Search Results (5,675)

In response to the problems of insufficient fusion of amplitude and phase heterogeneity features, deficient direction sensitivity modeling, and a single fusion level in the polarimetric synthetic aperture radar classification task, this paper proposes a PolSAR classification method based on dynamic weight adjustment and heterogeneous feature fusion. This method utilizes a dual-branch parallel structure to extract polarization features and landcover amplitude-phase direction difference features separately and constructs a three-level progressive fusion strategy of sub-branch, cross-branch, and decision layer to achieve adaptive complementation of heterogeneous features. Experiments on three standard datasets show that the classification accuracy and visual consistency of this method are significantly superior to the classical methods, with the overall accuracy being improved by 1.5% to 2.4%. Full article

While global nutrient insufficiency remains a critical health challenge, eggs have emerged as a potential solution due to their profile as an accessible and nutrient-dense food source. To quantitatively assess this potential for mitigating nutrient insufficiencies and guide the production of nutrient-enriched eggs, the study proposes the concept of egg nutriomics, establishing a comprehensive evaluation system with 35 indicators across seven nutritional dimensions (fatty acids, amino acids, vitamins, trace elements, pigments, antioxidant capacity, and dietary restriction factors). Methodologically, the system normalizes raw analytical data into standardized scores (0–100) using indicator-specific functional models, with weights rationally allocated based on the essentiality of the nutrients. These quantitative metrics are subsequently translated into intuitive results using visualization tools such as heatmaps and radar charts. This study applied this system to evaluate six commercial egg varieties (pasteurized, lutein-enriched, ω-3 enriched, animal welfare, low-cholesterol, and conventional cage eggs), profiling multidimensional nutrition that allows for the intuitive visualization of performance scores across distinct dimensions. These profiles extend beyond comprehensive evaluation by revealing specific quantitative advantages—such as ω-3 enriched eggs scoring 79 in the fatty acid dimension compared to 49 for conventional eggs—thus providing a reference to guide precision modulation as illustrated by a dietary ω-3 enrichment case study involving 200 laying hens. Building upon this foundation, the strategy empowers a shift from the sole pursuit of high yields to precision nutritional modulation. This multi-dimensional strategy bridges nutritional analysis with production control, facilitating the development of nutrient-dense eggs as a potential application to mitigate human malnutrition. Full article

The dielectric properties of cement-based composites (CBC) are highly sensitive to environmental humidity, which seriously restricts the quantitative interpretation accuracy of ground-penetrating radar (GPR) in the non-destructive testing of cement concrete pavement. In view of the lack of targeted prediction models due to the unclear mechanism of humidity influence in existing research, the core innovations of this study are: (1) the synergistic mechanism of water vapor dipole polarization and adsorbed water multi-layer polarization is clarified, revealing the intrinsic reason for the accelerated growth of permittivity in the high humidity range; (2) the constructed four-component dielectric model of “cement mortar–aggregate–water vapor–adsorbed water” achieves high-precision prediction within the range of 50~100% RH (R² > 0.94, relative error < 5%), and shows good predictive ability within the test scope of this study; (3) a GPR humidity correction protocol based on the model is proposed, which can effectively improve the accuracy of nondestructive testing of cement concrete structures. In this study, CBC samples with water–cement ratios of 0.4~0.6 were prepared using P.O 32.5/P.O 42.5 cement and limestone aggregate. Under the conditions of 20 ± 0.5 °C, relative humidity (RH) of 50~100%, and 2 GHz (common GPR frequency), the permittivity was measured using an Agilent P5001A network analyzer to verify the model. The results show that the permittivity increases monotonically with humidity, and the growth rate in the high humidity range (70~100%) is 2.2 times that of the low humidity range (50~70%); The higher the water–cement ratio, the shorter the age, and the lower the cement strength grade, the stronger the humidity sensitivity of CBC dielectric properties. This model provides a reliable humidity correction tool for GPR detection, and significantly improves the accuracy of nondestructive evaluation of cement concrete structures. Full article

Synthetic Aperture Radar (SAR) ship classification plays a critical role in maritime surveillance, addressing challenges such as the similarity between ship categories, as well as scarcity of annotated datasets and data imbalance. In this paper, a lightweight and real-time dual-branch architecture is proposed to effectively address the SAR ship classification task. The proposed approach integrates dual-polarization data within a hybrid convolution-transformer framework to improve classification performance. The model fuses dual-polarization modes, combining convolutional layers for local feature extraction with transformer blocks for global contextual understanding. Evaluations on the OpenSARShip 2.0 dataset show that the proposed model achieves 97.50% accuracy in the 3-class configuration and 93.28% in the 6-class configuration. For the FUSAR-Ship dataset, which does not provide dual-polarization data for the same ship target, the single branch model achieved an accuracy of 94.92% for the 7-class configuration. Despite its dual-branch design, the model maintains computational efficiency, making it suitable for real-time maritime monitoring applications. The results demonstrate the effectiveness of polarization-aware hybrid models for scalable and robust SAR ship classification. Full article

Digital elevation models (DEMs) are foundational for critical tasks such as flood inundation simulation, disaster risk assessment, and ecosystem monitoring in coastal zones, yet their vertical accuracy is significantly compromised by complex terrain and surface characteristics. This study quantitatively decomposes the vertical errors of three 30 m global DEMs (COP30, NASADEM, and AW3D30) across the subtropical coastal region of Southeast China using ICESat-2 ATL08 data as a reference. By integrating an eXtreme Gradient Boosting (XGBoost) model with SHapley Additive exPlanations (SHAP), we successfully decoupled systematic biases from random noise. The results show that NASADEM achieved the lowest RMSE (7.775 m), followed by COP30 and AW3D30. While the Terrain Ruggedness Index (TRI) and categorically encoded Land Cover were identified as the universally dominant error drivers across all datasets, explainable analysis revealed distinct secondary mechanisms: X-band COP30 is notably susceptible to canopy height, exhibiting significant positive bias in forests exceeding 15 m; C-band NASADEM shows a systematic bias related to topographic position, typically overestimating ridges and underestimating valleys; and optical AW3D30 is significantly affected by stereo-matching errors. Furthermore, the analysis quantified a systematic error component of ~40%. These findings provide a data-driven basis for DEM selection and highlight that accuracy improvements should prioritize vegetation removal for radar DEMs and enhanced stereo-matching for optical models. Full article

Tornado is a localized, small-scale severe convective weather phenomenon characterized by extreme destructiveness. Tornado detecting and warning mainly rely on Doppler weather radar, which identifies and tracks tornadoes by recognizing the tornado vortex signature and supercells in radar data. Artificial intelligence technology has been applied to tornado recognition in recent years. However, existing monitoring methods, especially those using unsupervised learning algorithms, still have limited recognition accuracy and timely warning, and usually struggle to strike a balance between detection accuracy and false alarm rate. A novel tornado detection algorithm TDA-DARKNet has been proposed to address the aforementioned issues. The algorithm integrates a dual attention mechanism, dense residual connections, and Kolmogorov–Arnold network (KAN). A tornado dataset suitable for deep learning has been formed, which utilizes features including radial velocity, reflectivity, velocity spectrum width, differential reflectivity, and correlation coefficient in radar data. The TDA-DARKNet algorithm was trained and tested using the tornado dataset, and evaluated in tornado cases. The experimental results show that TDA-DARKNet improves the detection probability and extends the lead time to a maximum of 42 min in strong tornado situations, while achieving 97.11% accuracy, 95.08% precision, indicating strong overall identification performance. In addition, by directly leveraging radar-based data for tornado identification, the algorithm eliminates the need for manual feature engineering, simplifies data processing, reduces complexity, and further enhances detection effectiveness. Full article

Atmospheric refractivity governs the propagation behavior of electromagnetic waves in the lower troposphere. Accurate spatial characterization of this parameter is essential for optimizing communication, radar, and navigation systems. This study presents a geostatistical framework for generating high-resolution refractivity maps using Universal Kriging (UK) applied to meteorological observations from a dense network of automatic weather stations in the Galician region (NW Spain). The methodology explicitly models the non-stationary vertical structure of the atmosphere by decomposing the refractivity field into a deterministic altitude-dependent drift and a stochastic residual component characterized by an exponential variogram. Validation, performed using independent test stations bounding the regional vertical profile, demonstrates that the UK approach significantly outperforms Ordinary Kriging (OK). UK not only reduces mean errors and improves linear agreement, but critically minimizes systematic bias and extreme outlier occurrences ($P_{95}$). Beyond accurate spatial interpolation, the dynamically estimated vertical drift retrieves the macroscopic refractivity gradient, serving as a direct, real-time diagnostic tool to classify anomalous radio-frequency (RF) propagation regimes (e.g., super-refraction and ducting) and supporting robust decision-making in complex topographies. Full article

Accurate precipitation nowcasting plays an important role in disaster prevention and hydrometeorological applications, yet it remains highly challenging due to the complex spatiotemporal variability and multi-scale structural characteristics of precipitation systems. Existing deep learning methods are largely data-driven and often struggle to effectively exploit multi-source observations or learn physically meaningful representations. To address these limitations, this study proposes a Multi-Scale Frequency–Temporal Network (MS-FTNet) for precipitation nowcasting. The framework leverages Fourier transform-based frequency-domain modeling to achieve an interpretable multi-scale decomposition of precipitation dynamics. Specifically, low-frequency components capture large-scale stratiform patterns and their temporal evolution, while high-frequency components represent localized convective structures and abrupt variations. Building on this, a Global Feature Collaboration (GFC) module integrates global frequency-domain representations with multi-scale convolutional features, and an Adaptive Temporal Fusion (ATF) module enhances temporal dependency modeling. Experiments on the SEVIR dataset demonstrate that MS-FTNet consistently outperforms representative baseline models in terms of MSE, CSI, and LPIPS, particularly for heavy precipitation events and longer forecast lead times. Full article

The resolution and accuracy of airborne/spaceborne SAR are continuously improving, making it an effective means for observing ocean dynamic processes and detecting marine targets. In contrast, utilizing its unique orbital angular momentum (OAM) mode, vortex radar does not require temporal accumulation to achieve azimuthal resolution, making it particularly suitable for observing moving sea surfaces. This capability enables stable and continuous monitoring of dynamic ocean scenes. This paper proposes a vortex radar imaging method based on three-dimensional sea surface scattering characteristics: first, a three-dimensional wind-driven sea surface geometric model is established based on the Elfouhaily sea spectrum, and its scattering characteristics under different incident angles, wind speeds, and wind directions are analyzed using the semi-deterministic facet-based two-scale method; then, two-dimensional range-azimuth imaging is achieved through coordinate transformation, echo modeling, pulse compression, and fast Fourier transform (FFT) in OAM mode domain, with the correctness of the imaging algorithm verified through multiple point target imaging results. Finally, simulation results of two-dimensional sea surface vortex imaging under different incident angles are presented, and the influence of wind speed and direction on sea surface vortex imaging is analyzed. The study shows that the vortex imaging system can effectively reflect wave fluctuations and wind direction characteristics, demonstrating the feasibility and potential of vortex radar imaging in oceanographic applications. Full article

The Taoping paleo-landslide poses a significant risk to local residents and critical infrastructure. However, traditional field surveys and deformation monitoring methods are often inadequate for capturing subtle, localized deformation characteristics—particularly at the head scarp and lateral margins—thereby limiting comprehensive assessments of slope instability. Surface strain data offer direct insights into internal stress redistribution during slope evolution and are essential for interpreting landslide mechanisms and forecasting failure. Given the current limitations in dense and wide-area strain monitoring technologies, this study proposes a novel method for modeling landslide strain fields based on Interferometric Synthetic Aperture Radar (InSAR) phase gradients. Using the phase gradient stacking approach, InSAR-derived phase gradients are transformed into strain-related parameters, enabling estimation of shear strain rates, principal strain rates, and their directional distributions. The application to the Taoping paleo-landslide reveals clear spatial patterns of compressive and tensile strain across the landslide body. Field investigations corroborate the InSAR-derived strain features through corresponding geomorphological evidence observed in both compressional and extensional zones. The proposed method enhances the understanding of landslide deformation behavior, supports evaluation of shear surface continuity and evolution, and offers a robust framework for early warning and risk mitigation in complex landslide-prone areas. Full article

Accurate estimation of forest soil organic carbon (SOC) is considered critical for understanding terrestrial carbon cycling and supporting climate change mitigation strategies. However, the canopy block, intricate vertical structure of forests, and the constraints of single-source remote sensing data have presented considerable obstacles for estimating forest SOC. This study proposes a forest SOC estimation and uncertainty analysis (ForSOC-UA) framework to enhance forest SOC estimation and quantify its uncertainty in the natural secondary forests of northern China by integrating hyperspectral imagery (ZY-1F), synthetic aperture radar data (Sentinel-1), and environmental covariates (such as topography, vegetation, and soil indices). The performance of traditional machine learning models (RF, SVM, and CNN), geographically weighted regression (GWR), and a geographically weighted random forest (GWRF) model was compared across three different soil depths (0–5 cm, 5–10 cm, and 10–30 cm). The results showed that GWRF consistently outperformed all other models across all soil depth layers, with the highest accuracy achieved using multi-source data (R² = 0.58, RMSE = 27.49 g/kg, rRMSE = 0.31). Analysis of feature importance revealed that soil moisture, terrain characteristics, and Sentinel-1 polarization attributes were the primary predictors, while spectral derivatives in the red and near-infrared bands from ZY-1F also played a significant role for forest SOC estimation. The uncertainty analysis indicated a forest SOC estimation uncertainty of 37.2 g/kg in the 0–5 cm soil layer, with a decreasing trend as depth increased. This pattern is associated with the vertical spatial distribution of the measured forest SOC. This integrated approach effectively captures spatial heterogeneity and nonlinear relationships between feature and forest SOC, while also assessing estimation uncertainty, so providing a robust methodology for predicting forest SOC. The ForSOC-UA framework addresses the uncertainty quantification of SOC estimation at different vertical depths based on machine learning, providing methodological enhancements for the assessment of large-scale forest SOC and the monitoring of carbon sinks within forest ecosystems. Full article

Lake ice monitoring is critical for assessing climate change, but in-situ observations are often limited. Sentinel-1 Synthetic Aperture Radar (SAR) data is a strong method for ice detection because it is not restricted by cloud cover and it is readily available. However, SAR-based classification can be affected by atmospheric and surface-related noise. This study examines the impact of noise on machine learning-based lake ice detection over Lake Śniardwy, Poland, using Sentinel-1 Vertical-Vertical (VV) and Vertical-Horizontal (VH) backscatter data. Binary logistic regression models were trained on scenes with strong class separability between ice and water and then validated on separate low- and high-noise datasets. The models achieved high accuracy under low-noise scenes, reaching up to 96.9%, but performed poorly on high-noise scenes. The results show that wind-related surface roughness and associated atmospheric conditions can significantly reduce classification reliability. Comparison with backscatter from a nearby coniferous forest confirmed that the main disturbances were concentrated over the lake surface. The study highlights the importance of careful scene selection and noise assessment in SAR-based lake ice classification. Full article

Remote sensing object detection is fundamental to Earth observation, yet remains challenging when relying on a single sensing modality. While optical imagery provides rich spatial and textural details, it is highly sensitive to illumination and adverse weather; conversely, Synthetic Aperture Radar (SAR) offers robust all-weather acquisition but suffers from speckle noise and limited semantic interpretability. To address these limitations, we leverage the potential of foundation models for optical–SAR object detection via a novel gated–guided fusion approach. By integrating transferable and generalizable representations from foundation models into the detection pipeline, we enhance semantic expressiveness and cross-environment robustness. Specifically, a gated–guided fusion mechanism is designed to selectively merge cross-modal features with foundational priors, enabling the network to prioritize informative cues while suppressing unreliable signals in complex scenes. Furthermore, we propose a dual-stream architecture incorporating attention mechanisms and State Space Models (SSMs) to simultaneously capture local and long-range dependencies. Extensive experiments on the large-scale M4-SAR dataset demonstrate that our method achieves state-of-the-art performance, significantly improving detection accuracy and robustness under challenging sensing conditions. Full article

During the interpretation of Borehole Radar (BHR) B-scan profiles, the accurate determination of the azimuth of geological targets in three-dimensional space is a critical issue for achieving precise anomaly localization and spatial structure inversion. However, existing directional BHR anomaly localization methods exhibit limited intelligence, insufficient adaptability to multi-site data, and weak generalization capability, rendering them inadequate for engineering applications under complex geological conditions. To address these challenges, a robust deep learning model, termed BSS-Pose-BHR, is developed based on YOLOv11n-pose for keypoint detection in directional BHR profiles. The model incorporates three key optimizations: Bi-Level Routing Attention (BRA) replaces Multi-Head Self-Attention (MHSA) in the backbone to improve computational efficiency; Conv_SAMWS enhances keypoint-related feature weighting in the backbone and neck; and Spatial and Channel Reconstruction Convolution (SCConv) is integrated into the detection head to reduce redundancy and strengthen local feature extraction, thereby improving suitability for keypoint detection tasks. In addition, a three-dimensional electromagnetic model of limestone containing a certain density of clay particles is established to construct a simulation dataset. On the simulated test set, compared with current mainstream deep learning approaches and conventional directional borehole radar anomaly localization algorithms, BSS-Pose-BHR achieves superior performance, with an mAP50(B) of 0.9686, an mAP50–95(B) of 0.7712, an mAP50(P) of 0.9951, and an mAP50–95(P) of 0.9952. Ablation experiments demonstrate that each proposed module contributes significantly to performance improvement. Compared with the baseline, BSS-Pose-BHR improves mAP50(B) by 5.39% and mAP50(P) by 0.86%, while increasing model weight by only 1.05 MB, thereby achieving a reasonable trade-off between detection accuracy and complexity. Furthermore, indoor physical model experiments validate the effectiveness of the method on measured data. Robustness experiments under different Peak Signal-to-Noise Ratio (PSNR) conditions and varying missing-trace rates indicate that BSS-Pose-BHR maintains high detection accuracy under moderate noise and data loss, demonstrating strong engineering applicability and practical value. Full article

The accuracy of Digital Elevation Models (DEMs) plays a crucial role in determining their reliability for geoscientific and engineering applications. Next-generation distributed interferometric synthetic aperture radar (SAR) constellations, such as the PIESAT-1 wheel constellation with its “one primary, three secondary” setup, provide a novel method for efficiently acquiring high-precision DEMs. However, a comprehensive and systematic performance evaluation of DEMs derived from such an innovative constellation is lacking, particularly in the context of comparative studies under complex terrain conditions. This study uses PIESAT-1 SAR imagery to generate a 10 m resolution DEM through multi-baseline interferometric processing. The ICESat-2 ATL08 dataset serves as the reference baseline, and mainstream products, including ZY-3, GLO-30, TanDEM-X DEM, and AW3D30, are incorporated for a multidimensional vertical accuracy evaluation, considering land cover, slope, aspect, and topographic profiles. The results indicate that, in three representative mountainous regions, the PIESAT-1 DEM achieves optimal overall accuracy (RMSE = 3.25 m). Furthermore, in regions with significant radar geometric distortions, such as south-facing slopes, vegetation-covered areas, and regions with noticeable anthropogenic topographic changes, the PIESAT-1 DEM demonstrates superior stability and information capture capabilities relative to conventional single- or dual-baseline SAR systems. This study validates the technological potential of the PIESAT-1 wheel constellation in enhancing DEM accuracy and terrain adaptability, and provides insights for the scientific selection of high-resolution topographic data and the design of future spaceborne interferometric missions. Full article