Accurate classification of forest stand is crucial for protection and management needs. However, forest stand classification remains a great challenge because of the high spectral and textural similarity of different tree species. Although existing studies have used multiple remote sensing data for forest identification, the effects of different spatial resolutions and combining multi-source remote sensing data for automatic complex forest stand identification using deep learning methods still require further exploration. Therefore, this study proposed an object-oriented convolutional neural network (OCNN) classification method, leveraging data from Sentinel-2, RapidEye, and LiDAR to explore classification accuracy of using OCNN to identify complex forest stands. The two red edge bands of Sentinel-2 were fused with RapidEye, and canopy height information provided by LiDAR point cloud was added. The results showed that increasing the red edge bands and canopy height information were effective in improving forest stand classification accuracy, and OCNN performed better in feature extraction than traditional object-oriented classification methods, including SVM, DTC, MLC, and KNN. The evaluation indicators show that ResNet_18 convolutional neural network model in the OCNN performed the best, with a forest stand classification accuracy of up to 85.68%.

Accurate information on the location of dominant tree species is essential for scientific forest management. However, factors like changes in forest phenology, stand conditions, and mixed understory backgrounds introduce uncertainties in remote sensing-based species mapping. To address these challenges, this study maps dominant tree species using time series Sentinel-2 data combined with environmental context data. To quantify the impact of understory background on mapping accuracy, this study applied a random forest inversion model to estimate the canopy cover across the study area. Binary contour plots and Pearson’s correlation coefficient were used to quantify the relationship between canopy cover and classification uncertainty at both the grid and pixels. A 10 m resolution map of dominant tree species in Yunnan Province, featuring eight species, was produced with an overall accuracy of 83.52% and a Kappa coefficient of 0.8115. The R² value between the predicted and actual tree area proportions was greater than 0.93, with RMSEs consistently below 2.6. In addition, we observed strong negative correlations between different canopy cover classes. The correlations were −0.67 for low-cover areas, −0.40 for medium-cover areas, and −0.73 for high-cover areas. Our mapping framework enables the accurate identification of regional dominant species, and the established relationship between understory context and classification uncertainty provides valuable insights for analyzing potential mapping errors.

Water resources in arid and semi-arid areas are limiting factors for ecosystem health and economic development. Therefore, an accurate and reasonable assessment of ecological water demand is crucial for efficient water resource utilization. In this study, we used vegetation coverage and groundwater depth to assess the state of vegetation growth in the Zhenglanqi, located at the southeastern edge of Otindag Sandy Land. Our results indicate the existence of a statistical power index function between vegetation coverage and groundwater depth scatter plots, where even minor changes in groundwater depth can have a significant impact on vegetation growth. In order to quantitatively assess the impact of subsidence on vegetation ecology, we propose a maximum allowable subsidence level under conditions that maintain normal ecological conditions, based on the initial subsidence depth and ecological guarantee rate. Our findings suggest that regions with shallower initial groundwater depths are more sensitive to changes in their environment than regions with deeper groundwater depths. The total groundwater consumption in the study area was 83 million cubic meters while maintaining an ecological guarantee rate of 80%; thus, while ensuring normal environmental conditions, human exploitation of shallow groundwater accounts for only 16 percent.

Understanding the factors influencing individual tree mortality is essential for sustainable forest management, particularly for Prince Rupprech’s larch (Larix gmelinii var. Principis-rupprechtii) in North China’s natural forests. This study focused on 20 sample plots (20 × 20 m each) established in Shanxi Province, North China. This study compared three individual tree mortality models—Generalized Linear Model (GLM), Linear Discriminant Analysis (LDA), and Bayesian Generalized Linear Model (Bayesian GLM)—finding that both GLM and Bayesian GLM achieved approximately 0.87 validation accuracy on the test dataset. Due to its simplicity, GLM was selected as the final model. Building on the GLM model, six binning methods were applied to categorize diameter at breast height (DBH): equal frequency binning, equal width binning, cluster-based binning, quantile binning, Chi-square binning, and decision tree binning. Among these, the decision tree binning method achieved the highest performance, with an accuracy of 90.12% and an F1 score of 90.06%, indicating its effectiveness in capturing size-dependent mortality patterns. This approach provides valuable insights into factors affecting mortality and offers practical guidance for managing Larix gmelinii var. Principis-rupprechtii forests in temperate regions.

The intensifying global climate warming caused by human activities poses severe challenges to ecosystem stability. Constructing an ecological security pattern can identify ecological land supply and an effective spatial distribution baseline and provide a scientific basis for safeguarding regional ecological security. This study analyzes land-use data from 2000 to 2020 for Golog Tibetan Autonomous Prefecture. The PLUS model was utilized to project land-use potential for the year 2030. The InVEST model was employed to conduct a comprehensive assessment of habitat quality in the study area for both 2020 and 2030, thereby pinpointing ecological sources. Critical ecological restoration zones were delineated by identifying ecological corridors, pinch points, and barrier points through the application of the Minimum Cumulative Resistance model and circuit theory. By comparing ecological security patterns (ESPs) in 2020 and 2030, we proposed a dynamic restoration framework and optimization recommendations based on habitat quality changes and ESPs. The results indicate significant land-use changes in the eastern part of Golog Tibetan Autonomous Prefecture from 2020 to 2030, with large-scale conversion of grasslands into bare land, farmland, and artificial surfaces. The ecological security pattern is threatened by risks like the deterioration of habitat quality, diminished ecological sources as well as pinch points, and growing barrier points. Optimizing the layout of ecological resources, strengthening barrier zone restoration and pinch point protection, and improving habitat connectivity are urgent priorities to ensure regional ecological security. This study offers a scientific foundation for the harmonization of ecological protection and economic development and the policy development and execution of relevant departments.