• Journal of Forest and Environmental Science
• /
• v.39 no.4
• /
• pp.254-260
• /
• 2023

A sensor system has been developed that uses an ultrasonic sensor to detect the downhill slope on the side of a forest road and prevents a vehicle-type forest machine from rolling down a mountainside. A specular reflection of ultrasonic wave might cause severe issues in measuring distances to targets. By investigating the installation angle of the sensor to minimize the negative effects of specular reflection, the installation angle of lateral monitoring ultrasonic sensor could be determined based on the width of road shoulder. Obstacles such as small rocks or piece of log in a forest road may cause the forest machine to be overturned while the machine riding over due to excessive its posture change. It was determined that the laser sensor could be a part of a sensor system capable of specifying the location and size of small obstacles. Not only this sensor system including ultrasonic and laser sensors can issue a warning of dangerous sections to drivers in forest forwarders currently in use, but also it can be used as a driving safety sensor in autonomous forest machine or remote-control forest machine in the future.

• Journal of Forest and Environmental Science
• /
• v.39 no.4
• /
• pp.195-202
• /
• 2023

In this study, we sought to compare and evaluate the accuracy and predictive performance of machine learning algorithms for estimating the growth of individual Larix kaempferi trees in Gangwon Province, Korea. We employed linear regression, random forest, XGBoost, and LightGBM algorithms to predict tree growth using monitoring data organized based on different thinning intensities. Furthermore, we compared and evaluated the goodness-of-fit of these models using metrics such as the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). The results revealed that XGBoost provided the highest goodness-of-fit, with an R² value of 0.62 across all thinning intensities, while also yielding the lowest values for MAE and RMSE, thereby indicating the best model fit. When predicting the growth volume of individual trees after 3 years using the XGBoost model, the agreement was exceptionally high, reaching approximately 97% for all stand sites in accordance with the different thinning intensities. Notably, in non-thinned plots, the predicted volumes were approximately 2.1 m³ lower than the actual volumes; however, the agreement remained highly accurate at approximately 99.5%. These findings will contribute to the development of growth prediction models for individual trees using machine learning algorithms.

• Korean Journal of Remote Sensing
• /
• v.40 no.2
• /
• pp.123-139
• /
• 2024

Forest vertical structure is vital for comprehending ecosystems and biodiversity, in addition to fundamental forest information. Currently, the forest vertical structure is predominantly assessed via an in-situ method, which is not only difficult to apply to inaccessible locations or large areas but also costly and requires substantial human resources. Therefore, mapping systems based on remote sensing data have been actively explored. Recently, research on analyzing and classifying images using machine learning techniques has been actively conducted and applied to map the vertical structure of forests accurately. In this study, Sentinel-2 and digital surface model images were obtained on two different dates separated by approximately one month, and the spectral index and tree height maps were generated separately. Furthermore, according to the acquisition time, the input data were separated into cases 1 and 2, which were then combined to generate case 3. Using these data, forest vetical structure mapping models based on random forest, support vector machine, and extreme gradient boost(XGBoost)were generated. Consequently, nine models were generated, with the XGBoost model in Case 3 performing the best, with an average precision of 0.99 and an F1 score of 0.91. We confirmed that generating a forest vertical structure mapping model utilizing bi-seasonal data and an appropriate model can result in an accuracy of 90% or higher.

• Atmosphere
• /
• v.33 no.1
• /
• pp.61-72
• /
• 2023

Accurate estimation of forest carbon stocks is important in establishing greenhouse gas reduction plans. In this study, we estimate the spatial distribution of forest carbon stocks using machine learning techniques based on high-resolution remote sensing data and detailed field survey data. The high-resolution remote sensing data used in this study are Landsat indices (EVI, NDVI, NDII) for monitoring vegetation vitality and Shuttle Radar Topography Mission (SRTM) data for describing topography. We also used the forest growing stock data from the National Forest Inventory (NFI) for estimating forest biomass. Based on these data, we built a model based on machine learning methods and optimized for Korean forest types to calculate the forest carbon stocks per grid unit. With the newly developed estimation model, we created forest carbon stocks maps and estimated the forest carbon stocks in South Korea. As a result, forest carbon stock in South Korea was estimated to be 432,214,520 tC in 2020. Furthermore, we estimated the loss of forest carbon stocks due to the Donghae-Uljin forest fire in 2022 using the forest carbon stock map in this study. The surrounding forest destroyed around the fire area was estimated to be about 24,835 ha and the loss of forest carbon stocks was estimated to be 1,396,457 tC. Our model serves as a tool to estimate spatially distributed local forest carbon stocks and facilitates accounting of real-time changes in the carbon balance as well as managing the LULUCF part of greenhouse gas inventories.

• Journal of Environmental Science International
• /
• v.26 no.4
• /
• pp.521-527
• /
• 2017

Solar radiation forecasts are important for predicting the amount of ice on road and the potential solar energy. In an attempt to improve solar radiation predictability in Jeju, we conducted machine learning with various data mining techniques such as tree models, conditional inference tree, random forest, support vector machines and logistic regression. To validate machine learning models, the results from the simulation was compared with the solar radiation data observed over Jeju observation site. According to the model assesment, it can be seen that the solar radiation prediction using random forest is the most effective method. The error rate proposed by random forest data mining is 17%.

• Korea Trade Review
• /
• v.46 no.2
• /
• pp.281-299
• /
• 2021

This paper analyzes the feasibility of using machine learning methods to forecast the employment. The machine learning methods, such as decision tree, artificial neural network, and ensemble models such as random forest and gradient boosting regression tree were used to forecast the employment in Busan regional economy. The following were the main findings of the comparison of their predictive abilities. First, the forecasting power of machine learning methods can predict the employment well. Second, the forecasting values for the employment by decision tree models appeared somewhat differently according to the depth of decision trees. Third, the predictive power of artificial neural network model, however, does not show the high predictive power. Fourth, the ensemble models such as random forest and gradient boosting regression tree model show the higher predictive power. Thus, since the machine learning method can accurately predict the employment, we need to improve the accuracy of forecasting employment with the use of machine learning methods.

• The Pure and Applied Mathematics
• /
• v.24 no.4
• /
• pp.211-226
• /
• 2017

In this paper, machine learning models employed in various fields are discussed and applied to KOSPI200 stock index return forecasting. The results of hyperparameter analysis of the machine learning models are also reported and practical methods for each model are presented. As a result of the analysis, Support Vector Machine and Artificial Neural Network showed a better performance than k-Nearest Neighbor and Random Forest.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.229-239
• /
• 2019

All vegetation colonies have layered structure. This layer is called 'forest vertical structure.' Nowadays it is considered as an important indicator to estimate forest's vital condition, diversity and environmental effect of forest. So forest vertical structure should be surveyed. However, vertical structure is a kind of inner structure, so forest surveys are generally conducted through field surveys, a traditional forest inventory method which costs plenty of time and budget. Therefore, in this study, we propose a useful method to classify the vertical structure of forests using remote sensing aerial photographs and machine learning capable of mass data mining in order to reduce time and budget for forest vertical structure investigation. We classified it as SVM (Support Vector Machine) using RGB airborne photos and LiDAR (Light Detection and Ranging) DSM (Digital Surface Model) DTM (Digital Terrain Model). Accuracy based on pixel count is 66.22% when compared to field survey results. It is concluded that classification accuracy of layer classification is relatively high for single-layer and multi-layer classification, but it was concluded that it is difficult in multi-layer classification. The results of this study are expected to further develop the field of machine learning research on vegetation structure by collecting various vegetation data and image data in the future.

• Journal of Korean Society of Forest Science
• /
• v.111 no.4
• /
• pp.603-612
• /
• 2022

The study aims were to evaluate a machine-learning, algorithm-based, forest biomass-estimation model to estimate subnational forest biomass and to comparatively analyze REDD+ forest reference emission levels. Time-series Landsat satellite imagery and ESA Biomass Climate Change Initiative information were used to build a machine-learning-based biomass estimation model. The k-nearest neighbors algorithm (kNN), which is a non-parametric learning model, and the tree-based random forest (RF) model were applied to the machine-learning algorithm, and the estimated biomasses were compared with the forest reference emission levels (FREL) data, which was provided by the Paraguayan government. The root mean square error (RMSE), which was the optimum parameter of the kNN model, was 35.9, and the RMSE of the RF model was lower at 34.41, showing that the RF model was superior. As a result of separately using the FREL, kNN, and RF methods to set the reference emission levels, the gradient was set to approximately -33,000 tons, -253,000 tons, and -92,000 tons, respectively. These results showed that the machine learning-based estimation model was more suitable than the existing methods for setting reference emission levels.

• Journal of Korean Society of Forest Science
• /
• v.112 no.2
• /
• pp.145-156
• /
• 2023

In this study, Fourier-transform near-infrared (FT-NIR) spectra of Korean red pine seeds stored at -18℃ and 4℃ for 18 years were analyzed. To develop seed-germination prediction models, the performance of seven machine learning methods, namely XGBoost, Boosted Tree, Bootstrap Forest, Neural Networks, Decision Tree, Support Vector Machine, PLS-DA, were compared. The predictive performance, assessed by accuracy, misclassification, and area under the curve (0.9722, 0.0278, and 0.9735 for XGBoost, and 0.9653, 0.0347, and 0.9647 for Boosted Tree), was better for the XGBoost and decision tree models when compared with other models. The 54 wave-number variables of the two models were of high relative importance in seed-germination prediction and were grouped into six spectral ranges (811~1,088 nm, 1,137~1,273 nm, 1,336~1,453 nm, 1,666~1,671 nm, 1,879~2,045 nm, and 2,058~2,409 nm) for aromatic amino acids, cellulose, lignin, starch, fatty acids, and moisture, respectively. Use of the NIR spectral data and two machine learning models developed in this study gave >96% accuracy for the prediction of pine-seed germination after long-term storage, indicating this approach could be useful for non-destructive viability testing of stored seed genetic resources.