Forest growing stock volume is a crucial indicator for assessing forest resources. However, contemporary machine learning models used in estimating forest growing stock volume often exhibit fluctuating precision and are confined to specific tree species, lacking universality. This limitation impedes their capacity to provide comprehensive forest survey services. This study designed a novel model for predicting forest growing stock volume named RF-Adaboost. The model represented the inaugural application of the Adaboost algorithm in estimating forest growing stock volume. Additionally, the authors innovatively refined the Adaboost algorithm by integrating Random Forest as its weak learner. To substantiate the model’s effectiveness, the authors designed three data combination schemes at different scales and conducted regression estimation using the RF-Adaboost model, traditional Random Forest, and Adaboost models, respectively. The results indicated that the RF-Adaboost model consistently outperforms others across various data schemes. Furthermore, utilizing a combined data scheme of remote sensing and Continuous Forest Inventory, the RF-Adaboost model demonstrated optimal performance in estimating forest growing stock volume (R² = 0.81, RMSE = 7.08 m³/site, MAE = 3.36 m³, MAPE = 8%). Finally, the RF-Adaboost model exhibits greater universality, eliminating the need for strict differentiation between tree species. This research presented an efficient and cost-effective approach to estimate forest growing stock, addressing the challenges associated with conventional survey methods.

Accurate coffee plant counting is a crucial metric for yield estimation and a key component of precision agriculture. While multispectral UAV technology provides more accurate crop growth data, the varying spectral characteristics of coffee plants across different phenological stages complicate automatic plant counting. This study compared the performance of mainstream YOLO models for coffee detection and segmentation, identifying YOLOv9 as the best-performing model, with it achieving high precision in both detection (P = 89.3%, mAP50 = 94.6%) and segmentation performance (P = 88.9%, mAP50 = 94.8%). Furthermore, we studied various spectral combinations from UAV data and found that RGB was most effective during the flowering stage, while RGN (Red, Green, Near-infrared) was more suitable for non-flowering periods. Based on these findings, we proposed an innovative dual-channel non-maximum suppression method (dual-channel NMS), which merges YOLOv9 detection results from both RGB and RGN data, leveraging the strengths of each spectral combination to enhance detection accuracy and achieving a final counting accuracy of 98.4%. This study highlights the importance of integrating UAV multispectral technology with deep learning for coffee detection and offers new insights for the implementation of precision agriculture.

Rocky desertification severely restricts socio-economic development in the karst regions. However, assessments linking karst rocky desertification and NPP changes over the long term and at high resolution are limited. This study aims to reveal the spatiotemporal patterns and driving mechanisms of NPP changes in Wenshan Prefecture, addressing the scientific gap in quantitative process research and mechanism identification in karst desertification areas. We estimated vegetation NPP from 2000 to 2020 using remote sensing data and the CASA model. The Theil–Sen trend analysis and Mann–Kendall test were applied to assess temporal variation, while a Geographical Detector identified the dominant natural and human factors and their interactions shaping NPP spatial patterns. Our results showed that NPP increased overall by 4.07 gC m⁻² a⁻¹, alongside a general decline in rocky desertification. The most significant improvement occurred between 2010 and 2015, when rocky desertification shrank by 2224 km² and the dynamic rate reached 1.42%. Mean NPP reached 1057 gC m⁻² a⁻¹, with a “northwest high–southeast low” spatial pattern, and 77% of the region showed significant increases. Rocky desertification was most severe at elevations between 1000 and 2000 m. In the karst region, NPP is mainly controlled by natural factors, with soil depth and slope being the strongest influences. Human activity had the largest negative impact, and most factors interacted synergistically, where hydrothermal gradients and human disturbances more strongly suppressed NPP on steep, thin slopes than individually expected. These findings provide robust scientific evidence and practical decision-making support for ecological restoration, rocky desertification control and long-term sustainable development in Wenshan and other karst regions, highlighting the importance of continuous monitoring and adaptive management strategies to consolidate restoration achievements and guide future land-use planning and regional ecological policy.

Introduction: Forest aboveground biomass (AGB) is a critical carbon reservoir, and forest aboveground carbon stock (AGCS) is an important indicator of ecosystem carbon sequestration potential. However, accurate regional-scale AGCS mapping remains challenging in data-scarce regions because sparse field samples and strong spatial heterogeneity can lead to unstable errors that are difficult to quantify in both traditional and machine-learning regression models. Methods: To address this issue, we developed a Probabilistic Soft-Classification–Expectation Fusion (PSC–EF) framework for small-sample AGCS estimation in Huize County, China. The framework integrates Landsat 5 and ALOS PALSAR imagery with 42 field plots. It first uses a multi-source feature classifier to generate pixel-wise probability maps for three carbon-density classes, then reconstructs a continuous AGCS surface through expectation fusion, and finally quantifies uncertainty using variance propagation and bootstrap resampling. Results: Under 2×2 spatial block cross-validation, PSC–EF achieved a root mean square error (RMSE) of 182.13 Mg C ha ⁻¹ , a mean absolute error (MAE) of 150.92 Mg C ha ⁻¹ , and a bias of −4.64 Mg C ha ⁻¹ for continuous AGCS estimation. The probability maps showed a coherent low-to-high carbon gradient, and the total AGCS estimate for Huize County was consistent, with overlapping 95% confidence intervals derived from bootstrap resampling (4.54–5.18 × 10 ⁷ Mg C) and variance propagation (4.84–4.85 × 10 ⁷ Mg C). Discussion: The PSC–EF framework enables continuous AGCS mapping from probabilistic class membership while providing uncertainty information suitable for spatial decision-making. This framework provides spatially explicit carbon stock estimates with quantified uncertainty, supporting local carbon management and offering a transferable approach for AGCS assessment in other data-scarce regions.

Forest disturbance is a major driver shaping the structure and function of plantation ecosystems. Current research predominantly focuses on single forest types or landscape scales. However, species-level fine-scale assessments of disturbance dynamics are still scarce. In this study, we investigated Chinese fir (Cunninghamia lanceolata), Armand pine (Pinus armandii), and Yunnan pine (Pinus yunnanensis) plantations in the mountainous eastern Yunnan Plateau. We developed a Spatial Coupling Framework of Disturbance Legacy (SC-DL) to systematically elucidate the spatial associations between contemporary species distribution patterns and historical disturbance regimes. Using the Google Earth Engine (GEE) platform, we reconstructed pixel-level disturbance trajectories by integrating long-term Landsat time series (1993–2024) and applying the LandTrendr algorithm. By fusing multi-source remote sensing features (Sentinel-1/2) with terrain factors, employing RFE, and performing a multi-model comparison, we generated 10 m-resolution species distribution maps for 2024. Spatial overlay analysis quantified the cumulative proportion of the historically disturbed area and the spatial aggregation patterns of historical disturbances within current species ranges. Key results include the following: (1) The model predicting disturbance year achieved high accuracy (R² = 0.95, RMSE = 2.02 years, MAE = 1.15 years). The total disturbed area from 1993 to 2024 was 872.7 km², exhibiting three distinct phases. (2) The random forest (RF) model outperformed other classifiers, achieving an overall accuracy (OA) of 95.17% and a Kappa coefficient (K) of 0.93. Elevation was identified as the most discriminative feature. (3) Significant spatial differentiation in disturbance types emerged: anthropogenic disturbances (e.g., logging and reforestation/afforestation) dominated (63.1% of total disturbed area), primarily concentrated within Chinese fir zones (constituting 70.2% of disturbances within this species’ range). Natural disturbances accounted for 36.9% of the total, with fire dominating within the Yunnan pine range (79.3% of natural disturbances in this zone) and drought prevailing in the Armand pine range (71.3% of natural disturbances in this zone). (4) Cumulative disturbance characteristics differed markedly among species zones: Chinese fir zones exhibited the highest cumulative proportion of disturbed area (42.6%), with strong spatial aggregation. Yunnan pine zones followed (36.5%), exhibiting disturbances linearly distributed along dry–hot valleys. Armand pine zones showed the lowest proportion (20.9%), characterized by sparse disturbances within fragmented, high-altitude habitats. These spatial patterns reflect the combined controls of topographic adaptation, management intensity, and environmental stress. Our findings establish a scientific basis for identifying disturbance-prone areas and inform the development of differentiated precision management strategies for plantations.

Current mainstream remote sensing approaches to forest age estimation frequently neglect interspecific differences in functional traits, which may limit the accurate representation of species-specific tree growth strategies. This study develops and validates a technical framework that incorporates multi-source remote sensing and tree species functional trait heterogeneity to systematically improve the accuracy of plantation age mapping. We constructed a processing chain—“multi-source feature fusion–species identification–heterogeneity modeling”—for a typical karst plantation landscape in southeastern Yunnan. Using the Google Earth Engine (GEE) platform, we integrated Sentinel-1/2 and Landsat time-series data, implemented a Gradient Boosting Decision Tree (GBDT) algorithm for species classification, and built age estimation models that incorporate species identity as a proxy for the growth strategy heterogeneity delineated by the Plant Economic Spectrum (PES) theory. Key results indicate: (1) Species classification reached an overall accuracy of 89.34% under spatial block cross-validation, establishing a reliable basis for subsequent modeling. (2) The operational model incorporating species information achieved an R² (coefficient of determination) of 0.84 (RMSE (Root Mean Square Error) = 6.52 years) on the test set, demonstrating a substantial improvement over the baseline model that ignored species heterogeneity (R² = 0.62). This demonstrates that species identity serves as an effective proxy for capturing the growth strategy heterogeneity described by the Plant Economic Spectrum (PES) theory, which is both distinguishable and valuable for modeling within the remote sensing feature space. (3) Error propagation analysis demonstrated strong robustness to classification uncertainties (γ = 0.23). (4) Plantation structure in the region was predominantly young-aged, with forests aged 0–20 years covering over 70% of the area. Despite inherent uncertainties in ground-reference age data, the integrated framework exhibited clear relative superiority, improving R² from 0.62 to 0.84. Both error propagation analysis (γ = 0.23) and Monte Carlo simulations affirmed the robustness of the tandem workflow and the stability of the findings, providing a reliable methodology for improved-accuracy plantation carbon sink quantification.