A smart thinning operation refers to an advanced method of selecting and cutting trees to be thinned based on digitally captured forest information. In smart thinning operations, workers use the coordinates of individual trees to navigate to the target trees for thinning. However, it is difficult to accurately locate individual trees in a forest stand covered with a canopy, necessitating a precise real-time positioning system that can be used in the forest. Therefore, this study aimed to evaluate the applicability of the global navigation satellite system real-time kinematic (GNSS-RTK) device in a forest stand through analysis of its positioning accuracy within the forest environment and evaluation of the operational range of the single-baseline RTK based on analysis of the positioning precision and radio signal strength index (RSSI) change with increasing distance from the base station. The results showed that the root mean square error (RMSE) of the horizontal positioning error was highly accurate, with an average of 0.26 m in Larix kaempferi stands and 0.48 m in Pinus koraiensis stands. The RSSI decreased to a minimum of −103.3 dBm within 1 km of distance from the base station; however, this had no significant impact on the horizontal positioning precision. The conclusion is that the GNSS-RTK is suitable for use in smart thinning operations.

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.

Analyzing the current status of forest loss and its causes is crucial for understanding and preparing for future forest changes and the spatial pattern of forest loss. We investigated spatial patterns of forest loss in South Korea and assessed the effects of various factors on forest loss based on spatial heterogeneity. We used the local Moran’s I to classify forest loss spatial patterns as high–high clusters, low–low clusters, high–low outliers, and high–low outliers. Additionally, to assess the effect of factors on forest loss, two statistical models (i.e., ordinary least squares regression (OLS) and geographically weighted regression (GWR) models) and one machine-learning model (i.e., random forest (RF) model) were used. The accuracy of each model was determined using the R², RMSE, MAE, and AICc. Across South Korea, the forest loss rate was highest in the Seoul–Incheon–Gyeonggi region. Moreover, high–high spatial clusters were found in the Seoul–Incheon–Gyeonggi and Daejeon–Chungnam regions. Among the models, the GWR model was the most accurate. Notably, according to the GWR model, the main factors driving forest loss were road density, cropland area, number of households, and number of tertiary industry establishments. However, the factors driving forest loss had varying degrees of influence depending on the location. Therefore, our findings suggest that spatial heterogeneity should be considered when developing policies to reduce forest loss.

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.

A growing societal interest exists in the application of lidar technology to monitor forest resource information and forestry management activities. This study examined the possibility of estimating the diameter at breast height (DBH) of two tree species, Pinus koraiensis (PK) and Larix kaempferi (LK), by varying the number of terrestrial laser scanning (TLS) scans (1, 3, 5, 7, and 9) and DBH estimation methods (circle fitting [CF], ellipse fitting [EF], circle fitting with RANSAC [RCF], and ellipse fitting with RANSAC [REF]). This study evaluates the combination that yields the highest estimation accuracy. The results showed that for PK, the lowest RMSE of 0.97 was achieved when REF was applied to the data from nine scans after noise removal. For LK, the lowest RMSE of 1.03 was observed when applying CF to the data from seven scans after noise removal. Furthermore, ANOVA revealed no significant difference in the estimated DBH from nine scans when more than three scans were used for CF and RCF and more than five for EF and REF. These results are expected to be useful in establishing efficient and accurate DBH estimation plans using TLS for forest resource monitoring.