The accurate and scalable estimation of carbon stocks in living biomass remains challenging in structurally heterogeneous forests subjected to different silvicultural treatments. This study presents a multi-sensor machine learning framework that integrates unmanned aerial vehicle (UAV)-derived multispectral imagery with UAV- and airborne light detection and ranging (LiDAR) data for spatially explicit carbon stock estimation in managed forests of central and eastern Hokkaido, northern Japan. Field measurements from 38 plots were used for model development and validation. Spectral features derived from UAV multispectral imagery and structural metrics derived from UAV and airborne LiDAR data were integrated within a multi-sensor framework and evaluated using Multiple Linear Regression (MLR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost), with MLR serving as a baseline model. A key objective was to quantify the relative contributions of spectral and structural sensing information for carbon stock estimation in silviculturally treated forests through the systematic comparison of canopy height model (CHM)-only, RGB + CHM, and multispectral + CHM datasets. The machine learning models consistently outperformed the baseline MLR model, with XGBoost generally outperforming RF and achieving a maximum validation R² of 0.88 and root mean squared error (RMSE) of 27.41 Mg C ha⁻¹. Although the improvement in plot-level prediction accuracy over the CHM-only configuration was modest, integrating multispectral imagery with LiDAR-derived structural metrics reduced prediction errors and systematic bias in wall-to-wall carbon stock mapping. These findings highlight the complementary roles of structural and spectral remote sensing information for spatially explicit carbon stock estimation in silviculturally treated forests.

This study developed a hybrid deep learning framework for individual-tree crown delineation and species classification in broadleaf-dominated mixed forests using unmanned aerial vehicle (UAV)-derived multisource imagery and airborne Light Detection and Ranging (LiDAR) data. The study was conducted in two forest sites located in eastern Hokkaido, northern Japan. For individual-tree crown delineation, a Mask R-CNN model integrating UAV-derived RGB imagery and airborne LiDAR-derived canopy height model (CHM) data was developed, achieving F1-scores above 0.80. The delineated individual-tree crowns provided the basis for the subsequent species classification stage. For species classification, a deep neural network (DNN) was developed using feature embeddings extracted from the DINOv2 Vision Transformer (ViT-Small), combined with spectral and structural features derived from Normalized Difference Vegetation Index (NDVI), Green NDVI (GNDVI), and Normalized Difference Red Edge (NDRE), near-infrared (NIR), and CHM datasets. The proposed DINOv2-based DNN classifier achieved weighted F1-scores above 0.80 and outperformed the baseline Mask R-CNN-based classification approach. These results demonstrate the effectiveness of separating crown delineation and species classification tasks within a hybrid framework for accurate individual-tree species classification in complex mixed forests.