• 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 Heritage: History & Science
• /
• v.43 no.1
• /
• pp.190-211
• /
• 2010

The purpose of this paper is to provide the preliminary data for maintenance of old trees of natural monuments and establishing protection projects. Accordingly, growth conditions, location circumstances, environment and protection management were analyzed for old trees at 34 sites in Gyeongsangbuk-do. Tree forms, crown, trunk and trees' health, leaves volume were analyzed in survey sites. As the results, the growth of Picrasma quassioides in Songsadong, Andong-si and Catalpa ovata in Hongwon-ri, Cheongsong-gun were not in good condition, along with other old trees of 6 cities (Quercus variabilis in Susan-ri, Uljin-gun, Juniperus chinensis in Hujeong-ri, Uljin-gun, Pyrus ussuriensis in Ssangjeon-ri, Uljin-gun, Salix glandulosa var. pilosa in Deokchon-ri, Cheongdo-gun, Pinus densiflora for. multicaulis in Hwasan-ri, Mungyeong-si, Pinus densiflora in Daeha-ri, Mungyeong-si). Accoding to these results, protection project and consistent monitoring are necessary. The analysis results of growth conditions per location circumstances showed that the old trees in the small spaces with large traffic of people were in bad condition. Therefore, it is necessary to secure sufficient space and soil improvement for such trees. The analysis results of growth conditions per species showed that Zelkova serrata, Quercus spp., Pinus densiflora are in good condition while Salix koreensis and others, i.e. a singular tree, are in poor condition. Thus, relatively smaller individuals and separately situated trees need careful management in their protection. The analysis results of trunk's growth ratio showed that Pinus densiflora, Ginkgo biloba, Zelkova serrata are in good condition whereas Juniperus chinensis, Quercus variabilis, Salix koreensis are not. It is a recent trend that tree surgeries are gradually decreasing; there are a number of damaged trees with no maintenance/management, and several sites requiring mend trunks management and cabling, bracing in protection and management projects. Hence, in the future, local government and management organizations should plan for systematic management and establish a protection plan for the natural monument trees. Also, 12 sites were found to be in need to purchase lands in order to secure the growth spaces, and since most of these areas are available for purchase, it is needed to promote a budget and purchase those areas through persuasion of the owner. These areas seems crucial in order to maximize the effect of conservation efforts and budgets for the preservation and restoration of the old trees.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.23 no.6
• /
• pp.109-123
• /
• 2020

The purpose of this study is to provide basic data for the establishment of future countermeasures by diagnosing the growth status and actual condition of undesignated old trees distributed in Hyeongok-myeon, Gyeongju, Gyeongsangbuk-do. The number of old trees surveyed was 2 weeks in Gajeong-ri, 2 weeks in Haguri, 3 weeks in Nae-Tae-ri, 1 week in Nawon-ri, 6 weeks in Oryu-ri, 3 weeks in Sangguri, and 2 weeks in Sohyeon-ri, The trees species composition was 6 trees Celtis sinensis Pers., 1 Diospyros lotus L. trees, 4 trees Salix chaenomeloides Kimura trees, 2 Styphnolobium japonicum L. trees, and 7 Zelkova serrata (Thunb.) Makino trees. Growth status is 7.1~22.0m in height, 14.6~25.1m in long axis, 10.2~19.2m in short axis, root diameter is 76.0~236.4cm, diamter at breast height is 67.0~220.0cm, soil acidity is pH4.9~7.0, soil The hardness was measured to be 4.0-27.0mm. The result grade of the scoring data of health information is represented by monitoring generally, monitoring critically, and absolute monitoring, and it was confirmed that out of the 20 trees population in Hyeongok-myeon, the general monitoring grade was 7 weeks, the major monitoring grade was 13 weeks, and there was no absolute monitoring grade. Accordingly, the number of old trees of the general surveillance level was maintained at the current level, and ecological surgical operations were introduced for the major surveillance level, but the case of village forests should be different, and sequential treatments were the old tree urgently needed. The level and bark of the target tree, the state of the crown, the root exposure, the presence of pests and pests, the vitality and the ground condition, the degree of pollution are normal, poor, or very poor, operation and protection management, soil improvement, removal of cover, and disinfection were urgently needed for the old trees with the surveyed data. In order to compensate for these matters, continuous monitoring and management measures for the old number should be sought.

• Journal of Korean Society of Forest Science
• /
• v.89 no.2
• /
• pp.232-240
• /
• 2000

Correlation between Songyi(Tricholoma matsutake, pine mushroom, matsutake) production and the annual pine tree growth in Korea was analyzed with 18 years data of the mushroom production in Sangju area and the annual ring-growth of pine trees at Mt Sogni in the area. The two parameters were not significantly related to each other(r=0.408). A possible reason of this low relationship is that September and October climate affected annual Songyi production through mushroom primordial formation, continued growth of the primordia, while May and June climate did the annual tree-ring growth. Songyi production at Mt. Wolak in Chungcheongbukdo peaked while the minimum daily air temperature ranged about $7^{\circ}C$ to $13^{\circ}C$ during the first week of October in 1999. These show that Songyi production variation is not a simple trend depending on the energy the pine trees have accumulated. Rather, controlling soil moisture and air temperature during Songyi fruiting season can be a significant management option for improving the mushroom production.

• Journal of Forest and Environmental Science
• /
• v.34 no.5
• /
• pp.395-404
• /
• 2018

Since the mass mortality of Quercus mongolica has been first reported in Gyeonggi province at 2004, the disease spread rapidly over Korean peninsula annually. Ambrosia beetle (Platypus koryoensis) was known as the insect vector of oak wilt fungus, Raffaelea quercus-mongolicae, and control methods of the disease had mainly been focused on eradication of insect vector. However, for the efficient management of the disease, combined control methods for both of the pathogenic fungus and insect vector are strongly required. As one of the efforts to suppress the pathogenic fungus, antifungal activities of Streptomyces isolated from oak forest soil were assayed in this study. Optimum culture condition for the selected isolates was also studied, As a result, Streptomyces blastmyceticus cultured in PDB (Potato Dextrose Broth) at $25^{\circ}C$ for 1 week showed the strongest antifungal activity against oak wilt fungus. Mycelial growth inhibition rates (MGIRs) of Streptomyces isolates were compared on culture media supplemented with heated and unheated culture filtrates of S. blastmyceticus. MGIRs on culture media with unheated culture filtrates were generally higher than those on culture media with heated culture filtrates. Antagonistic mechanism to get involved in the inhibition of hyphal growth and spore formation of the pathogen is due to the antifungal metabolites produced by Streptomyces. This study will provide the fundamental information in developing biocontrol agents for the environment-friendly management of oak wilt disease.

• Journal of Korean Society of Forest Science
• /
• v.83 no.3
• /
• pp.380-390
• /
• 1994

This study was conducted to investigate the effects of the topographical factors (16 items), physico-chemical properties of soil (13 items) and meteorological factors(9 items) on the height growth of Pinus thunbergii stands along the coastal area in Korea. According to the coefficients by partial correlation analysis in total area, it was found that tree height growth was considerably affected by local topography, soil hardness, soil B-horizental depth, effective soil depth, soil moisture, parent rock, soil texture, and etc.. And the soil factors were available $P_2O_5$, total nitrogen, base saturation, exchangeable $Ca^{{+}+}$, and etc.. In partial correlation analysis, annual relative humidity, annual precipitation, index of aridity, and etc. were found to be the most important factors influencing on tree height growth of Pinus thunbergii stands. In conlusion, the topographical, soil and meteorological factors have multiplex influence on the tree height growth in the Pinus thunbergii stands. They promise to provide the basis of improving not only the selection of suitable sites and the management of soil fertilizer but also the estimation of growth and yield. Hence these results would be used successfully for the design in the scientific forest working plan.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.4
• /
• pp.197-212
• /
• 2019

The purpose of this study is to identify the maturity stages of venture firms through classification analysis, which is widely used as a big data technique. Venture companies should develop a competitive advantage in the market. And the maturity stage of a company can be classified into five stages. I will analyze a difference in the growth stage of venture firms between the survey response and the statistical classification methods. The firm growth level distinguished five stages and was divided into the period of start-up and declines. A classification method of big data uses popularly k-mean cluster analysis, hierarchical cluster analysis, artificial neural network, and decision tree analysis. I used variables that asset increase, capital increase, sales increase, operating profit increase, R&D investment increase, operation period and retirement number. The research results, each big data analysis technique showed a large difference of samples sized in the group. In particular, the decision tree and neural networks' methods were classified as three groups rather than five groups. The groups size of all classification analysis was all different by the big data analysis methods. Furthermore, according to the variables' selection and the sample size may be dissimilar results. Also, each classed group showed a number of competitive differences. The research implication is that an analysts need to interpret statistics through management theory in order to interpret classification of big data results correctly. In addition, the choice of classification analysis should be determined by considering not only management theory but also practical experience. Finally, the growth of venture firms needs to be examined by time-series analysis and closely monitored by individual firms. And, future research will need to include significant variables of the company's maturity stages.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.2
• /
• pp.1-10
• /
• 2006

The objective of this study was to develop a GIS application model for analyzing site-specific suitability and investment efficiency of major plantation tree species. The model was designed to choose the best plantation species in terms of both potential stand growth and investment efficiency. Site index and IRR were used as the criteria for the potential of stand growth and investment efficiency, respectively. In the model, the conditions of forest stand management and site index are estimated as the function of site-environmental factors extracted by a series of spatial analyses of digital maps of FGIS. Based on site index values of tree species, the model screens out all the high potential tree species, in terms of stand growth, as the candidates for species selection and, then, calculates IRR for managing plantation forest stands for all the candidate tree species. The tree species of the highest IRR would be chosen as the one possessing the highest potential in terms of stand growth and profit. The model was applied to a case study for analyzing the site-specific suitability of 6 tree species in Taehwa University Forest of Seoul National University and the results are given in this paper.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.6
• /
• pp.17-25
• /
• 2018

This study was conducted to calculate the optimum height of trees, estimating a model for the prediction of tree growth for the landscape improvement of the Gyeonghoeru area. For the verification of measures for management, this study conducted a photographic survey of the Gyeonghoeru area and used the Pressler's formula to examine the growth rate of the pine forest of Mansesan. The results of the study are as follows. First, as a result of a field survey and landscape analysis, trees in the Gyeonghoeru area are large ones with more than a diameter at breast height of 30cm, except for weeping cherry trees and persimmon trees, and especially, it is necessary to manage them or replace with small trees through the landscape of Mansesan, which screens the landscape and pruning the trees in the terraced flower garden in the north. Second, as a result of a measurement of the growth rate of trees, for 10 years on average, they grew up by 14% in source diameter and 5% in tree height 5% in south of Mansesan and by 7% in source diameter and 2.4% in tree height in the north of Mansesan. Furthermore, when a simulation was prepared based on the measured growth rate of trees, it was found out that 20 years later, on the landscape on the second floor of Gyeonghoeru, the pine forest of Mansesan would cut off the skyline of Mt. Inwang-san. Third, this study analyzed a landscape improvement simulation and proposed a plan for tree management to take a view of the landscape of the Gyeonghoeru area. This study has a significance that it drew an efficient planting maintenance policy, considering the landscape characteristics of the Gyeonghoeru area.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.229-236
• /
• 2017

An efficient frequent pattern algorithm is essential for mining association rules as well as many other mining tasks for convergence with its application spread over a very broad spectrum. Models for mining pattern have been proposed using a FP-tree for storing compressed information about frequent patterns. In this paper, we propose a centroid frequent pattern growth algorithm which we called "CAWFP-Growth" that enhances he FP-Growth algorithm by making the center of weights and frequencies for the itemsets. Because the conventional constraint of maximum weighted support is not necessary to maintain the downward closure property, it is more likely to reduce the search time and the information loss of the frequent patterns. The experimental results show that the proposed algorithm achieves better performance than other algorithms without scarifying the accuracy and increasing the processing time via the centroid of the items. The MapReduce framework model is provided to handle large amounts of data via a pseudo-distributed computing environment. In addition, the modeling of the proposed algorithm is required in the fully distributed mode.