This study evaluates land cover classification accuracy through adjustments to the deep learning model (DLM) training process, including variations in loss function, the learning rate scheduler, and the optimizer, along with diverse input dataset compositions. DLM datasets were created by integrating surface reflectance (SR) spectral data from satellite imagery with textural information derived from the gray-level co-occurrence matrix, yielding four distinct datasets. The U-Net model served as the baseline, with models A and B configured by adjusting the training parameters. Eight land cover classifications were generated from four datasets and two deep learning training conditions. Model B, utilizing a dataset comprising spectral, textural, and terrain information, achieved the highest overall accuracy of 90.3% and a kappa coefficient of 0.78. Comparing different dataset compositions, incorporating textural and terrain data alongside SR from satellite imagery significantly enhanced classification accuracy. Furthermore, using a combination of multiple loss functions or dynamically adjusting the learning rate effectively mitigated overfitting issues, enhancing land cover classification accuracy compared to using a single loss function.

The aim of this study was to select the optimal deep learning model for land cover classification through hyperparameter adjustment. A U-Net model with encoder and decoder structures was used as the deep learning model, and RapidEye satellite images and a sub-divided land cover map provided by the Ministry of Environment were used as the training dataset and label images, respectively. According to different combinations of hyperparameters, including the size of the input image, the configuration of convolutional layers, the kernel size, and the number of pooling and up-convolutional layers, 90 deep learning models were built, and the model performance was evaluated through the training accuracy and loss, as well as the validation accuracy and loss values. The evaluation results showed that the accuracy was higher with a smaller image size and a smaller kernel size, and was more dependent on the convolutional layer configuration and number of layers than the kernel size. The loss tended to be lower as the convolutional layer composition and number of layers increased, regardless of the image size or kernel size. The deep learning model with the best performance recorded a validation loss of 0.11 with an image size of 64 × 64, a convolutional layer configuration of C→C→C→P, a kernel size of 5 × 5, and five layers. Regarding the classification accuracy of the land cover map constructed using this model, the overall accuracy and kappa coefficient for three study cities showed high agreement at approximately 82.9% and 66.3%, respectively.

This study aimed to develop a thinning tree selection system by applying genetic algorithms based on precisely estimated tree-level forest structural parameters derived from LiDAR data. Conventional thinning tree selection methods have limitations due to their dependence on subjective judgement and field experience of operators, resulting in inconsistency and variations according to skill levels. To address these issues, tree positions, diameters at breast height (DBH), and tree heights were extracted by integrating terrestrial laser scanning (TLS) and Unmanned Aerial Vehicle Laser Scanning (ULS) data, forming a Multi-Platform LiDAR dataset. The derived DBH and Hegyi competition index were utilized as indicators for thinning tree selection. Optimization of tree selection was performed using a genetic algorithm, with an objective function designed to maximize the average DBH and minimize the average competition index of the remaining trees, and the system’s performance was compared with results obtained by forestry experts. The results showed that tree detection accuracy exceeded 99%, DBH estimation exhibited an RMSE of 0.74 cm, and tree height estimation showed an RMSE of approximately 2 m, demonstrating the construction of precise forest structural parameters. Compared to expert driven selection, the Genetic Algorithm-based thinning system produced a higher average DBH (30.06 cm vs. 29.26 cm) and a lower Hegyi competition index (1.31 vs. 1.41) under Scenario 3. This indicates superior performance in competition alleviation and growing space allocation among individual trees. Spatial statistical analysis revealed that while expert selection maintained the existing spatial clustering pattern of stand structure (Global Moran’s I = 0.16), the machine learning system achieved an almost random distribution (Global Moran’s I = −0.04) under Scenario 3. This study demonstrates the potential of overcoming the limitations of conventional thinning practices dependent on subjective judgement by introducing an objective, consistent, data-driven quantitative decision support system for precision forest management.

This study aims to segment individual tree structures (stem, crown, and ground) from terrestrial LiDAR-derived point cloud data (PCD) and to compare the segmentation accuracy between two models: XGBoost (machine learning) and PointNet++ (deep learning). A total of 17 input features were categorized into spatial coordinates and normals, geometric structure features, and local distribution features. These were combined into four input configurations and evaluated under three downsampling conditions (2048, 4096, and 8192 points), resulting in 12 experimental setups. XGBoost achieved the highest stem segmentation F₁-score of 87.8% using all features with 8192 points, whereas Point-Net++ reached 92.1% using only spatial coordinates and normals with 4096 points. The analysis of missegmentation patterns showed that XGBoost frequently confused structures near stem-to-ground boundaries and around branch junctions, while PointNet++ occasionally missegmented complex regions between stems and crowns. Regarding processing time, XGBoost required 10 to 47 min across all conditions, whereas Point-Net++ required 49 min for the 2048-point condition and up to 168 min for 8192 points. Overall, XGBoost provided advantages in computational efficiency and in generating feature-importance scores, while PointNet++ outperformed XGBoost in segmentation accuracy and the recognition of structurally complex regions.

Woo-Dam Sim, Jung-Soo Lee. Korean J. Remote Sens. 2024;40:675-89. https://doi.org/10.7780/kjrs.2024.40.5.1.20