Remote Sensing

Mangrove forests provide essential climate regulation and coastal protection, yet fine-scale quantification of carbon dynamics remains limited in the Sundarbans due to spatial heterogeneity and tidal influences. This study estimated canopy structural and photosynthetic dynamics from 2019 to 2023 by integrating 10 m spatial high-resolution remote sensing with a light use efficiency (LUE) modeling framework. Leaf Area Index (LAI) was retrieved at 10 m resolution using the PROSAIL radiative transfer model applied to Sentinel-2 data to characterize the canopy structure of the mangrove forest. LUE-based Gross Primary Productivity (GPP) was estimated using Sentinel-2 vegetation and water indices and MODIS fPAR with station observatory temperature data. Annual carbon uptake showed clear interannual variation, ranging from 1881 to 2862 g C m⁻² yr⁻¹ between 2019 and 2023. GPP estimates were strongly correlated with MODIS-GPP (R² = 0.86, p < 0.001), demonstrating the method’s reliability for monitoring mangrove carbon sequestration. LUE-based Solar-induced Chlorophyll Fluorescence (SIF) was derived at 10 m resolution and compared with TROPOMI-SIF observations to assess correspondence (R² = 0.88, p < 0.001) with photosynthetic activity. LAI, GPP and SIF exhibited pronounced seasonal and interannual variability on photosynthetic activity, with higher values during the monsoon growing season and lower values during dry periods. Mean NDVI declined from 2019 to 2023 and modeled annual carbon uptake ranged from approximately 43 to 65 Mt CO₂ eq, with lower sequestration in 2022–2023 associated with climatic stress. Strong correlations among LAI, NDVI, GPP, and SIF indicated consistent coupling between photosynthetic activity and carbon uptake in the mangrove ecosystem. These results provide a fine-scale assessment of mangrove carbon dynamics relevant to conservation and climate-mitigation planning in tropical regions.

In many land cover classification tasks, the limited precision of individual sensors hinders the accurate separation of certain classes, largely due to the complexity of the Earth’s surface morphology. To mitigate these issues, decision fusion methodologies are employed, allowing data from multiple sensors to be synthesized into robust and more conclusive classification outcomes. This study employs fully polarimetric Synthetic Aperture Radar (PolSAR) imagery and leverages the strengths of three decomposition methods, namely Pauli’s, Krogager’s, and Cloude’s, by extracting their respective components for improved detection. From each decomposition method, three scattering components are derived, enabling the extraction of informative features that describe the scattering behavior associated with various land cover types. The extracted scattering features, treated as independent sensors, were used to train three neural network classifiers. The resulting outputs were then considered as local decisions for each land cover type and subsequently fused through a decision fusion rule to generate more complete and accurate classification results. Experimental results demonstrate that the proposed Multi-Class Bahadur–Lazarsfeld Expansion (MC-BLE) fusion significantly enhances classification performance, achieving an overall accuracy (OA) of 95.78% and a Kappa coefficient of 0.94. Compared to individual classification methods, the fusion notably improved per-class accuracy, particularly for complex land cover boundaries. The core innovation of this work is the transformation of the Bahadur–Lazarsfeld Expansion (BLE), originally designed for binary decision fusion into a multi-class framework capable of addressing multiple land cover types, resulting in a more effective and reliable decision fusion strategy.

The hyperspectral image (HSI) is rich in spectral information and has important applications in the field of ground objects classification. However, HSI data have high dimensions and variable spatial–spectral features, which make it difficult for some models to adequately extract the effective features. Recent studies have shown that fusing spatial and spectral features can significantly improve accuracy by exploiting multi-dimensional correlations. Based on this, this article proposes a spectral integration and focused attention network (SIFANet) with a two-branch structure. SIFANet captures the local spatial features and global spectral dependencies through the parallel-designed spatial feature extractor (SFE) and spectral sequence Transformer (SST), respectively. A cross-module attention fusion (CMAF) mechanism dynamically integrates features from both branches before final classification. Experiments on the Salinas dataset and Xiong’an hyperspectral dataset show that the overall accuracy on these two datasets is 99.89% and 99.79%, which is higher than the other models compared. The proposed method also had the lowest standard deviation of category accuracy and optimal computational efficiency metrics, demonstrating robust spatial–spectral feature integration for improved classification.