The increasing number of severe storm events is threatening European forests. Besides the primary damages directly caused by storms, there are secondary damages such as bark beetle outbreaks and tertiary damages due to negative effects on the market. These subsequent damages can be minimized if a detailed overview of the affected area and the amount of damaged wood can be obtained quickly and included in the planning of clearance measures. The present work utilizes UAV-orthophotos and an adaptation of the U-Net architecture for the semantic segmentation and localization of windthrown stems. The network was pre-trained with generic datasets, randomly combining stems and background samples in a copy–paste augmentation, and afterwards trained with a specific dataset of a particular windthrow. The models pre-trained with generic datasets containing 10, 50 and 100 augmentations per annotated windthrown stems achieved F1-scores of 73.9% (S1Mod10), 74.3% (S1Mod50) and 75.6% (S1Mod100), outperforming the baseline model (F1-score 72.6%), which was not pre-trained. These results emphasize the applicability of the method to correctly identify windthrown trees and suggest the collection of training samples from other tree species and windthrow areas to improve the ability to generalize. Further enhancements of the network architecture are considered to improve the classification performance and to minimize the calculative costs.

Accurate digital forest inventory (DFI) is essential for sustainable forest management, yet single-sensor LiDAR approaches often fall short in capturing the full vertical structure of forest stands. This study evaluates the performance of a fused dataset combining UAV-based LiDAR (ULS) and personal laser scanner (PLS) data to overcome platform-specific limitations. A mixed forest stand in northeastern Germany was surveyed using both ULS and PLS under consistent scanning patterns, supported by ground control points for georeferencing. Point cloud fusion was achieved through a dynamic marker-based alignment and refined using partial iterative closest point (ICP) registration. The fused dataset, processed in TreeLS, enabled detailed stem reconstruction and vertical canopy characterization. Comparative analysis against field-measured tree metrics revealed a mean deviation of −2.5% for diameter at breast height (DBH) and +4.9% for tree height, with RMSE values of 2.9 cm and 3.84 m, respectively. These results highlight the complementary strengths of ULS and PLS platforms, demonstrating that their integration significantly enhances the accuracy, completeness, and efficiency of forest inventories. The presented workflow supports scalable, repeatable, and ecologically informative forest assessments, offering substantial potential for precision forestry and long-term monitoring applications.

Forest inventories are essential for sustainable forest management and health monitoring. Image-based surveys using unmanned aerial vehicles (UAVs) are increasingly adopted for this purpose. DeepForest, a deep learning model pre-trained on large annotated datasets, enables scalable and cost-efficient tree detection in the resulting imagery. Although it is known that fine-tuning DeepForest to specific target sites improves its performance, optimal fine-tuning strategies remain unclear. In this study, we investigate the fine-tuning of DeepForest on a small dataset of UAV imagery from a temperate mixed forest. We examine the influence of four parameters on model performance: (1) the method used to label training data (manual labeling, manual correction of DeepForest predictions, and automatic labeling using 3D point cloud segmentation), (2) input image resolution, (3) the number of fine-tuning epochs, and (4) the size of the training dataset. Our results show that the out-of-the-box DeepForest model performs poorly on the target dataset but substantially improves with fine-tuning, even when using limited data and a small number of training epochs. Manual and automatic labeling achieve similarly high performance, both outperforming the manual correction approach. Although the model initially performs better on lower-resolution images, this difference diminishes after fine-tuning on higher-resolution inputs. We observe no clear benefit from increasing the training set size, possibly due to the low diversity of our test dataset. Overall, our findings confirm that DeepForest is a suitable base model for forest tree detection in high-resolution UAV imagery and can be adapted to new environments with low effort.