Search Results (2,635)

Existing methods for reconstructing hyperspectral images from single RGB images struggle to obtain a large number of labeled RGB-HSI paired images. These methods face issues such as detail loss, insufficient robustness, low reconstruction accuracy, and the difficulty of balancing the spatial–spectral trade-off. To address these challenges, a Double-Gated Mamba Multi-Scale Adaptive Feature (DMMAF) learning network model is proposed. DMMAF designs a reflection dot-product adaptive dual-noise-aware feature extraction method, which is used to supplement edge detail information in spectral images and improve robustness. DMMAF also constructs a deformable attention-based global feature extraction method and a double-gated Mamba local feature extraction approach, enhancing the interaction between local and global information during the reconstruction process, thereby improving image accuracy. Meanwhile, DMMAF introduces a structure-aware smooth loss function, which, by combining smoothing, curvature, and attention supervision losses, effectively resolves the spatial–spectral resolution balance problem. This network model is applied to three datasets—NTIRE 2020, Harvard, and CAVE—achieving state-of-the-art unsupervised reconstruction performance compared to existing advanced algorithms. Experiments on the NTIRE 2020, Harvard, and CAVE datasets demonstrate that this model achieves state-of-the-art unsupervised reconstruction performance. On the NTIRE 2020 dataset, our method attains MRAE, RMSE, and PSNR values of 0.133, 0.040, and 31.314, respectively. On the Harvard dataset, it achieves RMSE and PSNR values of 0.025 and 34.955, respectively, while on the CAVE dataset, it achieves RMSE and PSNR values of 0.041 and 30.983, respectively. Full article

Hyperspectral image (HSI) and light detection and ranging (LiDAR) data offer complementary spectral and structural information; however, the integration of these high-dimensional, heterogeneous modalities poses significant challenges. We propose a Global–Local Mamba dual-modality fusion framework (GL-Mamba) for HSI–LiDAR classification. Each sensor’s input is decomposed into low- and high-frequency sub-bands: lightweight 3D/2D CNNs process low-frequency spectral–spatial structures, while compact transformers handle high-frequency details. The outputs are aggregated using a global–local Mamba block, a state-space sequence model that retains local context while capturing long-range dependencies with linear complexity. A cross-attention module aligns spectral and elevation features, yielding a lightweight, efficient architecture that preserves fine textures and coarse structures. Experiments on Trento, Augsburg, and Houston2013 datasets show that GL-Mamba outperforms eight leading baselines in accuracy and kappa coefficient, while maintaining high inference speed due to its dual-frequency design. These results highlight the practicality and accuracy of our model for multimodal remote-sensing applications. Full article

To improve the accuracy of detecting external defects in seed potatoes and address the reliance of current hyperspectral imaging methods on single-dimensional data, this study proposes a multi-dimensional spectral–spatial information fusion approach via concatenation based on a one-dimensional convolutional neural network (1DCNN) within the framework of deep learning. Hyperspectral three-dimensional data were acquired for normal seed potatoes and for samples presenting six types of external defects—decay, mechanical damage, wormhole, common scab, black scurf, and frostbite—across a wavelength range of 935–1721 nm. From the hyperspectral images, one-dimensional spectral data and two-dimensional spatial data were extracted. The one-dimensional spectral data were preprocessed using six methods: Savitzky–Golay smoothing (SG), standard normal variate (SNV), multiplicative scatter correction (MSC), first derivative (FD), second derivative (SD), and orthogonal signal correction (OSC). Feature wavelengths were subsequently selected through the successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS), serving as inputs for traditional machine learning models. Two-dimensional spatial data were first subjected to dimensionality reduction via principal component analysis (PCA). Texture features were then extracted from each principal component using the gray-level co-occurrence matrix (GLCM). Following normalization, all spatial texture data were fused with the preprocessed spectral data to form the inputs for the deep learning models Basic1DCNN and Stacked1DCNN. The results demonstrate that the fusion data with the Stacked1DCNN model yielded the best performance in identifying normal seed potatoes and six types of external defects. The overall accuracy, precision, recall, F1 score, and mean average precision reached 98.77%, 98.77%, 98.93%, 98.73%, and 99.66%, respectively, outperforming traditional machine learning approaches. Compared with the Stacked1DCNN model trained using spectral data alone, these metrics improved by 2.81%, 2.78%, 3.20%, 3.01%, and 1.11%. This study offers theoretical and technical insights into the development of automated sorting and non-destructive detection systems for seed potatoes. Full article

Lakes play a crucial role in maintaining agricultural irrigation water sources, regulating climate, and supporting the long-term resilience of regional ecosystems. However, accurately delineating the boundaries between lakes and land remains challenging due to seasonal hydrological fluctuations, spectral obfuscation with farmland, and the limitations of single-sensor methods. This study constructs a multi-source remote sensing framework integrating Sentinel-1 SAR, Sentinel-2 optical data, DEM, and key environmental variables to identify the water body, near-water body, and non-water surface of Weishan Lake, a major irrigation source in northern China. The study systematically compares various methods, including the optical index method, SAR-based threshold segmentation, and machine learning classifiers. The results show that the random forest model has higher accuracy and temporal robustness. Introducing the “near-water body” category allows for more accurate characterization of transitional areas sensitive to seasonal hydrological and agricultural processes. Migration tests of the model in three external lake systems demonstrate its strong generalization ability, while correlation analysis and SHAP-based analysis indicate that NDVI and elevation are the main factors influencing the spatial pattern of water and land. The proposed framework supports sustainable irrigation management by enabling accurate water boundary monitoring and enhancing the understanding of agricultural hydrological interactions. Full article

Coconut palms (Cocos nucifera L.) are a critical economic and ecological resource in Wenchang City, Hainan. Accurate mapping of their spatial distribution is essential for precision agricultural planning and effective pest and disease management. However, in tropical monsoon regions, persistent cloud cover, spectral similarity with other evergreen species, and redundancy among high-dimensional features hinder the performance of optical classification. To address these challenges, we developed a scalable multi-source remote sensing framework on the Google Earth Engine (GEE) with an emphasis on species-oriented feature design rather than generic feature stacking. The framework integrates Sentinel-1 SAR, Sentinel-2 MSI, and SRTM topographic data to construct a 42-dimensional feature set encompassing spectral, polarimetric, textural, and topographic attributes. Using Random Forest (RF) importance ranking and out-of-bag (OOB) error analysis, an optimal 15-feature subset was identified. Four feature combination schemes were designed to assess the contribution of each data source. The fused dataset achieved an overall accuracy (OA) of 92.51% (Kappa = 0.8928), while the RF-OOB optimized subset maintained a comparable OA of 92.83% (Kappa = 0.8975) with a 64% reduction in dimensionality. Canopy Water Index (CWI), Green Chlorophyll Index (GCI), and VV-polarized backscattering coefficient (${\mathsf{\sigma }}_{\mathrm{V}\mathrm{V}}$) were identified as the most discriminative features. Independent UAV validation (0.07 m resolution) in a 50 km² area of Chongxing Town confirmed the model’s robustness (OA = 90.17%, Kappa = 0.8617). This study provides an efficient and robust framework for large-scale monitoring of tropical economic forests such as coconut palms. Full article

Remote sensing acquires Earth surface information without physical contact through sensors operating at diverse spatial, spectral, and temporal resolutions. In high-resolution remote sensing imagery, objects often exhibit large scale variation, complex spatial distributions, and strong inter-class similarity, posing persistent challenges for accurate semantic segmentation. Existing methods still struggle to simultaneously preserve fine boundary details and model long-range spatial dependencies, and lack explicit mechanisms to decouple low-frequency semantic context from high-frequency structural information. To address these limitations, we propose the Multi-Perspective Information Fusion Network (MPIFNet) for remote sensing semantic segmentation, motivated by the need to integrate global context, local structures, and multi-frequency information into a unified framework. MPIFNet employs a Global and Local Mamba Block Self-Attention (GLMBSA) module to capture long-range dependencies while preserving local details, and a Double-Branch Haar Wavelet Transform (DBHWT) module to separate and enhance low- and high-frequency features. By fusing spatial, hierarchical, and frequency representations, MPIFNet learns more discriminative and robust features. Evaluations on the Vaihingen, Potsdam, and LoveDA datasets through ablation and comparative studies highlight the strong generalization of our model, yielding mIoU results of 86.03%, 88.36%, and 55.76%. Full article

Pansharpening plays a crucial role in remote sensing applications, as it enables the generation of high-spatial-resolution multispectral images that simultaneously preserve spatial and spectral information. However, most current methods struggle to preserve local textures and exploit spectral correlations across bands while modeling nonlocal information in source images. To address these issues, we propose a cascaded local–nonlocal pansharpening network (CLNNet) that progressively integrates local and nonlocal features through stacked Progressive Local–Nonlocal Fusion (PLNF) modules. This cascaded design allows CLNNet to gradually refine spatial–spectral information. Each PLNF module combines Adaptive Channel-Kernel Convolution (ACKC), which extracts local spatial features using channel-specific convolution kernels, and a Multi-Scale Large-Kernel Attention (MSLKA) module, which leverages multi-scale large-kernel convolutions with varying receptive fields to capture nonlocal information. The attention mechanism in MSLKA enhances spatial–spectral feature representation by integrating information across multiple dimensions. Extensive experiments on the GaoFen-2, QuickBird, and WorldView-3 datasets demonstrate that the proposed method outperforms state-of-the-art methods in quantitative metrics and visual quality. Full article

We present a novel framework for hyperspectral satellite image classification that explicitly balances spatial nearness with spectral similarity. The proposed method is trained on closed-set datasets, and it generalizes well to open-set agricultural scenarios that include both class distribution shifts and presence of novel and absence of known classes. This scenario is reflective of real-world agricultural conditions, where geographic regions, crop types, and seasonal dynamics vary widely and labeled data are scarce and expensive. The input data are projected onto a lower-dimensional spectral manifold, and a pixel-wise classifier generates an initial class probability saliency map. A kernel-based spectral-spatial weighting strategy fuses the spatial-spectral features. The proposed approach improves the classification accuracy by $7.22$–$15\%$ over spectral-only models on benchmark datasets. Incorporating an additional unsupervised learning refinement step further improves accuracy, surpassing several recent state-of-the-art methods. Requiring only 1–$10\%$ labeled training data and at most two tuneable parameters, the framework operates with minimal computational overhead, qualifying it as a data-efficient and scalable few-shot learning solution. Recent deep architectures although exhibit high accuracy under data rich conditions, often show limited transferability under low-label, open-set agricultural conditions. We demonstrate transferability to new domains—including unseen crop classes (e.g., paddy), seasons, and regions (e.g., Piedmont, Italy)—without re-training. Rice paddy fields play a pivotal role in global food security but are also a significant contributor to greenhouse gas emissions, especially methane, and extent mapping is very critical. This work presents a novel perspective on hyperspectral classification and open-set adaptation, suited for sustainable agriculture with limited labels and low-resource domain generalization. Full article

During the global transition of energy structures toward renewable sources, offshore wind power has experienced rapid advancement, coinciding with increasingly complex wave environments. This study focuses on the wave conditions of an offshore wind farm project in Vietnam. A dual-nested numerical framework (WAVEWATCH III + SWAN) is established, integrated with 32-year (1988–2019) high-resolution WRF wind fields and fused bathymetry data (GEBCO + in situ measurements). This framework overcomes the limitations of short-term datasets (10–22 years) in prior studies and achieves 1′ × 1′ (≈1.8 km) intra-farm resolution—critical for capturing topographic modulation of waves. A systematic analysis of the regional wave climate characteristics is performed, encompassing wave roses, joint distributions of significant wave height and spectral peak period, wave–wind direction correlations, and significant wave height–wind speed relationships. Extreme value theory, specifically the Pearson Type-III distribution, is applied to estimate extreme wave heights and corresponding periods for return periods ranging from 1 to 100 years, yielding critical design wave parameters for wind turbine foundations and support structures. Key findings reveal that the wave climate is dominated by E–SE (90°–120°) monsoon-driven waves (60% of $H_s$ = 0.5–1.5 m), while extreme waves are uniquely concentrated at 120°—attributed to westward Pacific typhoon track alignment and long fetch. For the outmost site (A55, 7.18 m water depth), the 100-year return period significant wave height ($H_{s100}$ = 4.66 m, $T_{p100}$ = 13.05 s) is 38% higher than sheltered shallow-water sites (A28, $H_{s100}$ = 2.7 m), reflecting strong bathymetric control on wave energy. This study makes twofold contributions: (1) Methodologically, it validates a robust framework for long-term wave simulation in tropical monsoon–typhoon regions, combining 32-year high-resolution data with dual-nested models. (2) Scientifically, it reveals the directional dominance and spatial variability of waves in the Mekong estuary, advancing understanding of typhoon–wave–topography interactions. Practically, it provides standardized design parameters (compliant with DNV-OS-J101/IEC 61400-3) for offshore wind projects in Southeast Asia. Full article

Hyperspectral image (HSI) target detection plays a critical role in both military and civilian applications, including military reconnaissance, environmental monitoring, and precision agriculture. However, the complex background of the scene severely restricts the further improvement of hyperspectral target detection performance. To address this challenge, we propose a diffusion model hyperspectral target detection method based on multivariate Gaussian background noise. The method constructs multivariate Gaussian-distributed background noise samples and introduces them into the forward diffusion process of the diffusion model. Subsequently, the denoising network is trained, the conditional probability distribution is parameterised, and a designed loss function is used to optimise the denoising performance and achieve effective suppression of the background, thus improving the detection performance. Moreover, in order to obtain accurate background noise, we propose a background noise extraction strategy based on spatial–spectral centre weighting. This strategy combines with the superpixel segmentation technique to effectively fuse the local spatial neighbourhood information of HSI. Experiments conducted on four publicly available HSI datasets demonstrate that the proposed method achieves state-of-the-art background suppression and competitive detection performance. The evaluation using ROC curves and AUC-family metrics demonstrates the effectiveness of the proposed background-suppression-guided diffusion framework. Full article

Remediated landfills require long-term monitoring due to ongoing processes such as settlement, water infiltration, leachate migration, and biogas emissions, which may lead to cover degradation and environmental risks. Traditional ground-based inspections are often time-consuming, costly, and limited in terms of spatial coverage. This study presents the application of Unmanned Aerial Vehicle (UAV)-based remote sensing methods for the structural assessment of a remediated landfill. A multi-sensor approach was employed, combining geometric data (Light Detection and Ranging (LiDAR) and photogrammetry), hydrological modeling (surface water accumulation and runoff), multispectral imaging, and thermal data. The results showed that subsidence-induced depressions modified surface drainage, leading to water accumulation, concentrated runoff, and vegetation stress. Multispectral imaging successfully identified zones of persistent instability, while UAV thermal imaging detected a distinct leachate-related anomaly that was not visible in red–green–blue (RGB) or multispectral data. By integrating geometric, hydrological, spectral, and thermal information, this paper demonstrates practical applications of remote sensing data in detecting cover degradation on remediated landfills. Compared to traditional methods, UAV-based monitoring is a low-cost and repeatable approach that can cover large areas with high spatial and temporal resolution. The proposed approach provides an effective tool for post-closure landfill management and can be applied to other engineered earth structures. Full article

Water availability critically affects basil (Ocimum basilicum L.) growth and physiological performance, making the early and precise monitoring of water-deficit responses essential for precision irrigation. However, conventional visual or biochemical methods are destructive and unsuitable for real-time assessment. This study presents a multimodal optical biosensing and 3D convolutional neural network (3D-CNN) fusion framework for phenotyping physiological responses of basil under water-deficit stress. RGB, depth, and chlorophyll fluorescence (CF) imaging were integrated to capture complementary morphological and photosynthetic information. Through the fusion of 130 optical parameter layers, the 3D-CNN model learned spatial and temporal–spectral features associated with resistance and recovery dynamics, achieving 96.9% classification accuracy—outperforming both 2D-CNN and traditional machine-learning classifiers. Feature-space visualization using t-SNE confirmed that the learned latent representations reflected biologically meaningful stress–recovery trajectories rather than superficial visual differences. This multimodal fusion framework provides a scalable and interpretable approach for the real-time, non-destructive monitoring of crop water stress, establishing a foundation for adaptive irrigation control and intelligent environmental management in precision agriculture. Full article

Owing to its substantial implications for black hole spectroscopy, spectral instability has attracted considerable attention in the literature. While the emergence of such instability is attributed to the non-Hermitian nature of the gravitational system, it remains sensitive to various factors. In this work, we conduct a focused analysis of black hole spectral instability using the Pöschl–Teller potential as a toy model. We investigate the dependence of the resulting spectral instability on the magnitude, spatial scale, and localization of deterministic and random perturbations in the effective potential of the wave equation, and discuss the underlying physical interpretations. It is observed that small perturbations in the potential initially have a limited impact on the less damped black hole quasinormal modes, with deviations typically around their unperturbed values, a phenomenon first derived by Skakala and Visser in a more restrictive context. In the higher-overtone region, the deviation propagates, amplifies, and eventually gives rise to spectral instability and, inclusively, bifurcation in the quasinormal mode spectrum. While deterministic perturbations give rise to a deformed but well-defined quasinormal spectrum, random perturbations lead to uncertainties in the resulting spectrum. Nonetheless, the primary trend of the spectral instability remains consistent, being sensitive to both the strength and location of the perturbation. However, we demonstrate that the observed spectral instability might be suppressed for perturbations that are physically appropriate. Full article

We demonstrate that pulsed laser annealing induces plasmonic gold nanoparticles in ZnO thin films, monitored in real-time via pulse-by-pulse spectroscopy. Initially embedded gold nanoparticles (smaller than 5 nm) in sputtered ZnO films were annealed using 532 nm pulses from a Q-switched Nd:YAG laser while monitoring transmission spectra in situ. A plasmonic resonance dip emerged after ~100 pulses in the 530–550 nm region, progressively deepening with continued exposure. Remarkably, different incident energies converged to a thermodynamically stable optical state centered near 555 nm, indicating robust nanoparticle configurations. After several hundred laser shots, the process stabilized, producing larger nanoparticles (40–200 nm diameter) with significant surface protrusion. SEM analysis confirmed substantial gold nanoparticle growth. Theoretical modeling supports these observations, correlating spectral evolution with particle size and embedding depth. The protruding gold nanoparticles can be functionalized to detect specific biomolecules, offering significant advantages for biosensing applications. This approach offers superior spatial selectivity and real-time process monitoring compared to conventional thermal annealing, with potential for optimizing uniform nanoparticle distributions with pronounced plasmonic resonances for biosensing applications. Full article

This study evaluates the use of UAV-based photogrammetry to document shallow submerged cultural heritage, focusing on the Tirpitz wreck salvage site near Håkøya, Norway. Using a DJI Phantom 4 Multispectral drone, we acquired RGB and multispectral imagery over structures located at depths of up to 5–10 m. Structure-from-motion (SfM) processing enabled the three-dimensional reconstruction of submerged features, including a 52 × 10 m wharf and adjacent debris piles, with an accuracy of the order of 10 cm. Our data represents the first and only accurate mapping of the site yet carried out, with an absolute position uncertainty estimated to be no greater than 3 m. Volumes of imaged debris could be estimated, using a background subtraction method to allow for variable bathymetry, at around 350 m³. Bathymetric data for the sea floor could be derived effectively from an SfM point cloud, though less effectively applying the Stumpf model to the multispectral data as a result of significant spectral variation in the sea floor reflectance. Our results show that UAV-based through-surface SfM is a viable, low-cost method for reconstructing submerged heritage with high spatial accuracy. These findings support the integration of UAV-based remote sensing into heritage and environmental monitoring frameworks for shallow aquatic environments. Full article