• Journal of Forest and Environmental Science
• /
• 제39권4호
• /
• 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
• /
• 제39권4호
• /
• 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.

• 대한원격탐사학회지
• /
• 제40권2호
• /
• 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.

• 대기
• /
• 제33권1호
• /
• 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.

• 한국환경과학회지
• /
• 제26권4호
• /
• 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%.

• 무역학회지
• /
• 제46권2호
• /
• 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.

• 한국수학교육학회지시리즈B:순수및응용수학
• /
• 제24권4호
• /
• 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.

• 대한원격탐사학회지
• /
• 제35권2호
• /
• pp.229-239
• /
• 2019

모든 식생 군락은 각자 층위구조를 가지고 있다. 이를 '식생층위구조'라 부른다. 요즈음은 이 층위구조가 산림의 활력도, 다양성, 그리고 환경영향을 평가하는데 중요한 식별자로 작용하기 때문에 산림조사에 있어서 식생층위구조는 필수적으로 조사되어야한다. 그런데, 식생층위구조는 일종의 내부구조이므로 일반적으로 산림조사는 현장조사를 통해 이루어지는데, 이는 전통적인 방식으로 시간과 예산이 많이 든다. 따라서 본 연구에서는 산림의 층위구조를 조사하는데 드는 시간과 예산을 줄이기 위해 넓은 지역 탐사에 효과적인 원격탐사기법 중 항공촬영 사진과 대량의 데이터 마이닝(Data Mining)이 가능한 머신러닝(Machine Learning)기법 이용한 층위구조의 분류 방법을 제시한다. 칼라 항공사진, LiDAR(Light Detection and Ranging) DSM(Digital Surface Model)과 DTM(Digital Terrain Model)을 이용하여 Support Vector Machine(SVM) 머신러닝 기법을 이용하여 층위분류 연구를 진행하였다. 현장조사 자료를 참조하여 SVM기법 분류 결과와 비교했을 때 픽셀수에 기반한 정확도는 66.22%로 확인 되었다. 층위 분류 정확도는 단층과 다층의 구분은 비교적 높게 나타났으나, 다층끼리의 분류는 어렵다는 결론이 나타났다. 이러한 연구결과는 향후 다양한 식생데이터와 영상자료를 수집한다면 식생구조에 대한 머신러닝 연구분야에 더욱 발전이 가능할 것으로 기대된다.

• 한국산림과학회지
• /
• 제111권4호
• /
• pp.603-612
• /
• 2022

본 연구는 다중시기 위성영상과 머신러닝 알고리즘을 이용하여 준국가수준의 시계열 산림바이오매스량을 추정하였으며, 이를 바탕으로 산림배출기준선 설정하여 비교·분석하였다. 머신러닝기반의 산림바이오매스 추정 모델을 구축하기 위하여 Landsat TM 위성영상과 유럽항공우주국에서 제공하는 Biomass Climate Change Initiative 정보를 이용하였으며, 머신러닝 알고리즘은 비모수 학습모델인 k-Nearest Neighbor(kNN)과 의사결정나무 기반의 Random Forest(RF)를 적용하였다. 또한, 추정된 산림바이오매스량은 Forest reference emission levels(FREL) 자료와 비교하였다. 머신러닝 알고리즘 별 산림바이오매스 추정 모델을 비교해보면, 최적의 kNN 모델과 RF 모델의 Root Mean Square Error (RMSE)는 각각 35.9와 34.41였으며, RF모델이 kNN모델보다 상대적으로 우수하였다. 또한, FREL, kNN, RF 모델 별 산림배출기준선의 기울기는 각각 약 -33천ton, -253천ton, -92천ton으로 설정되었다.

• 한국산림과학회지
• /
• 제112권2호
• /
• pp.145-156
• /
• 2023

본 연구에서는 -18℃ 및 4℃에서 18년간 저장된 소나무 종자 963개에 대해 FT NIR 스펙트럼을 조사하여 7개 머신러닝 방법(XGBoost, Boosted Tree, Bootstrap Forest, Neural Networks, Decision Tree, Support Vector Machine, PLS-DA)을 이용한 종자발아 예측모델을 만들고, 그 성능을 비교하였다. XGBoost 및 Boosted Tree 모델의 예측성능이 가장 우수하였으며, 정확도, 오분류율 및 AUC 값은 각각 0.9722, 0.0278, 0.9735과 0.9653, 0.0347, 0.9647이었다. 2개 모델에서 종자발아 유무를 예측하는 데 있어 상대적 중요도가 높았던 54개 파수 변수들에 대한 파장대는 크게 6개(811~1,088 nm, 1,137~1,273 nm, 1,336~1,453 nm, 1,666~1,671 nm, 1,879~2,045 nm, 2,058~2,409 nm) 그룹으로 나눌 수 있었으며, 방향족 아미노산, 셀룰로스, 리그닌, 전분, 지방산 및 수분과 관련된 것으로 추정되었다. 이상의 결과를 종합할 때, 본 연구에서 얻어진 FT NIR 스펙트럼 데이터과 2개의 머신러닝 모델은 소나무 저장종자의 발아 유무를 정확도 96% 이상으로 예측할 수 있기에 장기저장 종자 유전자원의 비파괴적 활력검정에 유용하게 활용될 수 있을 것으로 생각된다.