While it becomes more challenging to improve the energy efficiency of incremental delta-sigma data converters (IDCs) from the analog circuit design perspective, we propose two novel linear reconstruction filters for IDCs to enhance their performance in a digital way, including the L ${}_{\mathbf{2}}$ min ${}^{\mathbf{2}}$ filter and its symmetric version, the L ${}_{\mathbf{2}}$ min ${}^{\mathbf{2s}}$

Deep learning (DL) has been extensively used for hyperspectral image classification (HSIC) with significant success, but the classification of high-dimensional hyperspectral image (HSI) datasets with a limited amount of labeled samples is still a great challenge. Few-shot learning (FSL) has shown excellent performance in solving small-sample classification problems. However, most of the existing FSL

Hyperspectral images (HSIs) are typically utilized in a wide variety of practical applications. HSI is replete with spatial and spectral information, which provides precise data for material detection. HSIs are characterized by a high degree of variations and undesirable pixel distributions, providing major processing challenges. This article introduces the fast hyperspectral image classification (FHIC)

Deep-learning-based methods have attracted increasing attention on hyperspectral unmixing, where the transformer models have shown promising performance. However, recently proposed deep-learning-based hyperspectral unmixing methods usually tend to directly apply visual models, while ignoring the characteristics of hyperspectral imagery. In this article, we propose a novel double-aware transformer for

In recent years, in order to solve the problem of lacking accurately labeled hyperspectral image data, self-supervised learning has become an effective method for hyperspectral image classification. The core idea of self-supervised learning is to define a pretext task, which helps to train the model without the labels. By exploiting both the information of the labeled and unlabeled samples, self-supervised

Hyperspectral unmixing allows representing mixed pixels as a set of pure materials weighted by their abundances. Spectral features alone are often insufficient, so it is common to rely on other features of the scene. Matrix models become insufficient when the hyperspectral image (HSI) is represented as a high-order tensor with additional features in a multimodal, multifeature framework. Tensor models

In recent years, point clouds have been widely used in power-line inspection, smart cities, autonomous driving, and other fields. Deep learning-based point cloud processing methods have achieved some impressive results in point cloud semantic segmentation, which has attracted more and more attention. However, there are still some problems that need to be solved, such as the efficiency of point cloud

Generating 3-D city models rapidly is crucial for many applications. Monocular height estimation (MHE) is one of the most efficient and timely ways to obtain large-scale geometric information. However, existing works focus primarily on training and testing models using unbiased datasets, which does not align well with real-world applications. Therefore, we propose a new benchmark dataset to study the

The necessary prerequisite for effective data fusion is the strict registration of low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs). However, registration requires a complex process that takes into account the effects of light, imaging angle, and geometric distortion of the image during acquisition. Therefore, to avoid complex registration, we focused

Change detection (CD) by comparing two bitemporal images is a crucial task in remote sensing. With the advantages of requiring no cumbersome labeled change information, unsupervised CD has attracted extensive attention in the community. However, existing unsupervised CD approaches rarely consider the seasonal and style differences incurred by the illumination and atmospheric conditions in multitemporal

The freeze-thaw (F/T) process plays a significant role in climate change and ecological systems. The soil F/T state can now be determined using microwave remote sensing. However, its monitoring capacity is constrained by its low spatial resolution or long revisit intervals. In this study, spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) data with high temporal and spatial resolutions

Weakly supervised semantic segmentation (WSSS) based on image-level labels can reduce the expensive costs of annotating pixel-level labels, and it has achieved great progress by generating class activation maps (CAMs) as pseudo-labels for training a segmentation model. However, it is challenging to generate high-quality CAMs due to the large supervision gap between classification and segmentation.

Without sufficient data, the quantity of information available for supervised training is constrained, as obtaining sufficient synthetic aperture radar (SAR) training data in practice is frequently challenging. Therefore, current SAR automatic target recognition (ATR) algorithms perform poorly with limited training data availability, resulting in a critical need to increase SAR ATR performance. In

Hyperspectral images (HSIs) provide hundreds of continuous spectral bands and have been widely used for fine identification of targets with similar appearances. In earlier studies, convolutional neural networks (CNNs) have been an effective method for HSIs’ classification due to their powerful feature extraction capabilities. Recently, self-attention (SA)-based vision transformer (ViT) architecture

Convolutional neural networks (CNNs) are powerful in extracting local information but lack the ability to model long-range dependencies. In contrast, the transformer relies on multihead self-attention mechanisms to effectively extract the global contextual information and thus model long-range dependencies. In this article, we propose a novel encoder–decoder structured semantic segmentation network

In the study of deterministic sea waves, the predictable zone refers to the area where the phase-resolvable wave field can be fully reconstructed and accurately predicted based on measured data. Under certain marine environmental and radar measurement parameter conditions, expanding the predictable zone is of great significance for domains such as quiescent period prediction (QPP) for ships and optimizing

Change detection (CD) is an important Earth observation task that can monitor change areas at two times from the view of space. However, fully supervised CD has a heavy dependence on numerous manually labeled data, limiting their applications in practice. Beyond the fully supervised setting, semi-supervised CD (SSCD), which uses a few labeled data to guide the unsupervised learning of dominant unlabeled

Contrastive learning is a self-supervised comparison of two samples to identify characteristics and traits that distinguish one data class from another, improving performance on visual tasks. The performance of existing super-resolution-based approaches degrades with increasing scaling factors, hence practically not useful for high-resolution (HR) imaging applications. We proposed a novel framework

It is urgently needed to obtain the hourly near-real-time all-weather land surface temperature (NRT-AW LST) for immediately monitoring the disaster and environmental changes. Nevertheless, studies on estimating hourly NRT-AW LST are in the preliminary stage. In this study, we proposed a Spatio-TEmporal Fusion (STEF) method for fusing the reanalysis dataset derived from the China Land Surface Data Assimilation

High-frequency surface wave radar (HFSWR) as a maritime surveillance facility faces the tough challenges. One of them is that various unwanted echo components constantly destroy the detection performance of HFSWR, especially the dynamically changing ionosphere clutter. This article proposes an adaptive ionosphere clutter suppression and target detection algorithm (AICSTD) based on improved higher order

Unsupervised domain adaptation for remote sensing semantic segmentation seeks to adapt a model trained on the labeled source domain to the unlabeled target domain. One of the most promising ways is to translate images from the source domain to the target domain to align the spectral information or imaging mode by the generative adversarial network (GAN). However, source-to-target translation often

Hyperspectral unmixing (HSU) is an effective tool to ascertain the material composition of each pixel in a hyperspectral image with typically hundreds of spectral channels. In this article, we propose two graph-based semisupervised unmixing methods. The first one directly applies graph learning to the unmixing problem, while the second one solves an optimization problem that combines the linear unmixing

Single hyperspectral image (HSI) super-resolution (SR) is an important topic in the remote-sensing field. However, existing HSI SR methods mainly use the feed-forward upsampling technique and convolutional neural network (CNN) to learn the feature representation, failing to learn the complex mapping relationship between low-resolution (LR) and high-resolution (HR) and long-range joint spectral and

Uncertainty-aware semantic segmentation of the point clouds includes predictive uncertainty estimation and uncertainty-guided model optimization. One key challenge in the task is the efficiency of pointwise predictive distribution establishment. The widely used Monte Carlo (MC) dropout establishes the distribution by computing the standard deviation of samples using multiple stochastic forward propagations

Recognition of microseismic events is the primary task of microseismic monitoring. Aiming at the low signal-to-noise ratio (SNR) of weak microseismic events and the high cost of labeling them, an unsupervised learning method for recognizing microseismic events is proposed. The method first recognizes microseismic events from monitoring data segments by simultaneous deep clustering and then performs

A novel forest leaf area index (LAI) inversion scheme using polarimetric synthetic aperture radar (PolSAR) images is proposed. The advantage of inversion using synthetic aperture radar (SAR) images over conventional optical methods is the ability to perform all-weather and all-time forest observation, especially in the tropical rainforest area. In this article, leaves were assumed to be isotropic media

Mangrove mapping (MM) is a critical satellite remote sensing technology since mangrove forests have a large capacity for carbon storage among the blue carbon ecosystems. However, we surprisingly found that benchmark MM methods are all index-based ones, completely ignoring the spatially neighboring information on the one hand and quite sensitive to the threshold setting on the other hand. Deep learning

Deep learning (DL) has become increasingly popular in remote sensing (RS) change detection (CD), leading to the development of massive networks that surpass traditional methods in accuracy and automation. However, the need for enormous amounts of annotated data remains a major concern, and accurate boundary segmentation in RS images is challenging due to their complexity and heterogeneity. Moreover

Few-shot learning (FSL) is a method that does not require a large number of labeled samples and has the ability to identify unseen samples. Recently, many excellent FSL methods have been developed for remote sensing scene classification (RSSC). However, for complex remote sensing scenes, the following problems have not been well addressed: 1) the order of local features and the spatial correlation

Due to the powerful feature extraction and expression ability of convolutional neural networks (CNNs), exceptional success has been achieved in the field of ship automatic target recognition (ATR) of synthetic aperture radar (SAR). However, the CNNs cannot work effectively with sparse labeled samples and imbalanced categories. This study proposes a new attention-dense-CycleGAN (ADCG) method that is

The distributions of cloud phases play an important role in influencing the weather and climate system. The characteristics of clouds above the Tibetan Plateau (TP) can profoundly affect regional and global atmospheric circulation. To research the distributions of cloud phases in the TP region, a retrieval algorithm was developed based on the combination of polarization lidar and millimeter cloud radar

Fracture networks are omnipresent in unconventional energy reservoirs. The inversion of fractures is of vital importance to oil and gas exploration and production. Most of the existing inversion methods are developed based on homogeneous media theory and rely on a solitary physical descriptor. For instance, one commonly employed single-property inversion approach is the determination of water saturation

The ionosphere is a dynamic region of the Earth’s upper atmosphere that exhibits various fluctuations in electron density. These fluctuations can be estimated using measurements from the global navigation satellite system (GNSS). In this article, our focus is on characterizing the probability distribution of total electron content (TEC) fluctuations and their temporal duration. The findings of this

Underground coal fires are global catastrophes that result in energy waste, carbon emission, and eco-environment pollution. Remote sensing (RS) detection is essential for underground coal fire extinguishing engineering, and the most used is thermal infrared (TIR) RS. It can well obtain the thermal anomalies of land surface temperature (LST), which is the most direct surface feature of underground coal

Measurement of soil dielectric permittivity is frequently used as a basis for soil water content estimation by many commercial and experimental sensors. However, the relations between dielectric permittivity and soil water content may be affected by various other factors, including texture, salinity, and temperature. In this present article, spectra of complex dielectric permittivity of samples of

Due to the sparse feature enhancement only concentrating on strong scatterers of target of interest, the conventional sparsity-driven synthetic aperture radar (SAR) imagery often encounters the loss of elaborated-structure features, where weak scatterers would be overlapped by the sidelobes of strong scatterers. In this article, an elaborated-structure awareness SAR (ESA-SAR) imaging algorithm is proposed

Due to the intricate and uncertain nature of petrophysical properties, the practical application of petrophysical joint inversion poses significant challenges, and the realization of multigeophysical joint inversion methods is particularly demanding. In this study, we present an effective and versatile joint inversion method based on a coreference model and wide-range petrophysical constraints, building

Deep learning has become a popular method for studying the semantic segmentation of high-resolution remote sensing images (HRRSIs). Existing methods have adopted convolutional neural networks (CNNs) to achieve better segmentation accuracy of HRRSIs, and the success of these models often depends on the model complexity and parameter quantity. However, the deployment of these models on equipment with

Radiation transfer is an important physical basis for establishing the relationship between spectral and biochemical information. In this article, the interior of the blade is regarded as superimposed by layers with different optical characteristics. The PIOSL (PROSPECT considers the internal optical structure of the leaves) model was proposed, and the element-specific absorption coefficients in the

Object detection in aerial images has attracted increasing attention in recent years. Due to the complex background and arbitrary-oriented objects, it is challenging to accurately locate the objects of interest in the images. Many methods have been developed for improving localization accuracy of oriented objects. However, classification and localization tasks require different features due to the

With the development of deep learning (DL), research on ship classification in synthetic aperture radar (SAR) images has made remarkable progress. However, such research has primarily focused on classifying large ships with distinct features, such as cargo ships, containers, and tankers. The classification of SAR fishing vessels is extremely challenging because of two main reasons: 1) the small size

The interrupted sampling repeater jamming (ISRJ) can effectively degrade the image quality and affect the subsequent target recognition by creating deceptive multiple false targets on synthetic aperture radar (SAR) images. A time-domain filtering method based on pulse coding to counter ISRJ is proposed in this article. First, this coding method requires the radar to transmit a full pulse signal consisting

The multipath effect in Global Navigation Satellite System (GNSS) has become a robust data source thanks to GNSS interferometric reflectometry (GNSS-IR), which provides environment-related features by considering the interference pattern of direct and reflected signals recorded simultaneously on the antenna phase center (APC) of the GNSS receiver. When analyzing the fluctuation of the signal strength

Multispectral image pan-sharpening aims to increase the spatial details of multispectral images by fusing multispectral and panchromatic (PAN) images. Existing component substitution (CS)-based deep learning pan-sharpening is generally regarded as a black box and fails to mine the image interaction relation with physical significance in each step of pan-sharpening, which not only limits the improvement

Recently, interferometric altimeters (IAs), such as the surface water and ocean topography (SWOT) satellite, have been launched and will improve the observation of ocean dynamics. The validation of altimeters is a complex and important process that can effectively improve their observation accuracy. For the IA validation of sea surface height (SSH) in 2-D, it is normal to use the steric height (SH)

In recent years, Transformer-based networks, known for their ability to model long-range dependencies, have been widely used in downstream computer vision tasks, surpassing certain neural network architectures. However, Transformer-based networks suffer from issues, such as large parameter size, high-computational complexity (CC), and difficulties in extending spatial and channel features to the third

Visual question answering (VQA) aims to build an interactive system that infers the answer according to the input image and text-based question. Recently, VQA for remote sensing has attracted considerable attention since it is essential and expedient for monitoring global resources and querying objective attributes. In reality, question-related semantic information is helpful for reasoning and understanding

Hyperspectral image super-resolution (SR) using auxiliary RGB image has obtained great success. Currently, most methods, respectively, train single model to handle different scale factors, which may lead to the inconsistency of spatial and spectral contents when converted to the same size. In fact, the manner ignores the exploration of potential interdependence among different scale factors in a single

This article considers the problem of change detection (CD) with multisensor optical remote sensing (RS) images. Copulas are adopted to characterize the dependence structure between the image pair. For this problem, a conditional copula-based CD technique has been proposed in the literature; however, in this technique, it is difficult to select the best copula function in an analytical framework. Resulting

Three-dimensional gravity inversion is an effective method for extracting underground density distribution from gravity data. However, traditional deterministic gravity inversion methods suffer from problems such as skin effect, low computational accuracy, and poor efficiency. Therefore, we propose a 3-D gravity data focusing inversion algorithm based on the supervised descent method (SDM). SDM is

Acoustic logging is essential for probing formations surrounding a borehole. However, conventional logging signal processing methods cannot process inhomogeneous formation structures. Inspired by seismic full waveform inversion (FWI), this study proposed a novel borehole imaging algorithm called borehole full-waveform inversion (BFWI) to probe the near-formation properties surrounding boreholes. To

In the field of radar, nonlinearity has always been significant challenge in target tracking algorithms. It is evident in the complexity of the target motion model, observation model, and maneuverability of the target. Traditional model-based algorithms often rely on numerical approximations or simulations to obtain suboptimal solutions, which may lead to conversion errors and increase algorithm complexity

Inspired by animals’ long-distance migration behaviors, we proposed a novel and reliable long-distance true navigation method based on the measurement of geomagnetic fields. By establishing a 2-D gradient approaching a coordinate plane with geomagnetic intensity and inclination, long-distance true navigation can be achieved from any starting spot in this area. Without other calibration and auxiliary

When new unknown samples are captured continually in the open-world environment, the concept diversity accumulation of existing classes and the identification/creation of new concept classes should be considered simultaneously. Since the initial training set of existent classes may be underprepared, adhering to immediate decisions will inevitably lead to reduced open-set recognition (OSR) performance

The low-rank tensor model has made great progress for hyperspectral image (HSI) restoration. Recently, the low-rank tensor methods have further been boosted with subspace learning by transforming original HSI into a low-dimensional subspace with reduced computational burden and discriminative feature representation. However, existing subspace-based methods consistently employ a fixed subspace dimension

Multispectral Sentinel-2 (S-2) images are a valuable source of Earth observation data; however, spatial resolution of their spectral bands limited to 10-, 20-, and 60-m ground sampling distance (GSD) remains insufficient in many cases. This problem can be addressed with super-resolution (SR), aimed at reconstructing a high-resolution (HR) image from a low-resolution (LR) observation. For S-2, spectral

In the absence of a well-log-based low-frequency model, a broadband inversion strategy with a low-frequency model calculated in complicated frequency-domain inversion can successfully mine low-frequency seismic information and decrease the inversion results’ reliance on the starting model to some extent. Furthermore, from the standpoint of the equation, prestack nonlinear inversion based on the nonlinear

In this article, we reported a critical improvement on the measurement method for the dielectric dispersion characteristics of hydrate-bearing sediment in a frequency range between 1 MHz and 3 GHz, and, with the use of the method, a systematic evaluation of the microwave dielectric dispersion of the hydrate-bearing artificial sediment and influence factors. First, the optimized and verified procedure

Velocity model building is an indispensable part of seismic exploration, which can directly affect the accuracy of subsequent data processing. Traditional full-waveform inversion (FWI) is usually challenging to update the deep background velocity information. Moreover, deep learning (DL)-based velocity modeling efforts can face the problem of lacking generalization ability. Based on this, we propose

Sparse acoustic impedance (AI) inversion methods are widely used in seismic processing and interpretation. Due to the insufficiency of the sparse representation and absence of time–frequency domain prior information in traditional sparse inversion methods, the inversion results have low accuracy in pinch-out points and thin layers. To overcome these barriers, a multitrace AI inversion method based