Focusing on the trend of continuously seeking high-precision tree species classification results in small areas from the perspectives of sensors and classification algorithms. This study aimed to explore the effects of data sources, classifiers, and seasons on classification accuracy in regions with significant environmental variation, examining patterns of tree species classification to enhance the transferability of classification. Considering two typical forest distribution regions in the north and south of China, this study utilized the revisitation cycle and open-source advantages of Sentinel-2 and Landsat-8. Leveraging the Google Earth Engine (GEE) platform, this study captured spectral features, vegetation indices, and texture features for single seasonal and seasonal combination images. With the assistance of Sentinel-1A and SRTM (Shuttle Radar Topography Mission) DEM (Digital Elevation Model), backscattering coefficient features and topographical features were extracted and input with features captured from Sentinel-2 and Landsat-8 into three types of classifiers: random forest (RF), support vector machine (SVM), and gradient tree boosting (GTB) for major tree species classification. In this research, we discovered that the best classification for single season in the northern study area was spring, whereas, for the southern study area, it was winter. Seasonal combination images effectively improved the classification accuracy of single seasonal images, with Sentinel-2 imagery displaying better classification performance compared to Landsat-8, and the optimal classifier differing between the north and the south. The inclusion of topographical or backscattering coefficient features in the four-season combination imagery contributed to improvements in classification accuracy, with topographical features significantly enhancing the classification performance in the topographically varied southern study area. The evaluation of feature importance indicated that elevation was the most critical feature for classification, while spectral features and vegetation indices were also significant. In the southern study area with large topographical discrepancies, subdividing into different terrain units led to improved tree species classification accuracy in medium-altitude, gentle slope areas. These findings provide insights into the regularity of enhancing tree species classification accuracy in environmentally diverse areas through the use of multi-source remote sensing data and multi-seasonal imagery. Consequently, the results offer a reference for the identification of tree species across large areas and the creation of spatial distribution maps.

China is one of the countries with the largest citrus cultivation areas, and its citrus industry has received significant attention due to its substantial economic benefits. Traditional manual forestry surveys and remote sensing image classification tasks are labor-intensive and time-consuming, resulting in low efficiency. Remote sensing technology holds great potential for obtaining spatial information on citrus orchards on a large scale. This study proposes a lightweight model for citrus plantation extraction that combines the DeepLabV3+ model with the convolutional block attention module (CBAM) attention mechanism, with a focus on the phenological growth characteristics of citrus in the Guangxi region. The objective is to address issues such as inaccurate extraction of citrus edges in high-resolution images, misclassification and omissions caused by intra-class differences, as well as the large number of network parameters and long training time found in classical semantic segmentation models. To reduce parameter count and improve training speed, the MobileNetV2 lightweight network is used as a replacement for the Xception backbone network in DeepLabV3+. Additionally, the CBAM is introduced to extract citrus features more accurately and efficiently. Moreover, in consideration of the growth characteristics of citrus, this study augments the feature input with additional channels to better capture and utilize key phenological features of citrus, thereby enhancing the accuracy of citrus recognition. The results demonstrate that the improved DeepLabV3+ model exhibits high reliability in citrus recognition and extraction, achieving an overall accuracy (OA) of 96.23%, a mean pixel accuracy (mPA) of 83.79%, and a mean intersection over union (mIoU) of 85.40%. These metrics represent an improvement of 11.16%, 14.88%, and 14.98%, respectively, compared to the original DeepLabV3+ model. Furthermore, when compared to classical semantic segmentation models, such as UNet and PSPNet, the proposed model achieves higher recognition accuracy. Additionally, the improved DeepLabV3+ model demonstrates a significant reduction in both parameters and training time. Generalization experiments conducted in Nanning, Guangxi Province, further validate the model’s strong generalization capabilities. Overall, this study emphasizes extraction accuracy, reduction in parameter count, adherence to timeliness requirements, and facilitation of rapid and accurate extraction of citrus plantation areas, presenting promising application prospects.

Vegetation changes and factors have a profound influence on the local ecology, the economy, and the long-term durability of human construction. This study focuses on the impacts of climate change and human activity on vegetation changes on the Qinghai-Tibet Plateau and aims to develop a dataset of human activity levels on the plateau. Sen and Mann-Kendall trend analysis was used to evaluate the spatial distribution of vegetation NDVI and its trends, as well as the lagged response of plant growth to climatic circumstances. Using a geodetector model, the effects of meteorological and anthropogenic intensity data were examined. The study’s findings show that, although anthropogenic influences and ecosystem vulnerability caused a decline in the region’s vegetation, a stable climate and a healthy ecosystem supported the growth of vegetation. From 2000 to 2017, the area where vegetation grass improved significantly accounted for the highest proportion, reaching 34.22%. Different anthropogenic intensities are distributed spatially, and this interplay of anthropogenic intensities and climatic factors affects the distribution of vegetation greenness more than each element acting alone. The study of how human activity and climate change affect vegetation greenness can offer practical recommendations for maintaining the Qinghai-Tibet Plateau’s natural ecology. It is crucial to responsibly safeguard the Qinghai-Tibet Plateau’s environment in response to the nation’s ecological civilization.

Accurate modeling of windbreaks is essential for the precise assessment of wind protection performance. However, in most windbreak studies, the models used the approximate shape of the simulated trees, resulting in significant differences between the simulated results and the actual situation. In this study, terrestrial laser scanning (TLS) was used to extract tree parameters, which were used in a quantitative structural model (AdQSM) to recreate the tree structure and restore the wind field environment using the computational fluid dynamics software PHOENICS. In addition, we compared the bias, precision, and accuracy of porosity of Ginkgo biloba (with elliptical crown) and Populus alba (with conical crown), which have been commonly used in previous windbreak studies. The results showed that AdQSM has a high reduction rate and ability to reproduce the field conditions of the study area. After wind field simulation, the wind speed root mean square errors of the point cloud model at three heights (3, 6, and 9 m) were 0.272, 0.377, and 0.437 m/s, respectively, and the wind speed correlation coefficients r were 0.967, 0.965, and 0.937, respectively, which were significantly more accurate than those of the remaining two structures. Finally, the porosity of the windbreak forest obtained using the modeled sample plot showed a higher correlation with the wind permeability coefficient than that obtained using the existing approach. Windbreak models with three different porosities under the same conditions had different effects on the wind environment, particularly the location of the maximum wind speed reduction, variation of wind speed with porosity, and recovery rate of leeward wind speed. TLS can accurately extract windbreak factors and calculate the porosity, thus greatly improving the reliability of windbreak effect research in windbreak forests. This study provides a promising direction for future research related to the simulation of windbreak effects in windbreak forests.

Tree-level information can be estimated based on light detection and ranging (LiDAR) point clouds. We propose to develop a quantitative structural model based on terrestrial laser scanning (TLS) point clouds to automatically and accurately estimate tree attributes and to detect real trees for the first time. This model is suitable for forest research where branches are involved in the calculation. First, the Adtree method was used to approximate the geometry of the tree stem and branches by fitting a series of cylinders. Trees were represented as a broad set of cylinders. Then, the end of the stem or all branches were closed. The tree model changed from a cylinder to a closed convex hull polyhedron, which was to reconstruct a 3D model of the tree. Finally, to extract effective tree attributes from the reconstructed 3D model, a convex hull polyhedron calculation method based on the tree model was defined. This calculation method can be used to extract wood (including tree stem and branches) volume, diameter at breast height (DBH) and tree height. To verify the accuracy of tree attributes extracted from the model, the tree models of 153 Chinese scholartrees from TLS data were reconstructed and the tree volume, DBH and tree height were extracted from the model. The experimental results show that the DBH and tree height extracted based on this model are in better consistency with the reference value based on field survey data. The bias, RMSE and R2 of DBH were 0.38 cm, 1.28 cm and 0.92, respectively. The bias, RMSE and R2 of tree height were −0.76 m, 1.21 m and 0.93, respectively. The tree volume extracted from the model is in better consistency with the reference value. The bias, root mean square error (RMSE) and determination coefficient (R2) of tree volume were −0.01236 m3, 0.03498 m3 and 0.96, respectively. This study provides a new model for nondestructive estimation of tree volume, above-ground biomass (AGB) or carbon stock based on LiDAR data.