Leaf chlorophyll content (LCC) is a key indicator in representing the photosynthetic capacity of Populus deltoides (Populus deltoides Marshall). Unmanned aerial vehicle (UAV) hyperspectral imagery provides an effective approach for LCC estimation, but the issue of band redundancy significantly impacts model accuracy and computational efficiency. Commonly used single feature selection algorithms not only fail to balance computational efficiency with optimal set search but also struggle to combine different regression algorithms under dynamic set conditions. This study proposes an ensemble feature selection framework to enhance LCC estimation accuracy using UAV hyperspectral data. Firstly, the embedded algorithm was improved by introducing the SHapley Additive exPlanations (SHAP) algorithm into the ranking system. A dynamic ranking strategy was then employed to remove bands in steps of 10, with LCC models developed at each step to identify the initial band subset based on estimation accuracy. Finally, the wrapper algorithm was applied using the initial band subset to search for the optimal band subset and develop the corresponding model. Three regression algorithms including gradient boosting regression trees (GBRT), support vector regression (SVR), and gaussian process regression (GPR) were combined with this framework for LCC estimation. The results indicated that the GBRT-Optimal model developed using 28 bands achieved the best performance with R² of 0.848, RMSE of 1.454 μg/cm² and MAE of 1.121 μg/cm². Compared with a model performance that used all bands as inputs, this optimal model reduced the RMSE value by 24.37%. In addition to estimating biophysical and biochemical parameters, this method is also applicable to other hyperspectral imaging tasks.

The Silk Road Economic Belt and the 21st Century Maritime Silk Road Initiative (BRI) proposed in 2013 by China has greatly accelerated the social and economic development of the countries along the Belt and Road (B&R) region. However, the international community has questioned its impact on the ecological environment and a comprehensive assessment of ecosystem quality changes is lacking. Therefore, this study proposes an objective and automatic method to assess ecosystem quality and analyzes the spatiotemporal changes in the B&R region. First, an ecosystem quality index (EQI) is established by integrating the vegetation status derived from three remote sensing ecological parameters including the leaf area index, fractional vegetation cover and gross primary productivity. Then, the EQI values are automatically categorized into five ecosystem quality levels including excellent, good, moderate, low and poor to illustrate their spatiotemporal changes from the years 2016 to 2020. The results indicate that the spatial distributions of the EQIs across the B&R region exhibited similar patterns in the years 2016 and 2020. The regions with excellent levels accounted for the lowest proportion of less than 12%, while regions with moderate, low and poor levels accounted for more than 68% of the study area. Moreover, based on the EQI pattern analysis between the years 2016 and 2020, the regions with no significant EQI change accounted for up to 99.33% and approximately 0.45% experienced a significantly decreased EQI. Therefore, this study indicates that the ecosystem quality of the B&R region was relatively poor and experienced no significant change in the five years after the implementation of the “Vision and Action to Promote the Joint Construction of the Silk Road Economic Belt and the 21st Century Maritime Silk Road”. This study can provide useful information for decision support on the future ecological environment management and sustainable development of the B&R region.

Accurate forest type classification in subtropical regions is essential for ecological monitoring and sustainable management. Multimodal remote sensing data provide rich information support, yet the synergy between network architectures and fusion strategies in deep learning models remains insufficiently explored. This study established a multimodal deep learning framework with integrated interpretability analysis by combining high-resolution Beijing-2 RGB imagery, Sentinel-1 data, and time-series Sentinel-2 NDVI data. Two representative architectures (U-Net and Swin-UNet) were systematically combined with three fusion strategies, including feature concatenation (Concat), gated multimodal fusion (GMU), and Squeeze-and-Excitation (SE). To quantify feature contributions and decision patterns, three complementary interpretability methods were also employed: Shapley Additive Explanations (SHAP), Grad-CAM++, and occlusion sensitivity. Results show that Swin-UNet consistently outperformed U-Net. The SwinUNet-SE model achieved the highest overall accuracy (OA) of 82.76%, exceeding the best U-Net model by 3.34%, with the largest improvement of 5.8% for mixed forest classification. The effectiveness of fusion strategies depended strongly on architecture. In U-Net, SE and Concat improved OA by 0.91% and 0.23% compared with the RGB baseline, while GMU slightly declined. In Swin-UNet, all strategies achieved higher gains between 1.03% and 2.17%, and SE effectively reduced NDVI sensitivity. SHAP analysis showed that RGB features contributed most (values > 0.0015), NDVI features from winter and spring ranked among the top 50%, and Sentinel-1 features contributed less. These findings reveal how architecture and fusion design interact to enhance multimodal forest classification.

Accurate delineation of glacier extent is crucial for monitoring glacier degradation in the context of global warming. Satellite remote sensing with high spatial and temporal resolution offers an effective approach for large-scale glacier mapping. However, persistent cloud cover limits its application on the Tibetan Plateau, leading to substantial omissions in glacier identification. Therefore, this study proposed a novel sub-cloudy glacier extraction model (SCGEM) designed to extract glacier boundaries from cloud-affected satellite images. First, the cloud-insensitive characteristics of topo-graphic (Topo.), synthetic aperture radar (SAR), and temporal (Tempo.) features were investigated for extracting glaciers under cloud conditions. Then, a transformer-based generative adversarial network (GAN) was proposed, which incorporates an image reconstruction and an adversarial branch to improve glacier extraction accuracy under cloud cover. Experimental results demonstrated that the proposed SCGEM achieved significant improvements with an IoU of 0.7700 and an F1 score of 0.8700. The Topo., SAR, and Tempo. features all contributed to glacier extraction in cloudy areas, with the Tempo. features contributing the most. Ablation studies further confirmed that both the adversarial training mechanism and the multi-task architecture contributed notably to improving the extraction accuracy. The proposed architecture serves both to data clean and enhance the extraction of glacier texture features.