The tobacco seedling stage is a crucial period for tobacco cultivation. Accurately extracting tobacco seedlings from satellite images can effectively assist farmers in replanting, precise fertilization, and subsequent yield estimation. However, in complex Karst mountainous areas, it is extremely challenging to accurately segment tobacco plants due to a variety of factors, such as the topography, the planting environment, and difficulties in obtaining high-resolution image data. Therefore, this study explores an accurate segmentation model for detecting tobacco seedlings from UAV RGB images across various geomorphic partitions, including dam and hilly areas. It explores a family of tobacco plant seedling segmentation networks, namely, U-Net, U-Net++, Linknet, PSPNet, MAnet, FPN, PAN, and DeepLabV3+, using the Hill Seedling Tobacco Dataset (HSTD), the Dam Area Seedling Tobacco Dataset (DASTD), and the Hilly Dam Area Seedling Tobacco Dataset (H-DASTD) for model training. To validate the performance of the semantic segmentation models for crop segmentation in the complex cropping environments of Karst mountainous areas, this study compares and analyzes the predicted results with the manually labeled true values. The results show that: (1) the accuracy of the models in segmenting tobacco seedling plants in the dam area is much higher than that in the hilly area, with the mean values of mIoU, PA, Precision, Recall, and the Kappa Coefficient reaching 87%, 97%, 91%, 85%, and 0.81 in the dam area and 81%, 97%, 72%, 73%, and 0.73 in the hilly area, respectively; (2) The segmentation accuracies of the models differ significantly across different geomorphological zones; the U-Net segmentation results are optimal for the dam area, with higher values of mIoU (93.83%), PA (98.83%), Precision (93.27%), Recall (96.24%), and the Kappa Coefficient (0.9440) than those of the other models; in the hilly area, the U-Net++ segmentation performance is better than that of the other models, with mIoU and PA of 84.17% and 98.56%, respectively; (3) The diversity of tobacco seedling samples affects the model segmentation accuracy, as shown by the Kappa Coefficient, with H-DASTD (0.901) > DASTD (0.885) > HSTD (0.726); (4) With regard to the factors affecting missed segregation, although the factors affecting the dam area and the hilly area are different, the main factors are small tobacco plants (STPs) and weeds for both areas. This study shows that the accurate segmentation of tobacco plant seedlings in dam and hilly areas based on UAV RGB images and semantic segmentation models can be achieved, thereby providing new ideas and technical support for accurate crop segmentation in Karst mountainous areas.

The forest area in China’s plateaus and mountainous regions accounts for as much as 43% of the country’s total forest area. Accurately estimating the aboveground biomass (AGB) in these plateau and mountain forests is significant for global carbon sink assessment and climate change. However, the complexity of the natural environment poses significant challenges to the accurate estimation of forests’ aboveground biomass (AGB), and the accuracy of both AGB estimation and spatial mapping needs further improvement. This study utilized support vector regression, backpropagation neural networks, and random forests to predict trends in AGB and establish an optimal original model for forest AGB estimation. Further calibration was performed using regression kriging on the optimal model. The results indicated that (1) random forests achieved the highest coefficient of determination (R² for cypress = 0.63, R² for fir = 0.66, R² for cryptomeria = 0.64, and R² for mixed forest = 0.54), showing greater potential in predicting AGB in complex mountainous mixed forests; (2) the residual kriging method significantly improved the estimation accuracy, increasing the R² values of the original RF model by 25%, 24%, and 22%, and improving the accuracy of mixed plot estimates from 54% to 81%; and (3) the residual kriging method effectively addressed the underestimation of high values and overestimation of low values in AGB estimates, broadening the range of AGB values and allowing for a more detailed spatial distribution of forests’ aboveground biomass.

Rapidly and accurately extracting tobacco plant information can facilitate tobacco planting management, precise fertilization, and yield prediction. In the karst mountainous of southern China, tobacco plant identification is affected by large ground undulations, fragmented planting areas, complex and diverse habitats, and uneven plant growth. This study took a tobacco planting area in Guizhou Province as the research object and used DJI UAVs to collect UAV visible light images. Considering plot fragmentation, plant size, presence of weeds, and shadow masking, this area was classified into eight habitats. The U-Net model was trained using different habitat datasets. The results show that (1) the overall precision, recall, F1-score, and Intersection over Union (IOU) of tobacco plant information extraction were 0.68, 0.85, 0.75, and 0.60, respectively. (2) The precision was the highest for the subsurface-fragmented and weed-free habitat and the lowest for the smooth-tectonics and weed-infested habitat. (3) The weed-infested habitat with smaller tobacco plants can blur images, reducing the plant-identification accuracy. This study verified the feasibility of the U-Net model for tobacco single-plant identification in complex habitats. Decomposing complex habitats to establish the sample set method is a new attempt to improve crop identification in complex habitats in karst mountainous areas.

Rapidly and accurately extracting tobacco plant information can facilitate tobacco planting man-agement, precise fertilization and yield prediction. In karst plateau of southern China, tobacco plant identification is affected by large ground undulations, fragmented planting areas, complex and diverse habitats and uneven plant growth. This study took a tobacco planting area in Gui-zhou Province as the research object and used DJI UAVs to collect UAV visible light images. Considering plot fragmentation, plant size, presence of weeds and shadow masking, this area was classified into eight habitats. The datasets of different habitats were constructed to train the U-Net model. The results show that (1) the overall precision, recall, F1-score and IOU of tobacco plant information extraction were 0.68, 0.85, 0.75 and 0.60, respectively. (2) The precision was the highest for the subsurface-fragmented and weed-free habitat and the lowest for the smooth-tectonics and weed-infested habitat. (3) The weed-infested habitat with smaller tobacco plants can cause blurred images, reducing the plant identification accuracy. This study verified the feasibility of the U-Net model for tobacco single-plant identification in complex habitats. Decomposing complex habitats to establish the sample set method is a new attempt to improve crop identification in complex habitats in karst mountainous areas.

Under the backdrop of global climate warming, both forest vegetation greening and resilience decline coexist, and the consistency of these trends at the regional scale remains controversial. This study uses the kNDVI (Kernel Normalized Difference Vegetation Index) and TAC (Temporal Autocorrelation) index framework, combined with BEAST and Random Forest methods, to quantify and analyze the spatiotemporal evolution of forest resilience and its driving factors in Southwest China from 2000 to 2022. The results show the following: (1) Forest resilience exhibits a “high in the northwest and low in the southeast” spatial distribution, with a temporal pattern of “increase-decrease-increase.” The years 2010 and 2015 are key turning points. Trend shift analysis divides resilience into six types. (2) Although forest vegetation shows a clear greening trend, resilience does not necessarily increase with greening, and in some areas, an “increase in greening—decline in resilience” asynchronous pattern appears. (3) The annual average temperature, precipitation, and solar radiation are the main climate factors and their influence on resilience follows a nonlinear relationship. Higher temperatures and increased radiation may suppress resilience, while increased precipitation can enhance it. This study suggests incorporating the TAC indicator into ecological monitoring and early warning systems, along with applying trend classification results for region-specific management to improve the scientific basis and adaptability of forest governance under climate change.

Study region: The study region encompasses the karst plateau lakes of southwestern China, characterized by rugged terrain, sinuous shorelines, pronounced deep-canyon shadows, and intense dissolution landforms. Study focus: To tackle edge degradation, missed detection of small water bodies, and spectral confusion with aquatic vegetation, we propose KASH-Water (Karst-Adaptive Spatial Heterogeneity Water extraction framework), which integrates karst spatial heterogeneity modeling with an empirically weighted dual-gradient synergy strategy. A hybrid BCE-Dice loss is developed to adaptively modulate gradients and alleviate optimization instability from severe class imbalance and fragmented water distributions. We systematically benchmark three segmentation models with distinct inductive biases, and conduct ablation experiments to investigate error propagation and module contributions. New hydrological insights for the region: (1) KASH-DeepLabV3+ achieves the highest overall precision (0.973, 0.983, 0.967) due to ASPP multi-scale context; KASH-HarDNet exhibits enhanced sensitivity to fragmented patches, while KASH-U-Net suffers boundary adhesion under heterogeneity. (2) The hybrid loss yields IoU gains of 5.7%, 6.4%, and 5.3% over conventional BCE loss, significantly improving connectivity of fine-scale water structures. (3) The results reveal the coupling between network inductive biases and karst heterogeneity, illustrating how architectures modulate error propagation. This framework provides reliable support for high-precision water monitoring in ecologically fragile karst regions.