Deep descriptors have advantages over handcrafted descriptors on local image patch matching. However, due to the complex imaging mechanism of remote sensing images and the significant differences in appearance between multi-modal images, existing deep learning descriptors are unsuitable for multi-modal remote sensing image registration directly. To solve this problem, this article proposes a deep feature

Recently, many collaborative representation (CR)-based algorithms have been proposed for hyperspectral anomaly detection (AD). CR-based detectors approximate the image by a linear combination of background dictionaries and the coefficient matrix and derive the detection map by utilizing recovery residuals. However, these CR-based detectors are often established on the premise of precise background

As a typical application of remote sensing technology, change detection can find the ground information changes by acquiring the images of the same region at different times. The change detection using the synthetic aperture radar (SAR) with the advantages of all day and all-weather usually monitors the significant surface change, such as flood disasters and earthquake deformation. However, when it

Remote sensing pushbroom-type imaging systems acquire entire columns of an image with a single detector. As a consequence, the miss-calibration of the detectors produces stripes on the image. In this context, this article introduces a new self-calibration destriping method based on an affine response model for the detectors, called statistical affine destriping (SAD). In contrast, some previous contributions

As oil and gas exploration moves toward complicated geological environments, high-resolution and true-amplitude seismic imaging becomes increasingly important for detecting and evaluating hydrocarbon reservoirs. Traditional ray-based and wave-equation imaging methods can be considered as the adjoint operator of seismic forward modeling, which are difficult to produce high-quality images in complicated

The holographic subsurface radar (HSR) has been a promising geophysical electromagnetic technique for detecting shallowly buried targets with high lateral resolution image. However, radar images are considerably interpreted by strong reflections from rough surface and inhomogeneity in media of interest. In this article, we focus on mitigating the clutter in HSR applications using a learning-based approach

In recent years, convolutional neural network (CNN)-based methods have been widely used for remote sensing (RS) scene classification tasks and have achieved excellent results. However, CNNs are not good at exploring contextual information, which is essential for fully understanding RS scenes. A new model named transformer attracts researchers’ attention to address this problem, which is skilled in

Distributed acoustic sensing (DAS) is a new exploration technology widely used to acquire vertical seismic profiles (VSPs). DAS can achieve low-cost and high-density observations, but the signal-to-noise ratio (SNR) of the VSP data collected by DAS is low compared with traditional electrical geophones. Moreover, DAS VSP data cover many types of noise, including random noise, fading noise, checkerboard

To realize high azimuth resolution for sea-surface targets, this article proposes a superresolution imaging method that relies on the Weibull distribution. The proposed method introduces the generalized Gaussian distribution and Weibull distribution to represent the statistical distribution function of the target prior information and sea clutter, respectively. The corresponding objective function

Identifying useful microseismic events is one of the key steps in monitoring tunnel rockbursts. Here, we propose a strong noise-tolerance deep learning (SNTDL) network for the automatic classification of noisy microseismic events. The training set, validation set, and test set of the SNTDL network consist of 27989 unfiltered microseismic recordings. First, to comprehensively characterize the microseismic

Predicting wildfire spread is critical for land management and disaster preparedness. To this end, we present “Next Day Wildfire Spread,” a curated, large-scale, multivariate dataset of historical wildfires aggregating nearly a decade of remote-sensing data across the United States. In contrast to existing fire datasets based on Earth observation satellites, our dataset combines 2-D fire data with

Accurate and high-frequency sea-level monitoring is of great importance in ocean environments and global climatic studies, but traditional techniques have their respective limitations. In the last decades, the application of Global Navigation Satellite System Multipath Reflectometry (GNSS-MR) in sea-level monitoring has developed rapidly. Recently, more available GNSS signals are expected to bring

The high-resolution imaging camera (HiRIC) onboard China’s Tianwen-1 Mars probe aims to acquire detailed imagery of the Martian surface to comprehensively investigate its topography and geomorphology. The HiRIC is a pushbroom camera comprising three CCDs to simultaneously achieve submeter resolution and a large swath. However, processing HiRIC images using the conventional photogrammetric workflow

Surface upward longwave radiation (SULR) is a key parameter that regulates surface radiation budget balance and matter–energy exchange. However, the state-of-the-art SULR retrieval methods based on remotely sensed data are only effective under clear skies, which mean that the existing methods are unable to generate spatiotemporal continuous SULR product at regional or global scale. Herein, taking the

Hyperspectral imaging (HSI) greatly improves the capacity to identify and monitor ground objects due to the high spectral resolution. As the real-time remote sensing monitoring and warning tasks are getting more attention, new algorithms for low-power on-board classification are required to reduce the transmission time of satellite downlink. In this article, we propose the multiscale local maximum

Realistic hyperspectral image (HSI) super-resolution (SR) techniques aim to generate a high-resolution (HR) HSI with higher spectral and spatial fidelity from its low-resolution (LR) counterpart. The generative adversarial network (GAN) has proven to be an effective deep learning framework for image SR. However, the optimization process of existing GAN-based models frequently suffers from the problem

We present an analytical formulation of the correlation coefficient of the electromagnetic fields scattered at near-specular direction by a rough or gently undulating surface and measured at two spatially separated positions occupied by a moving receiver at slightly different times. This allows us obtaining an explicit expression of the correlation time of the received signal in terms of radar and

Deep learning (DL) has achieved promising results for impedance inversion via seismic data. Generally, these networks, composed of convolution layers and residual blocks, tend to deliver good results with deep architectures. Nevertheless, deep networks accompany a large number of parameters and longer training time. The volume of seismic data, especially 3-D scenarios, is very large. Therefore, it

Typhoons, a kind of devastating natural disaster, have caused incalculable damages worldwide. The meteorological radar image is essential for weather forecasting, especially typhoons. The weather nowcasting (future 0–6 h) can be implemented via extrapolating radar images without using the primary weather forecasting method—the numerical weather prediction model. However, the existing related techniques

Ionospheric monitoring and modeling have been difficult for a long time over the data-void or data-sparse oceans. As an emerging remote sensing technique, global navigation satellite system reflectometry (GNSS-R) has presented great potential in ionosphere sounding over these regions. However, the conventional approach to generate delay-Doppler-map (DDM) involved in the GNSS-R total electron content

Multimodal land cover classification (MLCC) using the optical and synthetic aperture radar (SAR) modalities has resulted in outstanding performances over using only unimodal data due to their complementary information on land properties. Previous multimodal deep learning (MDL) methods have relied on handcrafted multibranch convolutional neural networks (CNN) to extract the features of different modalities

Timely and up-to-date bathymetry maps over large geographical areas have been difficult to create, due to the cost and difficulty of collecting in situ calibration and validation data. Recently, combinations of spaceborne Ice, Cloud, and Elevation Satellite-2 (ICESat-2) lidar data and Landsat/sentinel-2 data have reduced these obstacles. However, to date, there have been no means of automatically extracting

In this article, we propose the false-alarm-rate-controllable (FAC) classification of sea clutter recurrence plots (RPs) based on convolutional neural networks (CNNs), which is shortened as RPs-CNN. Sea clutter data are a nonlinear and recursive time series, and RPs provide qualitative analysis of nonlinear and recursive dynamic systems. Thus, we construct the RPs’ datasets to extract the recursive

Sky-wave over-the-horizon radar (OTHR) propagates radio waves off the ionosphere to provide long-range surveillance around the Earth’s curvature. Frequency selection for high-latitude and polar OTHRs is challenging unless there is an environmental monitor that addresses the significant ionospheric variability in high-latitude regions, a spectrum monitor that finds unoccupied frequencies in the high-frequency

Polarized scanning atmospheric corrector (PSAC) onboard the HuanjingJianzai-2 (HJ-2) A/B satellites is a cross-track scanning polarimetric remote sensor that measures the intensity and direction of light reflected by the Earth and its atmosphere by nine full polarized spectral bands from near-ultraviolet (near-UV) to shortwave infrared (SWIR). In particular, geolocation accuracy is an important factor

Multisource image registration is challenging due to intensity, rotation, and scale differences among the images. Considering the characteristics and differences in multisource remote sensing images, a feature-based registration algorithm named multiscale histogram of local main orientation (MS-HLMO) is proposed. Harris corner detection is first adopted to generate feature points. The HLMO feature

The traditional method to improve the resolution in electromagnetic inversion is increasing the number of iterations, which displays poor nonlinear mapping and strong nonuniqueness. To meet this challenge, a new strategy is proposed via reconstructing the geoelectric model for traditional inversion results through a deep neural network (DNN). DNN possesses the advantage of establishing an uncertain

As the successors of the Huanjing Jianzai-1 (HJ-1) series satellites in the Chinese Environmental Protection and Disaster Monitoring Satellite Constellation, the first two Huanjing Jianzai-2 (HJ-2) A/B satellites have been successfully launched on September 27, 2020. The polarized scanning atmospheric corrector (PSAC) sensors, onboard the HJ-2 A/B satellites, are served as the synchronously atmospheric

Target detection in sea clutter is of great significance in military radar research. Because the characteristics of sea clutter are complex and easily affected by wind direction, the method of suppressing sea clutter by using sea clutter characteristics to reproduce is not advantageous. To address this problem, this article focuses on the direct extraction of the target echo. According to the difference

Geolocation is one of the key synthetic aperture radar (SAR) image processing procedures in SAR-based remote-sensing applications. The conventional SAR imagery geolocation model is based on the range-Doppler (RD) equation, which is derived from the Fresnel approximation of SAR. Currently, there is no other rigorous geolocation model for modern high-resolution SAR; however, this approximation may not

At present, few-shot object detection research in the field of optical remote sensing images has been conducted, but few-shot object detection in the field of synthetic aperture radar (SAR) images has rarely been explored. To this end, this article proposes a lightweight metalearning-based SAR image few-shot object detection method, which improves the accuracy and speed of SAR image few-shot object

Many unmixing methods hold the assumption that endmembers correspond to major land covers, but not true for some unmixing tasks where observed minor object signals corresponding to some special types of endmembers are relatively weak. When there exist weak signals that have low intensity potentially caused by subtle mixing abundance fractions regarding the endmembers of minor objects, the traditional

Microwave photonic synthetic aperture radar (MWP-SAR) offers a larger signal bandwidth than conventional SAR, and its theoretical resolution can be improved to centimeter level. To achieve same order of magnitude resolution in the azimuth direction, long synthetic aperture is always required, which results in extremely high requirements for the accuracy of imaging procedure. Compared with the conventional

Remote sensing image super-resolution (SR) aims to boost the image resolution while recovering rich high-frequency details. Currently, most of the SR methods are based on an assumption that the degradation kernel is a specific downsampler. However, the degradation kernel is unknown and sophisticated for real remote sensing scenes, leading to a severe performance drop. To alleviate this problem, we

Seismic data interpolation and denoising play vital roles in obtaining complete and clean data in seismic data processing. Seismic data usually miss along various spatial axes and always mix with random noise. To obtain complete and clean seismic data, reconstruction technology can interpolate missing data and attenuate random noise. A nonsubsampled contourlet transform (NSCT) is an effective transform

Building extraction is an essential task due to its relevance to urban planning and automatic surveying mapping activities. Despite the existing convolutional neural network-based methods that have achieved remarkable progress on building extraction from remote sensing images, the accurate extraction of buildings with extremely large variations of scales and layouts is still challenging. In this study

Subsidence of the gob area is an important geological problem in coal mines. Such events not only pose potential safety risks, but also can seriously impair the subsequent mining of coal mines. Therefore, detection of gob subsidence is important to ensure sustainable coal mining. Due to the complex seismic and geological conditions in the gob subsidence area, it is difficult to accurately identify

Graph neural networks (GNNs) are naturally distributed architectures for learning representations from network data. This renders them suitable candidates for decentralized tasks. In these scenarios, the underlying graph often changes with time due to link failures or topology variations, creating a mismatch between the graphs on which GNNs were trained and the ones on which they are tested. Online

Structured compressed sensing takes signal structure into account, thereby outperforming earlier compressed sensing methods. However, results are usually based on sampling in the Fourier domain, such as in Magnetic Resonance Imaging. In the time domain, the benefits of structured compressed sensing are still unknown. This paper introduces concepts that incorporate the signal structure into both the

Recently, vision-language models based on transformers are gaining popularity for joint modeling of visual and textual modalities. In particular, they show impressive results when transferred to several downstream tasks such as zero and few-shot classification. In this article, we propose a visual question answering (VQA) approach for remote sensing images based on these models. The VQA task attempts

This article presents a new method to retrieve dynamic information from spaceborne Doppler radar observations. The method is based on a complex convolution Doppler resampling (CConDoR) formulation, which links the spaceborne pulse-pair (PP) correlation measurements to high-resolution PP products that are not affected by the spacecraft motion. The CConDoR formalism allows to easily simulate Doppler

Ambiguity clutter for airborne radar systems is usually caused by a uniform pulse repetition interval (UPRI) waveform, which significantly degrades target detection and location performance. To address this issue, this article proposes an ambiguity clutter suppression method resorting to a pseudorandom pulse repetition interval (PrPRI) waveform. First, an airborne radar clutter model accounting for

Fine-grained image classification can be considered as a discriminative learning process where images of different subclasses are separated from each other while the same subclass images are clustered. Most existing methods perform synchronous discriminative learning in their approaches. Although achieving promising results in fine-grained visual classification (FGVC) in natural images, these methods

Recently, many state-of-the-art results for remote sensing image scene classification have been achieved by convolutional neural networks (CNNs) due to their large learning capability. However, in the forward process of CNNs, the high-frequency/texture features are gradually blurred with hierarchical downsampling and convolution operations. High-frequency features are important to capture the diversity

In this paper, an effective joint radar assignment and power scheduling (JRAPS) scheme is proposed for the multi-target tracking (MTT) task in multi-radar systems (MRSs) under imperfect detection, namely, target related measurements are collected with the probability of detection ($\boldsymbol{P}_{\boldsymbol{D}}$) less than 1. The centralized fusion architecture is adopted by the MRS. Specifically

Nowadays, benefiting from its strong capability of nondestructive detection, the ground-penetrating radar (GPR) has been applied to detect and reconstruct underground targets and has drawn lots of attention both in military and civilian fields. However, in the processing of GPR imaging, due to the dispersion errors caused by random distribution of various particles in soil, conventional imaging methods

In recent years, the powerful nonlinear modeling capability of convolutional neural networks (CNN) has led to an increasing number of researchers focusing on deep-learning-based pansharpening methods. However, due to the diversity of remote sensing image features and the limitations of the convolution operation, the existing methods are still inadequate in restoring the spatial details of complex remote

In recent years, more concerns are shed on the lightweight detection model in remote sensing (RS), but it is difficult to reach a competitive performance relative to the deep model. Knowledge distillation has been verified as a promising method, which can promote the performance of the lightweight model without extra parameters. While there are two key issues of detection distillation, one is the sample

Currently, the spaceborne synthetic aperture radar (SAR) system transmits a great deal of data to the ground processing station and generates massive images daily, only a tiny fraction of which contains radio frequency interference (RFI). However, most of the existing RFI detection methods are based on the prior conditions in which the known image contains interference. In fact, it is difficult to

With the development of deep learning (DL) technology, the feature extraction capability of networks has gradually been enhanced, and high accuracy has been achieved in signal modulation classification (SMC) tasks. DL requires numerous training samples to achieve high classification accuracy. However, in non-cooperative cases, only a few labeled data are usually available. To solve this problem, we

Lippmann (or interferential) photography is the first and only analog photography method that can capture the full color spectrum of a scene in a single take. This technique, invented more than a hundred years ago, records the colors by creating interference patterns inside the photosensitive plate. Lippmann photography provides a great opportunity to demonstrate several fundamental concepts in signal

With the popularity of (hyperspectral) remote sensing systems coupled with a myriad of applications comes the need for investigations into hyperspectral system designs and parameter trade-off studies. Analytical models based on statistical descriptions and signal propagation are efficient methods to examine these parameter trade-off studies, as well as sensitivity studies, with low computational cost

The observation of coastal waters using satellite remote sensing is of primary importance to gain understanding on the complex processes occurring in those highly dynamical ecosystems. The analysis of ocean color data relies on the interaction between the incident sunlight daytime radiation that propagates within the ocean–atmosphere system and the suspended material (hydrosols and aerosols) present

This study aims at estimating the dry snow water equivalent (SWE) by using X-band synthetic aperture radar (SAR) data from the COSMO-SkyMed (CSK) satellite constellation. The time series of CSK acquisitions have been collected during the dry snow period in the Alto Adige test site, in the Italian Alps, during the winter seasons from 2013 to 2015 and from 2019 to 2021. The SAR data have been analyzed

In this article, a spatial-temporally varying generalized Pareto intensity distribution (STV-GPID) model is presented to characterize large-scene sea clutter in high-resolution maritime surveillance radars, and a multiscan recursive Bayesian bipercentile (MSRB-BiP) estimation method is proposed to implement the outlier-robust estimation of parameters in the STV-GPID model. Considering that sea clutter

Deep learning has achieved promising performance in hyperspectral image (HSI) classification. Training deep models usually requires labeling massive HSIs, which, however, is prohibitively time-consuming and expensive. To fill in the gap, this article proposes a novel meta-learning method for HSI few-shot classification that conducts HSI classification with a few labeled samples. Specifically, we introduce

This research introduces a novel oblique longwave infrared (LWIR) atmospheric compensation (AC) technique for hyperspectral imagery, oblique in-scene AC (OISAC). Current AC algorithms have been developed for nadir-viewing geometries, which assume that every pixel in the scene is affected by the atmosphere in nearly the same manner. However, this assumption is violated in oblique imaging conditions

Although there are plenty of approaches proposed for addressing seismic volumetric dip estimation, it still suffers from several limitations, for example, the expensive computation cost, the perturbations from sequence stratigraphic anomalies, and the difficulty for handling the complicated geologic structures. Recently, deep learning (DL)-based models have been proposed for seismic dip estimation

Since the start of the Sentinel-1 (S-1) mission, numerous cases of severe image degradation caused by radio frequency interference (RFI) have been reported, which puts forward an urgent need for RFI identification and mitigation. In this article, an automatic RFI identification method is proposed based on a Siamese-type deep convolutional neural network (Siam-CNN-RIM). The Siam-CNN-RIM can be served

Change detection in synthetic aperture radar (SAR) images is an essential task of remote sensing image analysis. However, the thresholding procedure is the main difficulty in change detection for a few changed areas for traditional change detection methods. In this article, we propose a novel change detection method for very few changed or even none changed areas. The proposed method contains three