments demonstrated that our approach achieved the state-of-the-art results for PolSAR image classification. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new anomaly detection method for hyperspectral images based on two well-designed dictionaries: background dictionary and potential anomaly dictionary. In order to effectively detect an anomaly and eliminate the influence of noise, the original image is decomposed into three components: background, anomalies, and noise. In this way, the anomaly detection task is regarded as a problem of matrix decomposition. Considering the homogeneity of background and the sparsity of anomalies, the low-rank and sparse constraints are imposed in our model. Then, the background and potential anomaly dictionaries are constructed using the background and anomaly priors. For the background dictionary, a joint sparse representation (JSR)-based dictionary selection strategy is proposed, assuming that the frequently used atoms in the overcomplete dictionary tend to be the background. In order to make full use of the prior information of anomalies hidden in the scene, the potential anomaly dictionary is constructed. We define a criterion, i.e., the anomalous level of a pixel, by using the residual calculated in the JSR model within its local region. Then, it is combined with a weighted term to alleviate the influence of noise and background. Experiments show that our proposed anomaly detection method based on potential anomaly and background dictionaries construction can achieve superior results compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have recently exhibited an excellent performance in hyperspectral image classification tasks. However, the straightforward CNN-based network architecture still finds obstacles when effectively exploiting the relationships between hyperspectral imaging (HSI) features in the spectral–spatial domain, which is a key factor to deal with the high level of complexity present in remotely sensed HSI data. Despite the fact that deeper architectures try to mitigate these limitations, they also find challenges with the convergence of the network parameters, which eventually limit the classification performance under highly demanding scenarios. In this paper, we propose a new CNN architecture based on spectral–spatial capsule networks in order to achieve a highly accurate classification of HSIs while significantly reducing the network design complexity. Specifically, based on Hinton’s capsule networks, we develop a CNN model extension that redefines the concept of capsule units to become spectral–spatial units specialized in classifying remotely sensed HSI data. The proposed model is composed by several building blocks, called spectral–spatial capsules, which are able to learn HSI spectral–spatial features considering their corresponding spatial positions in the scene, their associated spectral signatures, and also their possible transformations. Our experiments, conducted using five well-known HSI data sets and several state-of-the-art classification methods, reveal that our HSI classification approach based on spectral–spatial capsules is able to provide competitive advantages in terms of both classification accuracy and computational time. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification plays an important role in remote sensing image processing. In recent years, stacked auto-encoder (SAE) has obtained a series of excellent results in PolSAR image classification. The recently proposed projective dictionary pair learning (DPL) model takes both accuracy and time consumption into consideration, and another recently proposed semicoupled dictionary learning (SCDL) model gives a new way to fit different features. Based on the SAE, DPL, and SCDL models, we propose a novel semicoupled projective DPL method with SAE (SAE-SDPL) for PolSAR image classification. Our method can get the classification result efficiently and correctly and meanwhile giving a new method to fit different features. In this paper, three PolSAR images are used to test the performance of SAE-SDPL. Compared with some state-of-the-art methods, our method obtains excellent results in PolSAR image classification. [ABSTRACT FROM AUTHOR]

The spatial resolution is still a problem in passive microwave remote sensing, especially in low frequency. In recent years, the satellite formation flying has been proposed. Based on this technique, a large array is able to be synthesized in orbit to achieve higher spatial resolution. However, it is a big challenge for the control system to constrain all the satellites in a coplane in orbit. The 3-D array configuration is a good choice for a synthesized array based on satellite formation flying. In this paper, the complete formulation of visibility functions, including system imperfections, in a 3-D aperture synthesis radiometer (3-D ASR) is derived. The array factor of a 3-D ASR is defined. The reconstructed modified brightness temperature (BT) is a 3-D linear convolution of the modified BT and the array factor. Based on this relationship, the reconstruction method for a practical 3-D ASR is studied. The numerical results demonstrate that the reconstruction method is correct and stable. Finally, a discussion is given to analyze several existing methods that were proposed to reconstruct BT image for 3-D arrays in radio astronomy and earth observation. Compared with these existing methods, our imaging method is more suitable for earth observation based on the technique of satellites formation flying in low earth orbit. In addition, according to the derivations, some mature techniques that were developed for 2-D ASRs may be applied to 3-D ASRs. [ABSTRACT FROM AUTHOR]

Specular reflectance is an important error source in the remote retrieval of leaf pigment content. However, removing this disturbance is challenging because the specular component cannot be directly separated from the leaf reflectance. In this paper, we removed the specular reflectance through polarization measurements at single leaf scale. First, polarization measurements were taken on leaves in the nadir and an oblique viewing direction. Specular reflectance in these two directions was estimated. Second, leaf specular reflectance was subtracted from the total reflectance. Based on the consequent diffuse reflectance, three common types of vegetation indices (VIs), simple ratio (SR), normalized difference (ND), and red edge position (REP) were built to retrieve pigment content. The results show that: 1) specular reflectance interfered with the retrieval. The greater this component, the more serious it caused the disturbance. The retrieval accuracy in forward 35° was much lower than that in the nadir. 2) After specular reflectance removal, the retrieval in both directions was generally improved for the SR and the ND VIs. The improvement in forward 35° was remarkable, with accuracy reaching or approaching the corresponding nadir level. On the two pigments, improvement for chlorophylls was more apparent than for carotenoids. 3) Of all VIs investigated, the REP was insensitive to specular reflectance and had the best resistance capability. Overall, the proposed methods can effectively eliminate specular interference and improve pigment content retrieval. Even under disadvantageous circumstances with strong specular reflectance, the improvement was still reliable. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel sparsity-based algorithm for anomaly detection in hyperspectral imagery. The algorithm is based on the concept that a background pixel can be approximately represented as a sparse linear combination of its spatial neighbors while an anomaly pixel cannot if the anomalies are removed from its neighborhood. To be physically meaningful, the sum-to-one and nonnegativity constraints are imposed to abundance vector based on the linear mixture model, and the upper bound constraint on sparsity level is removed for better recovery of the test pixel. First, the proposed method utilizes the redundant background information to automatically remove anomalies from the background dictionary. Then, the reconstruction error obtained by the new background dictionary is directly used for anomaly detection. Moreover, a kernel version of the proposed method is also derived to completely exploit the nonlinear feature of hyperspectral data. An important advantage of the proposed methods is their capability to adaptively model the background even when some anomaly pixels are involved. Extensive experiments have been conducted on three real hyperspectral data sets. It is demonstrated that the proposed detectors achieve a promising detection performance with a relatively low computational cost. [ABSTRACT FROM AUTHOR]

It is a classical task to automatically extract road networks from very high-resolution (VHR) images in remote sensing. This paper presents a novel method for extracting road networks from VHR remotely sensed images in complex urban scenes. Inspired by image segmentation, edge detection, and object skeleton extraction, we develop a multitask convolutional neural network (CNN), called RoadNet, to simultaneously predict road surfaces, edges, and centerlines, which is the first work in such field. The RoadNet solves seven important issues in this vision problem: 1) automatically learning multiscale and multilevel features [gained by the deeply supervised nets (DSN) providing integrated direct supervision] to cope with the roads in various scenes and scales; 2) holistically training the mentioned tasks in a cascaded end-to-end CNN model; 3) correlating the predictions of road surfaces, edges, and centerlines in a network model to improve the multitask prediction; 4) designing elaborate architecture and loss function, by which the well-trained model produces approximately single-pixel width road edges/centerlines without nonmaximum suppression postprocessing; 5) cropping and bilinear blending to deal with the large VHR images with finite-computing resources; 6) introducing rough and simple user interaction to obtain desired predictions in the challenging regions; and 7) establishing a benchmark data set which consists of a series of VHR remote sensing images with pixelwise annotation. Different from the previous works, we pay more attention to the challenging situations, in which there are lots of shadows and occlusions along the road regions. Experimental results on two benchmark data sets show the superiority of our proposed approaches. [ABSTRACT FROM AUTHOR]

In the autumn and winter, aerosol is the important atmospheric pollutant over the Beijing–Tianjin–Hebei region. For monitoring aerosol in the autumn and winter, the lack of vegetation and the aging of MODIS sensor are two problems that needed to be solved. In this paper, after analyzing the characteristics of aerosol radiance in the red and shortwave infrared ($2.12~\mu \text{m}$) bands of MODIS, we develop a new algorithm for terrestrial aerosol with the assumption that the reflectance ratio between the red and $2.12~\mu \text{m}$ bands is invariant. With MODIS data over the Beijing–Tianjin–Hebei region from September 2016 to February 2017, the algorithm is applied to aerosol retrieval. The retrieved aerosol optical depth images show that our algorithm can retrieve aerosol over sparse vegetation, and the validation with the AERONET/PHOTONS Beijing site shows that the correlation is greater than 0.9% and 77% of the retrievals fall within the expected error. An error analysis shows that a 2% error in the proportion of the soot component can lead to 15% retrieval error, and over more than 60% of the surface area, the error from the changes in the ratio between the red and $2.12~\mu \text{m}$ bands can lead to retrieved errors less than 0.1. [ABSTRACT FROM AUTHOR]

With the rapid increase of remote sensing images in temporal, spectral, and spatial resolutions, it is urgent to develop effective techniques for joint interpretation of spatial-temporal images. Multitype change detection (CD) is a significant research topic in multitemporal remote sensing image analysis, and its core is to effectively measure the difference degree and represent the difference among the multitemporal images. In this paper, we propose a novel difference representation learning (DRL) network and present an unsupervised learning framework for multitype CD task. Deep neural networks work well in representation learning but rely too much on labeled data, while clustering is a widely used classification technique free from supervision. However, the distribution of real remote sensing data is often not very friendly for clustering. To better highlight the changes and distinguish different types of changes, we combine difference measurement, DRL, and unsupervised clustering into a unified model, which can be driven to learn Gaussian-distributed and discriminative difference representations for nonchange and different types of changes. Furthermore, the proposed model is extended into an iterative framework to imitate the bottom-up aggregative clustering procedure, in which similar change types are gradually merged into the same classes. At the same time, the training samples are updated and reused to ensure that it converges to a stable solution. The experimental studies on four pairs of multispectral data sets demonstrate the effectiveness and superiority of the proposed model on multitype CD. [ABSTRACT FROM AUTHOR]

In geosynchronous spaceborne–airborne bistatic synthetic aperture radar (GEO-BiSAR) system, the airborne platform achieves high-resolution imaging by passively receiving the signal from the interested scenario. In this paper, the Doppler characteristics of GEO-BiSAR and the individual contribution of the transmitter and the receiver are first analyzed. The airborne receiver is found to be the dominant contributor for the total Doppler bandwidth, which will lead to Doppler spectrum aliasing regarding the low pulse repetition frequency (PRF) adopted by the GEO-SAR. In order to suppress the Doppler ambiguity without adjusting the PRF of GEO-SAR, azimuth multichannel receiving technique is introduced to the airborne receiver. The multichannel transfer function is derived based on the method of series reversion and the spectrum reconstruction algorithm is then modified for multichannel GEO-BiSAR. Moreover, the reconstruction performance is closely related to the corresponding spacing between each channel (i.e., channel configuration). Therefore, the channel configuration design for GEO-BiSAR aims at optimizing the azimuth ambiguity-to-signal ratio with a satisfactory level of signal-to-noise ratio scaling factor by adjusting the channel configuration. The channel configuration design is modeled as a constrained single objective optimization problem (CSOP). Then, a channel configuration design method based on differential evolution and feasibility rule is proposed to solve the CSOP and obtain the channel configuration for the receiver with the optimal reconstruction performance. Finally, simulations results are presented to verify the effectiveness of the proposed method, and characteristics of channel configuration are analyzed in detail, which can be a practical guide for the implementation of multichannel GEO-BiSAR systems. [ABSTRACT FROM AUTHOR]

The Fourier-based image correlation technique has been widely concerned due to its accuracy, efficiency, and robustness to image contrast and brightness. Accordingly, a variety of subpixel methods have been proposed. However, the detailed subpixel-level influence of the complicated radiometric variations has yet to be investigated, and few corresponding improvements have been made. This paper presents a novel illumination-robust subpixel Fourier-based image correlation method based on phase congruency. Both the magnitude and orientation information of the phase congruency features are adopted to construct a structural image representation. The image representation is then embedded into the correlation scheme of the subpixel methods, either by linear phase estimation in the frequency domain or by kernel fitting in the spatial domain, achieving two improved subpixel methods. The proposed methods integrate the advantages of the structural image representation and the original correlation scheme, and make full use of both global and local phase information to achieve illumination-robust correlation. Experiments undertaken with both simulated and real radiometric differences were carried out with ground-truth subpixel shifts. The performances of the proposed methods and the other state-of-the-art subpixel Fourier-based correlation methods were evaluated and compared. The experimental results indicate that the proposed methods outperform the other methods in the presence of diverse radiometric variations, in both accuracy and robustness. [ABSTRACT FROM AUTHOR]

In this paper, a time series of 33 TerraSAR-X copolarized synthetic aperture radar (SAR) imagery collected in Stripmap mode over the Gulf of Mexico in a wide range of incidence angles and sea-state condition is exploited, together with a theoretical framework based on the X-Bragg scattering model, to analyze the effects of noise, angle of incidence, (AOI) and wind speed on the standard deviation of the copolarized phase difference ($\sigma _{\phi _{c}}$) evaluated over sea surface with and without oil slicks. This large data set represents an unprecedented opportunity to analyze, for the first time, the influence of both SAR acquisition and surface parameters on the broadening of the copolarized phase difference probability density function (pdf), $p_{\phi _{c}}(\phi _{c})$. Experimental results show that the X-Bragg scattering model, here adopted to predict the sea surface $p_{\phi _{c}}(\phi _{c})$ , gives an understanding of the increasing trend of $\sigma _{\phi _{c}}$ with respect to AOI. It is shown that the noise significantly contributes to broaden $p_{\phi _{c}}(\phi _{c})$ over both slick-free and slick-covered sea surface, while the effects of low-to-moderate wind regimes are negligible. In addition, $\sigma _{\phi _{c}}$ exhibits a larger sensitivity to the scene variability, if compared to single-polarization intensity channels, over both slick-free and oil-covered sea surface. This sensitivity is more pronounced at lower AOIs due to the higher noise equivalent sigma zero (NESZ) that affects larger AOIs. [ABSTRACT FROM AUTHOR]

A rain-gauge-adjusted algorithm for global satellite mapping of precipitation (GSMaP) that estimates the surface precipitation rate with resolutions of 0.1° and 1 h over the globe is described herein. Precipitation is one of the most important parameters of the earth’s system, and its global distribution and changes are essential data for modeling the water cycle, maintaining ecosystems, increasing agricultural production, improving weather forecasting precision, and implementing flood warning systems. In the Global Precipitation Measurement project, integrated products of high-resolution mapping of precipitation, obtained from microwave measurements made by a constellation satellite and infrared radiometers in geostationary orbit, are developed and supplied to the public. However, these high-resolution products, such as GSMaP_MVK, sometimes underestimate surface precipitation, introducing large errors into hydrological modeling. This paper combines the global gauge data set with GSMaP_MVK, using a new algorithm [gauge-adjusted GSMaP (GSMaP_Gauge)], described and evaluated herein using local radar and rain-gauge data sets. This algorithm outperforms other GSMaP products in all validation tests. [ABSTRACT FROM AUTHOR]

Vibration or rotation on a target or any structure of a target might induce a frequency modulation on the returned radar signal, which is called micro-Doppler effect, and is widely used for many of the remote sensing applications such as target detection, classification, and recognition. However, the micro-Doppler frequency could be large and it may cause micro-Doppler ambiguities which are undesirable in these applications. In this paper, we propose a novel and flexible method to resolve the micro-Doppler ambiguities based on the time-delayed cross correlation processing of wideband radar echoes for range-spread targets. Variable-sized shrinkage ratio can be obtained to reduce the micro-Doppler frequency of the signal to an appropriate numerical value, and the micro-Doppler ambiguities can be resolved in different situations. The effectiveness of the proposed method is validated by simulations and real data experiments. [ABSTRACT FROM AUTHOR]

Although several works have been done on high-resolution inverse synthetic aperture radar (ISAR) imaging via compressive sampling technology, they only explore sparse priors of targets in the scene and the image is recovered cell by cell separately. In order to potentially enhance targets and suppress clutters for fast and higher quality imaging, in this paper, we advance a collaborative compressive ISAR (CC-ISAR) imaging approach, by exploring both sparse priors and saliency priors of targets. First, a geometric saliency map is derived by performing pulse contourlet transform on a preliminary image. Then, a graph Laplacian is constructed to regularize a multiple measurement vector problem for collaborative compressive radar imaging. Third, targets are approximately separated from the background in the saliency map, and salient weights are defined for the target and background, respectively, to derive a saliency weighted $l_{1}$ -norm optimization algorithm. Some experiments are taken on real ISAR data to evaluate the performance of the proposed method, and both visual results and numerical guidelines prove that CC-ISAR imaging method can obtain more accurate targets and outperform its counterparts. [ABSTRACT FROM AUTHOR]

GaoFen1 is the first high-resolution earth observation satellite built in China, and carries four wide field-of-view (WFV) cameras to achieve large-scale monitoring and mapping. However, the unstable attitude measurement accuracy of the satellite generally imparts low geopositioning accuracy and inconsistent geometric error in overlapping areas of WFV images. A feasible and effective large-scale planar block adjustment (PBA) method is presented that corrects the geometric errors of the vast WFV images integrally, further improving the geometric accuracy of these images. In addition, whether ground control points (GCPs) are needed, and the effect of different numbers of GCPs on PBA accuracy is also investigated. Two key technologies are used in this paper. First, a universal PBA error equation based on the virtual control points is presented to allow PBA with or without GCPs. Second, an adjustment method aided by a digital elevation model is adopted to overcome the weak convergence geometry among WFV images, further ensuring stable estimation of PBA. The effectiveness of the proposed method was verified by 664 WFV images covering most of mainland China. The satisfactory experimental results indicate that the method presented herein is reasonable and effective, but that a certain number of GCPs is needed to ensure the accuracy of large-scale PBA results for WFV images. [ABSTRACT FROM AUTHOR]

Remote sensing image scene classification is a fundamental problem, which aims to label an image with a specific semantic category automatically. Recently, deep learning methods have achieved competitive performance for remote sensing image scene classification, especially the methods based on a convolutional neural network (CNN). However, most of the existing CNN methods only use feature vectors of the last fully connected layer. They give more importance to global information and ignore local information of images. It is common that some images belong to different categories, although they own similar global features. The reason is that the category of an image may be highly related to local features, other than the global feature. To address this problem, a method based on rearranged local features is proposed in this paper. First, outputs of the last convolutional layer and the last fully connected layer are employed to depict the local and global information, respectively. After that, the remote sensing images are clustered to several collections using their global features. For each collection, local features of an image are rearranged according to their similarities with local features of the cluster center. In addition, a fusion strategy is proposed to combine global and local features for enhancing the image representation. The proposed method surpasses the state of the arts on four public and challenging data sets: UC-Merced, WHU-RS19, Sydney, and AID. [ABSTRACT FROM AUTHOR]

In this paper, the usefulness of remote sensing imageries for identifying soil texture classes was evaluated by classification trees under one-against-one (OAO), one-against-all, and all-together schemes. A set of normalized difference vegetation indices (NDVIs) was obtained from cloud-free Landsat images over a small mountainous watershed. Terrain indicators (elevation, slope, and topographic wetness index) were derived from a digital elevation map (30 m). Models with different input parameters (purely NDVI, purely topography and stratum, and NDVI plus topography and stratum) were developed. Overall accuracy, kappa statistic, receiver operating characteristics (ROC), and the area under ROC curve (AUC) were applied to evaluate the classification accuracy. Results showed that the classification strategy had great effects on the outputs. The models under OAO scheme performed better with averaged overall accuracy, kappa statistic, and AUC of 0.949, 0.821, and 0.87, respectively. Among them, the model with NDVI plus topography and stratum performed best with overall accuracy, kappa statistic, and AUC of 0.975, 0.918, and 0.907, respectively. Similar performances were obtained by the model with purely NDVI and the model with purely topography and stratum. More samples of clay and sand were identified with the help of NDVI. The contributions of NDVI to explain soil texture class variability were 144%, 0%, and 14% for clay, loam, and sand, respectively. NDVI measured during the stem and leaf growth period of sweet potatoes was the optimum period for identifying soil texture classes in the watershed. Our findings will provide valuable information for assessing the quality of ecological environment using remote sensing data. [ABSTRACT FROM AUTHOR]

Establishing causal relations between random variables from observational data is perhaps the most important challenge in today’s science. In remote sensing and geosciences, this is of special relevance to better understand the earth’s system and the complex interactions between the governing processes. In this paper, we focus on an observational causal inference, and thus, we try to estimate the correct direction of causation using a finite set of empirical data. In addition, we focus on the more complex bivariate scenario that requires strong assumptions and no conditional independence tests can be used. In particular, we explore the framework of (nondeterministic) additive noise models, which relies on the principle of independence between the cause and the generating mechanism. A practical algorithmic instantiation of such principle only requires: 1) two regression models in the forward and backward directions and 2) the estimation of statistical independence between the obtained residuals and the observations. The direction leading to more independent residuals is decided to be the cause. We instead propose a criterion that uses the sensitivity (derivative) of the dependence estimator, the sensitivity criterion allows to identify samples most affecting the dependence measure, and hence, the criterion is robust to spurious detections. We illustrate the performance in a collection of 28 geoscience causal inference problems, a database of radiative transfer models simulations and machine learning emulators in vegetation parameter modeling involving 182 problems, and assessing the impact of different regression models in a carbon cycle problem. The criterion achieves the state-of-the-art detection rates in all cases, and it is generally robust to noise sources and distortions. The presented approach confirms the validity in observational bivariate problems in the earth sciences. [ABSTRACT FROM AUTHOR]

Relationships between vegetation indices (VIs) and leaf area index (LAI) tend to saturate in the nadir direction, and vary with crop canopy structure and view zenith angles (VZAs). The objective of this paper was to improve the monitoring accuracy and angular stability of VIs for estimating LAI using multiangular remote sensing data. The relationship between LAI and ground-based hyperspectral spectral reflectance was quantified in winter wheat (Triticum aestivum L.) exhibiting erectophile and planophile growth habits. To further reduce the saturation, species specificity, and angular sensitivity, we developed a saturation factor (SF), based on near-infrared and green bands. Multiplying all VIs by SF greatly improved the association with LAI across all VZAs ($R^{2} = 0.73{-}0.82$). Most VI $\times$ SF values, particularly optimized soil-adjusted VI $\times$ SF, were able to construct universal algorithms across VZAs for accurate estimation of LAI due to the sensitivity of SF to LAI in a dense canopy, and the insensitivity of SF to view effects with larger VZAs. This approach is also promising for the exploitation of multiangular satellite data for the design and calibration of nonview-angle-corrected spectral reflectance, for which the sensor is only deployed at fixed observation direction. [ABSTRACT FROM AUTHOR]

Multitemporal airborne and satellite imagery data with frequent repeat coverage provide great capability for change detection (CD). When comparing two images taken at different times of day or in different seasons for CD, the variation of topographic shades and shadows caused by the change of sunlight angle can be so significant that it overwhelms the real object and environmental changes, making automatic detection unreliable. An effective CD algorithm, therefore, has to be robust to the illumination variation. In this paper, the robustness of phase correlation (PC) to shadow effects is proven via mathematical analysis, and then, an illumination-invariant change detection (IICD) metric is proposed based on pixel-wise dense PC matching. In the proposed IICD method, a graph-based visual saliency map is introduced for the initial CD followed by an active contour-based segmentation to precisely quantize the change region. Compared to the state-of-the-art CD algorithms, experiments using daily images of a landscape model and Landsat satellite images demonstrate that only the proposed method can effectively detect and precisely segment appearance changes under daily and seasonal sunlight changes. [ABSTRACT FROM AUTHOR]

High-spatial hyperspectral (HH) image reconstruction using both high-spatial multispectral (HM) image and low-spatial hyperspectral (LH) image over the same scene is widely used in many real applications. Nevertheless, the pair of HM image and LH image over the same scene is hard to obtain. To solve this problem, a new HH image reconstruction method using spectral library-based dictionary learning (named as HIRSL) is proposed in this paper, only from one HM image. The above reconstruction problem is formulated in the framework of sparse representation, as an estimation of the band matching matrix, the spectral dictionary, and the sparse coefficients. More specifically, a band matching method is proposed for mapping the common spectral library to a specific spectral library corresponding to the reconstructed HH image in spectral domain. Then, an efficient spectral dictionary learning method is proposed for the construction of spectral dictionary using the matched specific spectral library, which avoids the dependence of the LH image over the same scene. Finally, the sparse coefficients of the HM image with respect to the learned spectral dictionary are estimated using the alternating direction method of multipliers without nonnegative constraint. Comparison results on simulated and real data sets with the relative state-of-the-art methods demonstrate that even only using one HM image, our proposed method achieves a comparable reconstruction quality of high-spatial hyperspectral image both in spatial and spectral domains. [ABSTRACT FROM AUTHOR]

This paper aims to provide a compact superresolution formulation specific for multispectral (MS) multiresolution optical data, i.e., images characterized by different scales across different spectral bands. The proposed method, named multiresolution sharpening approach (MuSA), relies on the solution of an optimization problem tailored to the properties of those images. The superresolution problem is formulated as the minimization of an objective function containing a data-fitting term that models the blurs and downsamplings of the different bands and a patch-based regularizer that promotes image self-similarity guided by the geometric details provided by the high-resolution bands. By exploiting the approximately low-rank property of the MS data, the ill-posedness of the inverse problem in hand is strongly reduced, thus sharply improving its conditioning. The state-of-the-art color block-matching and 3D filtering (C-BM3D) image denoiser is used as a patch-based regularizer by leveraging the “plug-and-play” framework: the denoiser is plugged into the iterations of the alternating direction method of multipliers. The main novelties of the proposed method are: 1) the introduction of an observation model tailored to the specific properties of (MS) multiresolution images and 2) the exploitation of the high-spatial-resolution bands to guide the grouping step in the color block-matching and 3D filtering (C-BM3D) denoiser, which constitutes a form of regularization learned from the high-resolution channels. The results obtained on the real and synthetic Sentinel 2 data sets give an evidence of the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

The advanced Himawari imager (AHI) aboard the Himawari-8 geostationary satellite provides high-frequency observations with broad coverage, multiple spectral channels, and high spatial resolution. In this paper, AHI data were used to develop an algorithm for joint retrieval of aerosol optical depth (AOD) over land and land surface bidirectional reflectance. Instead of performing surface reflectance estimation before calculating AOD, the AOD and surface bidirectional reflectance were retrieved simultaneously using an optimal estimation method. The algorithm uses an atmospheric radiative transfer model coupled with a surface bidirectional reflectance factor (BRF) model. Based on the assumption that the surface bidirectional reflective properties are invariant during a short time period (i.e., a day), multiple temporal AHI observations were combined to calculate the AOD and surface BRF. The algorithm was tested over East Asia for year 2016, and the AOD retrieval results were validated against the aerosol robotic network (AERONET) sites observation and compared with the Moderate Resolution Imaging Spectroradiometer Collection 6.0 AOD product. The validation of the retrieved AOD with AERONET measurements using 14 713 colocation points in 2016 over East Asia shows a high correlation coefficient: $R = 0.88$ , root-mean-square error = 0.17, and approximately 69.9% AOD retrieval results within the expected error of $\pm 0.2\cdot {\mathrm {AOD}}_{\mathrm {AERONET}}\pm 0.05$. A brief comparison between our retrieval and AOD product provided by Japan Meteorological Agency is also presented. The comparison and validation demonstrates that the algorithm has the ability to estimate AOD with considerable accuracy over land. [ABSTRACT FROM AUTHOR]

Graph-based and manifold-regularization (MR)-based semisupervised learning, including Laplacian regularization (LapR) and hypergraph LapR (HLapR), have achieved prominent performance in preserving locality and similarity information. However, it is still a great challenge to exactly explore and exploit the local structure of the data distribution. In this paper, we present an efficient and effective approximation algorithm of hypergraph ${p}$ -Laplacian and then propose hypergraph ${p}$ -LapR (HpLapR) to preserve the geometry of the probability distribution. In particular, hypergraph is a generalization of a standard graph while hypergraph ${p}$ -Laplacian is a nonlinear generalization of the standard graph Laplacian. The proposed HpLapR shows great potential to exploit the local structures. We integrate HpLapR with logistic regression for remote sensing image recognition. Experiments on UC-Merced data set demonstrate that the proposed HpLapR has superior performance compared with several popular MR methods including LapR and HLapR. [ABSTRACT FROM AUTHOR]

Image classification is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, a convolutional neural network (CNN) has established itself as a powerful model in classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the classification performance. In this paper, we propose a method to classify hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral band groups to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of 3-D data cubes. Furthermore, we introduce a deep deconvolution network that improves the final classification performance. We also introduced a new data set and experimented our proposed method on it along with several widely adopted benchmark data sets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method. [ABSTRACT FROM AUTHOR]

In ground-based remote sensing cloud image observation, images with the highest possible resolution are captured to obtain sufficient information about clouds. However, when features are extracted and classification is performed on the basis of the original images, a high-resolution probably means a high (or even more, unacceptable) computation cost. In practical application, a simple and commonly adopted method is to appropriately resize the original image to a version with a decreased resolution. An inevitable problem is whether useful information is lost in this resizing operation. This paper demonstrates that information loss is inevitable and poor classification results may be obtained from the analysis of local binary pattern (LBP) histogram features. However, this problem has been always neglected in previous studies, and the original image is arbitrarily resized without any criterion. In particular, the histogram features based on LBPs actually reflect the distribution of features. Thus, a criterion based on the Kullback–Leibler divergence between LBP histograms from the original and resized images and a penalty term imposed on the resolution are proposed to select the resolution of the resized image. The optimal resolution of the resized image can be selected by minimizing this criterion. Furthermore, experiments based on three ground-based remote sensing cloud image data sets with different original resolutions validate this criterion by analyzing the LBP histogram features. [ABSTRACT FROM AUTHOR]

Latent heat is the energy released or absorbed by a substance through phase change without changing its temperature. Its flux is a crucial element of the hydrological cycle at the land–air interface. Many water-related indexes have been proposed as indicators for latent heat flux extraction from satellite imagery, while the extraction accuracy still remains a space to improve nowadays. In this paper, a new multiband index, called normalized difference latent heat index (NDLI), is proposed for remote sensing of land surface heat flux. It utilizes the reflectance observations of three bands from Landsat 8 operational land imager, including red, green, and shortwave infrared channels. Its performance in terms of deriving latent heat flux through their incorporation into the commonly used surface energy balance algorithm for land (SEBAL) is then compared with the other three existing water-related indexes with two of them using normalized difference water index and normalized difference vegetation index. Results show that NDLI exhibits the strongest correlation with the SEBAL-derived latent heat flux among the used water-related indexes with correlation coefficient $r = 0.75$. They also indicate that the NDLI is the most sensitive and reliable index outperforming the previously developed indexes to determine the characteristics of water content in different land cover types. It is concluded that NDLI can be used as a good indicator to represent the potential latent heat flux at the earth’s surface. [ABSTRACT FROM AUTHOR]

Accurate crown detection and delineation of dominant and subdominant trees are crucial for accurate inventorying of forests at the individual tree level. The state-of-the-art tree detection and crown delineation methods have good performance mostly with dominant trees, whereas exhibits a reduced accuracy when dealing with subdominant trees. In this paper, we propose a novel approach to accurately detect and delineate both the dominant and subdominant tree crowns in conifer-dominated multistoried forests using small footprint high-density airborne Light Detection and Ranging data. Here, 3-D candidate cloud segments delineated using a canopy height model segmentation technique are projected onto a novel 3-D space where both the dominant and subdominant tree crowns can be accurately detected and delineated. Tree crowns are detected using 2-D features derived from the projected data. The delineation of the crown is performed at the voxel level with the help of both the 2-D features and 3-D texture information derived from the cloud segment. The texture information is modeled by using 3-D Gray Level Co-occurrence Matrix. The performance evaluation was done on a set of six circular plots for which reference data are available. The high detection and delineation accuracies obtained over the state of the art prove the performance of the proposed method. [ABSTRACT FROM AUTHOR]

Change detection is one of the central problems in earth observation and was extensively investigated over recent decades. In this paper, we propose a novel recurrent convolutional neural network (ReCNN) architecture, which is trained to learn a joint spectral–spatial–temporal feature representation in a unified framework for change detection in multispectral images. To this end, we bring together a convolutional neural network and a recurrent neural network into one end-to-end network. The former is able to generate rich spectral-spatial feature representations, while the latter effectively analyzes temporal dependence in bitemporal images. In comparison with previous approaches to change detection, the proposed network architecture possesses three distinctive properties: 1) it is end-to-end trainable, in contrast to most existing methods whose components are separately trained or computed; 2) it naturally harnesses spatial information that has been proven to be beneficial to change detection task; and 3) it is capable of adaptively learning the temporal dependence between multitemporal images, unlike most of the algorithms that use fairly simple operation like image differencing or stacking. As far as we know, this is the first time that a recurrent convolutional network architecture has been proposed for multitemporal remote sensing image analysis. The proposed network is validated on real multispectral data sets. Both visual and quantitative analyses of the experimental results demonstrate competitive performance in the proposed mode. [ABSTRACT FROM AUTHOR]

Label information plays an important role in a supervised hyperspectral image classification problem. However, current classification methods all ignore an important and inevitable problem—labels may be corrupted and collecting clean labels for training samples is difficult and often impractical. Therefore, how to learn from the database with noisy labels is a problem of great practical importance. In this paper, we study the influence of label noise on hyperspectral image classification and develop a random label propagation algorithm (RLPA) to cleanse the label noise. The key idea of RLPA is to exploit knowledge (e.g., the superpixel-based spectral–spatial constraints) from the observed hyperspectral images and apply it to the process of label propagation. Specifically, the RLPA first constructs a spectral–spatial probability transform matrix (SSPTM) that simultaneously considers the spectral similarity and superpixel-based spatial information. It then randomly chooses some training samples as “clean” samples and sets the rest as unlabeled samples, and propagates the label information from the “clean” samples to the rest unlabeled samples with the SSPTM. By repeating the random assignment (of “clean” labeled samples and unlabeled samples) and propagation, we can obtain multiple labels for each training sample. Therefore, the final propagated label can be calculated by a majority vote algorithm. Experimental studies show that the RLPA can reduce the level of noisy label and demonstrates the advantages of our proposed method over four major classifiers with a significant margin—the gains in terms of the average overall accuracy, average accuracy, and kappa are impressive, e.g., 9.18%, 9.58%, and 0.1043. The MATLAB source code is available at https://github.com/junjun-jiang/RLPA. [ABSTRACT FROM AUTHOR]

The airborne Operation IceBridge and spaceborne CryoSat-2 missions observe polar sea ice at different spatial and temporal scales as well as with different sensor suites. Comparison of data products from IceBridge and CryoSat-2 is complicated by the fact that they use different geophysical corrections: reference ellipsoid, geoid model, tide model, and atmospheric corrections to derive surface elevation and sea-ice freeboard. In this paper, we compare sea-ice surface elevation and freeboard using eight coincident CryoSat-2, Airborne Topographic Mapper (ATM), and Land, Vegetation, and Ice Sensor (LVIS) observations with direct IceBridge underflights of CryoSat-2 ground tracks. We apply identical geophysical corrections to CryoSat-2 and IceBridge data to eliminate elevation biases due to these differences and focus on differences due to retracker performance. The IceBridge ATM and LVIS elevation and freeboard and Snow Radar snow depth data sets are averaged to each CryoSat-2 footprint for comparison. With snow depth measurements, we are able to compare elevations and freeboards at the snow/ice interface for five different CryoSat-2 retrackers (ESA, GSFCv1, AWI, JPL, and GSFCv2) and IceBridge. The overall mean of freeboard differences between GSFCv2, ESA, AWI, JPL retrackers, and ATM are in agreement within 0.05 m. However, the five different CryoSat-2 retrackers show distinct differences in mean elevation over leads and over floes. This suggests that the physical interpretation of the different retrackers needs to be considered depending on usage, for example, elevations from CryoSat-2 retrackers need to be carefully calibrated before comparing with elevation from other satellites for long-term surface elevation trends. [ABSTRACT FROM AUTHOR]

Spatial information has widely been used in hyperspectal image (HSI) classification to improve classification accuracy. However, the structural information may not be fully explored when using spatial information, this paper proposes the joint collaborative representation classification with correlation matrix (CRC-CM) for HSI by using spatial correlation features in patches, which could keep the local intrinsic structure in band images. Considering spatial heterogeneity in a patch, local correlation matrices of a target neighborhood patch and training neighborhood patch are improved by a binary weight matrix and shape-adaptive neighborhood. To explore nonlinear nature of spatial features, corresponding kernel CRC-CM is also proposed. To evaluate the effectiveness of the proposed methods, three real HSIs with different degree of heterogeneity are used. The experimental results show that the proposed spatial correlation features outperform the original spectral feature and other spatial features which widely used in HSI classifiers. [ABSTRACT FROM AUTHOR]

Topographic effects on canopy reflectance play a pivotal role in the retrieval of surface biophysical variables over rugged terrain. In this paper, we proposed a new canopy anisotropic reflectance model for discrete forests, Geometric Optical and Mutual Shadowing and Scattering-from-Arbitrarily-Inclined-Leaves model coupled with Topography (GOSAILT), which considers the effects of slope, aspect, geotropic nature of tree growth, multiple scattering, and diffuse skylight. GOSAILT-simulated areal proportions of four scene components (i.e., sunlit crown, shaded crown, sunlit background, and shaded background) were evaluated using the Geometric Optical model for Sloping Terrains (GOST) model. The canopy reflectances simulated by GOSAILT were validated against two reflectance data sets: Discrete anisotropic radiative transfer (DART) simulations and wide-angle infrared dual-model line/area array scanner (WIDAS) observations. Compared with a horizontal surface, the forest canopy reflectance over a steep slope (60°) is significantly distorted with absolute (relative) bias values of 0.048 (79.60%) and 0.056 (12.02%) for the red and near-infrared (NIR) bands, respectively. The GOSAILT-simulated component areal proportions show close agreements with GOST. Moreover, GOSAILT simulations have high overall accuracy (red band: coefficient of determination ($R^{2}) = 0.96$ ; root-mean-square error (RMSE) = 0.003; and mean absolute percentage error (MAPE) = 3.91%; and NIR band: $R^{2} = 0.78$ , RMSE = 0.019; MAPE = 3.94%) when compared with the DART simulations. These extensive validations indicate good performances of GOSAILT in canopy reflectance simulations over sloped surfaces. [ABSTRACT FROM AUTHOR]

In this paper, we present an algorithm for retrieving all the second statistical moments of the sea surface that affect the scattering of waves at small angles of incidence. A feature of this algorithm is the analysis of the spectral characteristics of the reflected waves only, without taking into account the backscattering cross section. The analysis of the width and the shift of the Doppler spectrum (DS) allows us to use the obtained algorithm without the preliminary instrumental calibration, which is necessary for the backscattering cross section. We give final expressions for calculating the width and the shift of the DS in the monostatic problem statement for small angles of incidence. We obtain the expressions within the framework of the Kirchhoff approximation, which makes them reliable only in the quasi-specular reflection region. Features of these formulas are the description of the surface by five statistical moments of the second order and taking into account the anisotropic antenna pattern (AP). To solve the inverse problem of retrieving sea surface parameters, we propose a measurement scheme including three motionless transceiver antennas with different APs. For this measurement scheme, we give analytical expressions for all five unknown parameters of surface waves. Also, we give a theoretical analysis of the accuracy of the algorithm obtained for different wind speeds and wind directions. All the results are valid for the scattering of both acoustic and electromagnetic waves. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification, which aims to assign an accurate label for hyperspectral pixels, has drawn great interest in recent years. Although low-rank representation (LRR) has been used to classify HSI, its ability to segment each class from the whole HSI data has not been exploited fully yet. LRR has a good capacity to capture the underlying low-dimensional subspaces embedded in original data. However, there are still two drawbacks for LRR. First, the LRR does not consider the local geometric structure within data, which makes the local correlation among neighboring data easily ignored. Second, the representation obtained by solving LRR is not discriminative enough to separate different data. In this paper, a novel locality- and structure-regularized LRR (LSLRR) model is proposed for HSI classification. To overcome the above-mentioned limitations, we present locality constraint criterion and structure preserving strategy to improve the classical LRR. Specifically, we introduce a new distance metric, which combines both spatial and spectral features, to explore the local similarity of pixels. Thus, the global and local structures of HSI data can be exploited sufficiently. In addition, we propose a structural constraint to make the representation have a near-block-diagonal structure. This helps to determine the final classification labels directly. Extensive experiments have been conducted on three popular HSI data sets. And the experimental results demonstrate that the proposed LSLRR outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recent studies demonstrate the power of applying satellite imagery in combination with artificial intelligence (AI) methods to advance the accuracy of forecasting ungauged river network water levels and discharge for early flood warning and management. In predicting river water levels and discharge time series, one of the most common sources of error with AI forecasting algorithms is the input imitation defect. When the input imitation defect occurs, regression methods simply present the input variables as output. In this paper, the input imitation defect is minimized by first introducing the two concepts of vertical error and horizontal error. Subsequently, upstream imagery information is combined with previous lags to propose a new procedure for predicting future satellite signals accurately and with the lowest possible input imitation defect. To accomplish this, the brightness temperature received by the Advanced Microwave Scanning Radiometer is used as a proxy of river discharge. The proposed method (PM) is finally compared with the simple linear regression and three well-known AI methods, i.e., multilayer perceptron, extreme learning machines, and radial basis function. The study outcome indicates that the PM results are more trustworthy and realistic. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) exhibit good performance in image processing tasks, pointing themselves as the current state-of-the-art of deep learning methods. However, the intrinsic complexity of remotely sensed hyperspectral images still limits the performance of many CNN models. The high dimensionality of the HSI data, together with the underlying redundancy and noise, often makes the standard CNN approaches unable to generalize discriminative spectral–spatial features. Moreover, deeper CNN architectures also find challenges when additional layers are added, which hampers the network convergence and produces low classification accuracies. In order to mitigate these issues, this paper presents a new deep CNN architecture specially designed for the HSI data. Our new model pursues to improve the spectral–spatial features uncovered by the convolutional filters of the network. Specifically, the proposed residual-based approach gradually increases the feature map dimension at all convolutional layers, grouped in pyramidal bottleneck residual blocks, in order to involve more locations as the network depth increases while balancing the workload among all units, preserving the time complexity per layer. It can be seen as a pyramid, where the deeper the blocks, the more feature maps can be extracted. Therefore, the diversity of high-level spectral–spatial attributes can be gradually increased across layers to enhance the performance of the proposed network with the HSI data. Our experiments, conducted using four well-known HSI data sets and 10 different classification techniques, reveal that our newly developed HSI pyramidal residual model is able to provide competitive advantages (in terms of both classification accuracy and computational time) over the state-of-the-art HSI classification methods [ABSTRACT FROM AUTHOR]

The global navigation satellite system (GNSS) data are beneficial for sensing the earth’s ionosphere by virtue of their temporal continuity and spatial coverage. In recent years, GNSS (GPS, GLONASS, BDS, and GALILEO) has developed rapidly, with BDS and GALILEO offering position, navigation, and timing services and the ongoing modernization of GPS and GLONASS. The customary approach to sensing the ionosphere normally uses the dual- or multifrequency (DF) data provided by geodetic-grade receivers and consists of two sequential steps. The first step is retrieving ionospheric observables using the carrier-to-code leveling technique. In the second step, using the thin-layer ionospheric model, one can isolate the main vertical total electron content (VTEC) for ionosphere sensing as well as the by-product of the satellite differential code biases (SDCBs) and the receiver differential code biases. In this paper, we proposed a multi-GNSS single-frequency (SF) precise point positioning approach enabling the simultaneous retrieval of VTEC and SDCBs with low-cost receivers. The root mean square of the VTEC differences between the values retrieved from the multi-GNSS SF method and DF method is approximately 0.5 total electron content unit in each system. [ABSTRACT FROM AUTHOR]

The China-France Oceanography Satellite (CFOSAT) to be launched in October 2018 will carry two innovative payloads, i.e., the surface wave investigation and monitoring instrument and the rotating fan-beam scatterometer [CFOSAT scatterometer (CFOSCAT)]. Both instruments, operated in Ku-band microwave frequency, are dedicated to the measurement of sea surface wave spectra and wind vectors, respectively. This paper provides an overview of the system definition and characteristics of the CFOSCAT instrument. A prelaunch analysis is carried out to estimate the scatterometer backscatter and wind quality based on the developed CFOSCAT simulator prototype. The overall simulation includes two parts: first, a forward model is developed to simulate the ocean backscatter signals, accounting for both instrument and geophysical noise. Second, a wind inversion processor is used to retrieve wind vectors from the outputs of the forward model. The benefits and challenges of the novel observing geometries are addressed in terms of the CFOSCAT wind retrieval. The simulations show that the backscatter accuracy and the retrieved wind quality of CFOSCAT are quite promising and meet the CFOSAT mission requirements. [ABSTRACT FROM AUTHOR]