Individual-tree aboveground biomass (AGB) estimation can highlight the spatial distribution of AGB and is vital for precision forestry. Accurately estimating individual tree AGB is a requisite for accurate forest carbon stock assessment of natural secondary forests (NSFs). In this study, we investigated the performance of three machine learning and three ensemble learning algorithms in tree species classification based on airborne laser scanning (ALS) and WorldView-3 imagery, inversed the diameter at breast height (DBH) using an optimal tree height curve model, and mapped individual tree AGB for a site in northeast China using additive biomass equations, tree species, and inversed DBH. The results showed that the combination of ALS and WorldView-3 performed better than either single data source in tree species classification, and ensemble learning algorithms outperformed machine learning algorithms (except CNN). Seven tree species had satisfactory accuracy of individual tree AGB estimation, with R² values ranging from 0.68 to 0.85 and RMSE ranging from 7.47 kg to 36.83 kg. The average individual tree AGB was 125.32 kg and the forest AGB was 113.58 Mg/ha in the Maoershan study site in Heilongjiang Province, China. This study provides a way to classify tree species and estimate individual tree AGB of NSFs based on ALS data and WorldView-3 imagery.

Identifying important factors (e.g., features and prediction models) for forest aboveground biomass (AGB) estimation can provide a vital reference for accurate AGB estimation. This study proposed a novel feature of the canopy height distribution (CHD), a function of canopy height, that is useful for describing canopy structure for AGB estimation of natural secondary forests (NSFs) by fitting a bimodal Gaussian function. Three machine learning models (Support Vector Regression (SVR), Random Forest (RF), and eXtreme Gradient Boosting (Xgboost)) and three deep learning models (One-dimensional Convolutional Neural Network (1D-CNN4), 1D Visual Geometry Group Network (1D-VGG16), and 1D Residual Network (1D-Resnet34)) were applied. A completely randomized design was utilized to investigate the effects of four feature sets (original CHD features, original LiDAR features, the proposed CHD features fitted by the bimodal Gaussian function, and the LiDAR features selected by the recursive feature elimination algorithm) and models on estimating the AGB of NSFs. Results revealed that the models were the most important factor for AGB estimation, followed by the features. The fitted CHD features significantly outperformed the other three feature sets in most cases. When employing the fitted CHD features, the 1D-Renset34 model demonstrates optimal performance (R² = 0.80, RMSE = 9.58 Mg/ha, rRMSE = 0.09), surpassing not only other deep learning models (e.g.,1D-VGG16: R² = 0.65, RMSE = 18.55 Mg/ha, rRMSE = 0.17) but also the best machine learning model (RF: R² = 0.50, RMSE = 19.42 Mg/ha, rRMSE = 0.16). This study highlights the significant role of the new CHD features fitting a bimodal Gaussian function and the effects between the models and the CHD features, which provide the sound foundations for effective estimation of AGB in NSFs.

Natural secondary forests play a crucial role in global ecological security, climate change mitigation, and biodiversity conservation. However, accurately delineating individual tree crowns and identifying tree species in dense natural secondary forests remains a challenge. This study combines deep learning with traditional image segmentation methods to improve individual tree crown detection and species classification. The approach utilizes hyperspectral, unmanned aerial vehicle laser scanning data, and ground survey data from Maoershan Forest Farm in Heilongjiang Province, China. The study consists of two main processes: (1) combining semantic segmentation algorithms (U-Net and Deeplab V3 Plus) with watershed transform (WTS) for tree crown detection (U-WTS and D-WTS algorithms); (2) resampling the original images to different pixel densities (16 × 16, 32 × 32, and 64 × 64 pixels) and inputting them into five 3D-CNN models (ResNet10, ResNet18, ResNet34, ResNet50, VGG16). For tree species classification, the MSFB combined with the CNN models were used. The results show that the U-WTS algorithm achieved a recall of 0.809, precision of 0.885, and an F-score of 0.845. ResNet18 with a pixel density of 64 × 64 pixels achieved the highest overall accuracy (OA) of 0.916, an improvement of 0.049 over the original images. After incorporating MSFB, the OA improved by approximately 0.04 across all models, with only a 6% increase in model parameters. Notably, the floating-point operations (FLOPs) of ResNet18 + MSFB were only one-eighth of those of ResNet18 with 64 × 64 pixels, while achieving similar accuracy (OA: 0.912 vs. 0.916). This framework offers a scalable solution for large-scale tree species distribution mapping and forest resource inventories.