Hongtao Shi

A B S T R A C TSpaceborne GNSS-Reflectometry (GNSS-R) is a powerful tool for soil moisture (SM) retrieval. However, complex topography and steep slopes over the Tibetan Plateau lead to significant signal loss and sampling sparsity. This study proposes a novel Dirichlet-prior-guided Vision Transformer (DG-ViT) framework to integrate multi-source observations from CYGNSS, Tianmu-1, and the FY-3E/F/G constellation. By incorporating land-cover-based prior weights into a gated fusion mechanism, the DG-ViT enhances physical consistency, significantly outperforming both traditional machine learning fusion methods and the standard ViT architecture without prior weights. To assess generalization, the fused surface reflectivity (SR) was coupled with six mainstream machine learning algorithms (RF, XGBoost, ANN, BP, SVM, and GBDT) for SM retrieval, with multi-scale validation conducted against ERA5 SM and nine in-situ stations. Results demonstrate that the DG-ViT framework achieves a daily SR coverage of 89.49%, representing an improvement of 20.13% and 14.32% over standalone CYGNSS and Tianmu-1 data, respectively. In addition, this fusion strategy overcomes the coverage gap of CYGNSS north of 38°N and compensates for the inability of individual FY-3 missions to support daily SM retrieval. In comparative assessments, the DG-ViT combined with RF yields superior performance (R=0.955, RMSE=0.039 cm3/cm3, bias=0.000 cm3/cm3), markedly enhancing retrieval accuracy relative to results derived from single-source CYGNSS or Tianmu-1 SR. In-situ validation shows ubRMSE values between 0.0232 and 0.0619 cm3/cm3, a 15.1% precision gain over ERA5 SM. The proposed DG-ViT combined with RF approach effectively exploits the complementarity among multi-spaceborne GNSS-R observations over the Tibetan Plateau, thereby compensating for the signal deficiencies of individual missions. This integrated approach provides a novel perspective for soil moisture retrieval in high-altitude areas, specifically addressing the intricate non-linear relationships between surface reflectivity and soil moisture.

Spatiotemporal fusion integrates multi-source remote sensing data to produce imagery that simultaneously possesses high spatial and temporal resolution. However, existing spatiotemporal fusion approaches still face limitations in reconstructing abrupt land-cover changes while preserving spatial structures, which become more pronounced under extreme events, often leading to structural distortions and error propagation. A hierarchical residual-driven spatiotemporal fusion (HRSF) framework is proposed to address these limitations. The framework integrates temporal extrapolation with spatial residual redistribution, under the guidance of object-level structural constraints and a pixel-level adaptive propagation mechanism, in which temporal extrapolation, object-level residual redistribution, pixel-level adaptive residual propagation, and a spectrally weighted refinement module are progressively designed to establish a bidirectional coupling between temporal variation and spatial structure, thereby achieving unified modeling of structural preservation and change reconstruction. Furthermore, building upon pixel-level residual redistribution, a dual-ranking consistency strategy is introduced to ensure stable and physically consistent similar-pixel selection, imposing both explicit and implicit constraints on residual propagation. HRSF is evaluated against five state-of-the-art spatiotemporal fusion methods across three distinct landscapes. Quantitative results demonstrate that HRSF consistently outperforms existing approaches, achieving both higher accuracy and superior structural preservation. Overall, HRSF effectively balances spatial structural stability and spectral consistency, enabling high-fidelity spatiotemporal fusion for dynamic environmental monitoring. The Python code of HRSF and the experimental dataset are available at https://github.com/paboooo/HRSF.

Spatiotemporal fusion integrates multi-source remote sensing data to produce imagery that simultaneously possesses high spatial and temporal resolution. However, existing spatiotemporal fusion approaches still face limitations in reconstructing abrupt land-cover changes while preserving spatial structures, which become more pronounced under extreme events, often leading to structural distortions and error propagation. A hierarchical residual-driven spatiotemporal fusion (HRSF) framework is proposed to address these limitations. The framework integrates temporal extrapolation with spatial residual redistribution, under the guidance of object-level structural constraints and a pixel-level adaptive propagation mechanism, in which temporal extrapolation, object-level residual redistribution, pixel-level adaptive residual propagation, and a spectrally weighted refinement module are progressively designed to establish a bidirectional coupling between temporal variation and spatial structure, thereby achieving unified modeling of structural preservation and change reconstruction. Furthermore, building upon pixel-level residual redistribution, a dual-ranking consistency strategy is introduced to ensure stable and physically consistent similar-pixel selection, imposing both explicit and implicit constraints on residual propagation. HRSF is evaluated against five state-of-the-art spatiotemporal fusion methods across three distinct landscapes. Quantitative results demonstrate that HRSF consistently outperforms existing approaches, achieving both higher accuracy and superior structural preservation. Overall, HRSF effectively balances spatial structural stability and spectral consistency, enabling high-fidelity spatiotemporal fusion for dynamic environmental monitoring. The Python code of HRSF and the experimental dataset are available at https://github.com/paboooo/HRSF.

Model-based polarimetric SAR (PolSAR) algorithms for bio- and geophysical parameter estimation rely on the effective separation of the combined scattering response of vegetation canopies and the soil surface through physically based models. However, the interpretation of polarimetric features derived from physical models is still subject to some ambiguity. Another strategy for complementing the model-based approaches for scattering mechanisms characterisation deals with the separation of the polarised and depolarised contributions of the PolSAR data according to their degree of polarisation. In this paper, we propose a two-component decomposition for estimating the depolarised and polarised components within the target and their corresponding coherency matrices. The method requires the previous calculation of the backscattering powers given by the model-free three-component (MF3C) decomposition, which in turn relies on the 3-D Barakat degree of polarisation. This quantitative information allows us to construct an inversion algorithm to retrieve the proportion of the polarised and depolarised contributions for all the elements of the observed coherency matrix under the reflection symmetry assumption. In essence, the proposed decomposition can be regarded as an extension of the MF3C method and, as a consequence, it enables the exploitation of both model-free and model-based approaches by using a physical rationale driven by the capability of the 3-D Barakat degree of polarisation. Therefore, practical applications can benefit from this approach as the retrieval of target parameters could presumably be done in a more accurate way by directly applying existing scattering models to both components. Indoor multi-frequency datasets acquired over three vegetation samples from the European Microwave Signature Laboratory (EMSL) and P-, L-, and C-band AIRSAR images over a boreal forest in Germany have been employed for testing the proposed decomposition. Performance analysis was performed using different polarimetric tools applied to the outcomes of the two-component decomposition, namely, the eigendecomposition and the copolar cross-correlation analysis of polarised and depolarised components, as well as histograms and a correlation analysis among backscattering powers. Overall, it has been observed that the method outputs are consistent with the theoretical expectations for the depolarised and polarised scattering components for a wide range of scenarios and sensor frequencies.

Due to the challenges presented by the different scales of objects and the complex interference in synthetic aperture radar (SAR) images, current detectors struggle to achieve satisfactory accuracy and exhibit weak generalization abilities across different datasets. This paper proposes a robust and universal object detector framework named ArgusSAR, which is suitable for both ship and aircraft object detection. The proposed framework comprises three key components: In detail, a Spatial Encoder, which employs Multi-Head Attention Blocks integrated with multi-layered Encoder Blocks, extracts robust feature representations while suppressing irrelevant interference inherent in complex SAR backgrounds. Moreover, a Fine-grained Feature Aggregation Encoder, which incorporates the multi-level pyramid architecture with content-aware upsampling operations, enabling precise integration of multi-dimensional features and enhanced extraction of object boundaries. Furthermore, a robust Multi-dimensional Awareness Attention Decoder, which incorporates scale-spatial-task self-attention mechanisms to strengthen geometric perception and improve both localization accuracy and generalization ability for ship and aircraft objects. Three publicly available SAR datasets involving ship and aircraft objects are chosen to confirm the effectiveness of ArgusSAR. Compared with the baseline and the other methods, our method has the best performance on these datasets. It demonstrates that ArgusSAR framework is robust for SAR ship and aircraft objects detection. The source code is available at https://github.com/masurq/ArgusSAR.

The monitoring of global soil moisture is crucial for understanding the hydrological cycle and managing terrestrial water resources. The Chinese-French Oceanography Satellite (CFOSAT), equipped with the first sector-beam rotary scanning microwave scatterometer (CSCAT), provides a novel opportunity for global soil moisture mapping. However, the capability of CFOSAT's Ku-band for soil moisture retrieval remains underexplored and lacks systematic evaluation. In this study, an Adaptive Backscatter Change Tracking (ABCT) algorithm is designed to retrieve absolute soil moisture from CFOSAT's CSCAT measurements. The ABCT algorithm assumes a stable roughness, where changes in backscattering are primarily attributed to soil moisture variation based on a logarithmic relationship. It incorporates a vegetation influence coefficient, which quantifies how vegetation impacts the backscatter signal This coefficient adaptively scales with changes in the Normalized Difference Vegetation Index (NDVI) to adjust the backscattering appropriately to include the effect of vegetation growth or decay. This allows the algorithm to isolate changes in the backscatter signal that are due to soil moisture while minimizing the false readings from vegetation growth or wilting. The CFOSAT ABCT algorithm's performance was evaluated against extensive in-situ soil moisture data, demonstrating a robust correlation, with the Vertical-Vertical Polarization Ascending Orbit (VV Asc) result showing the highest accuracy, indicated by Pearson's correlation coefficient (R) of 0.68 and unbiased root mean squared error (ubRMSE) of 0.057 m3/m3. Comparative analysis with the Advanced Scatterometer (ASCAT) data revealed that, while the ABCT algorithm's correlation was slightly lower than that of the official EUMETSAT H SAF product, it notably improved the bias and ubRMSE metrics. This study underscores that the CFOSAT ABCT soil moisture retrieval algorithm and product are a valuable addition to global soil moisture mapping, complementing existing satellite missions or sensors such as SMAP, SMOS, ASCAT, AMSR2 and FY-3/MWRI.