• Title/Summary/Keyword: Korea forest service

Search Result 742, Processing Time 0.027 seconds

A Study for Estimation of High Resolution Temperature Using Satellite Imagery and Machine Learning Models during Heat Waves (위성영상과 머신러닝 모델을 이용한 폭염기간 고해상도 기온 추정 연구)

  • Lee, Dalgeun;Lee, Mi Hee;Kim, Boeun;Yu, Jeonghum;Oh, Yeongju;Park, Jinyi
    • Korean Journal of Remote Sensing
    • /
    • v.36 no.5_4
    • /
    • pp.1179-1194
    • /
    • 2020
  • This study investigates the feasibility of three algorithms, K-Nearest Neighbors (K-NN), Random Forest (RF) and Neural Network (NN), for estimating the air temperature of an unobserved area where the weather station is not installed. The satellite image were obtained from Landsat-8 and MODIS Aqua/Terra acquired in 2019, and the meteorological ground weather data were from AWS/ASOS data of Korea Meteorological Administration and Korea Forest Service. In addition, in order to improve the estimation accuracy, a digital surface model, solar radiation, aspect and slope were used. The accuracy assessment of machine learning methods was performed by calculating the statistics of R2 (determination coefficient) and Root Mean Square Error (RMSE) through 10-fold cross-validation and the estimated values were compared for each target area. As a result, the neural network algorithm showed the most stable result among the three algorithms with R2 = 0.805 and RMSE = 0.508. The neural network algorithm was applied to each data set on Landsat imagery scene. It was possible to generate an mean air temperature map from June to September 2019 and confirmed that detailed air temperature information could be estimated. The result is expected to be utilized for national disaster safety management such as heat wave response policies and heat island mitigation research.

A Study of Big data-based Machine Learning Techniques for Wheel and Bearing Fault Diagnosis (차륜 및 차축베어링 고장진단을 위한 빅데이터 기반 머신러닝 기법 연구)

  • Jung, Hoon;Park, Moonsung
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.19 no.1
    • /
    • pp.75-84
    • /
    • 2018
  • Increasing the operation rate of components and stabilizing the operation through timely management of the core parts are crucial for improving the efficiency of the railroad maintenance industry. The demand for diagnosis technology to assess the condition of rolling stock components, which employs history management and automated big data analysis, has increased to satisfy both aspects of increasing reliability and reducing the maintenance cost of the core components to cope with the trend of rapid maintenance. This study developed a big data platform-based system to manage the rolling stock component condition to acquire, process, and analyze the big data generated at onboard and wayside devices of railroad cars in real time. The system can monitor the conditions of the railroad car component and system resources in real time. The study also proposed a machine learning technique that enabled the distributed and parallel processing of the acquired big data and automatic component fault diagnosis. The test, which used the virtual instance generation system of the Amazon Web Service, proved that the algorithm applying the distributed and parallel technology decreased the runtime and confirmed the fault diagnosis model utilizing the random forest machine learning for predicting the condition of the bearing and wheel parts with 83% accuracy.

The Regional Folk Plants in Inland of Gyeongsangbuk-do (I) (경상북도 내륙지역의 민속식물 I)

  • Chung, Gyu-Young;Park, Myung-Soon;Nam, Bo-Mi;Hong, Ki-Nam;Jang, Jin;Lee, Cheul-Ho
    • Korean Journal of Plant Resources
    • /
    • v.23 no.5
    • /
    • pp.465-479
    • /
    • 2010
  • This study was carried out to classify the regional folk plants in the inland of Gyeongsangbuk-do. According to the survey results from 582 survey sheets of 126 residents at 85 places of 17 counties and cities from March to October, 2009, the folk plants in the inland of Gyeongsangbuk-do consisted of a total 254 taxa; 76 families, 207 genera, 225 species, 2 subspecies, 26 varieties, and 1 form. The use by its usage was: 216 taxa; edible, 82 taxa; medicinal, 30 taxa; dye, 3 taxa; aroma, 4 taxa; spice, 4 taxa; ornamental, 1 taxa; fiber, 2 taxa; oil, 1 taxa; starch, 5 taxa; fuel, 9 taxa; others, respectively, so the edible use is the highest. The most useful part was the leaf, followed by stem and root. The folk plants of 3 head families from Yeongyang and Cheongsong were 42 taxa. The consistency comparison between the scientific name and the local name were the highest in the 50's and the lowest in 80's.

Floristic Study of Daeheuksando in Korea (대흑산도의 관속식물상)

  • Jang, Chang-Seok;Yang, Sun-Gyu;Jang, Hyun-Do;Lee, Ro-Young;Park, Min-Su;Kim, Ki-Hong;Oh, Byoung-Un
    • Korean Journal of Plant Resources
    • /
    • v.27 no.5
    • /
    • pp.518-533
    • /
    • 2014
  • The flora in the region of Daeheuksando ($N34^{\circ}37^{\prime}{\sim}34^{\circ}42^{\prime}$, $E125^{\circ}23^{\prime}{\sim}125^{\circ}38^{\prime}$) was surveyed from June 2010 to October 2011. The vascular plants from 22 field surveys were revealed to total of 496 taxa: 113 families, 316 genera, 446 species, four subspecies, 43 varieties and three forms. 124 taxa were the first records from this region. This field study discovered significant plants in various categories. Korean endemic plants numbered 7 taxa, and 6 taxa designated by Korean Forest Service as rare plants were investigated in this region. The taxa in the category II of rare and endangered plants and higher than the third degree among the floristic regional indicator plants designated by Korean Ministry of Environment were one taxon and 47 taxa, respectively. Especially, it was proved that Spiraea chartacea, Hosta yingeri, Hemerocallis hongdoensis and Saussurea polylepis were endemic to Heuksan-myeon including Daeheuksando in Korean peninsular. In addition, the naturalized plants of 46 taxa were recorded.

Patterns of Snake Roadkills on the Roads in the National Parks of South Korea (국립공원 내 도로에서 뱀류 로드킬 현황)

  • Kim, Seok-Bum;Lee, Jung-Hyun;Park, Daesik
    • Korean Journal of Ecology and Environment
    • /
    • v.51 no.3
    • /
    • pp.234-244
    • /
    • 2018
  • The roadkill that animals die after bumping by vehicles on the roads is acting as a factor to decrease the size of various animal populations. It has also been known to be the biggest artificial causations of Vertebrata deaths not only in urban areas but also protected areas such as national parks. Nevertheless, in the national park areas which are major protected national areas for conservation of national biodiversity and ecological diversity, snake roadkills occur frequently. Up to date, related studies are rare. Therefore, in this study, we described snake roadkill patterns on the roads in six national parks between 2006 and 2015. We identified total 736 snake roadkills compromising 10 different species. Five species, Rhabdophis lateralis, Elaphe dione, Gloydius ussuriensis, Lycodon rufozonatus, Gloydius brevicaudus occupied more than 91.7% of total roadkill cases. Active forager snakes were killed by roadkills more than ambush foragers, and the snake roadkill frequency was the highest in September, a migration period and in August when the young individuals dispersed at between 100 and 799 m altitude areas. Roads where roadkills were frequent lie between forest and hydrosphere or between forest and crop field road sides. Our results could be used to identify the trend of snake roadkills on the roads in national parks, and to establish effective roadkill mitigation measures and policies.

A Flora of Vascular Plants in Mt. Cheongnyangsan (Bonghwa-gun, Andong-si) (청량산(봉화군, 안동시)의 관속식물상)

  • Nam, Bo Mi;Kim, Jae Young;Jeong, Seon;Lee, Jae-Hyeon;Nam, Myoung Ja;Oh, Byoung-Un;Chung, Gyu Young
    • Korean Journal of Plant Resources
    • /
    • v.28 no.5
    • /
    • pp.616-634
    • /
    • 2015
  • This study was carried out to elucidate the distribution of vascular plants and their usefulness of Mt. Cheongnyangsan (870 m) in Gyeongsangbuk-do. The vascular plants that were collected 16 times 2006 and 2014 consisted a total of 614 taxa; 97 families, 330 genera, 541 species, 3 subspecies, 61 varieties and 9 forms. For the Korean endemic plants, 21 taxa were recorded and 8 taxa of Vulnerable Species (VU) and 5 taxa of Least Concerned species (LC) categorized by the Korean Forest Service as rare plants were investigated in this region. Furthermore, Ⅴ, Ⅳ, Ⅲ degrees of floristic regional indicator plants designated by the Korean Ministry of Environment included 2 taxa, 10 taxa and 18 taxa, respectively. Moreover, four species of distributional interesting plants, Aconitum austro-koreense Koidz., Allium spirale Willd., Dipsacus japonicus Miq. and Pinellia tripartita (Blume) Schott, in Mt. Cheongnyangsan were discovered by this study. Among them, edible, pasturing, medicinal, ornamental, timber, dye, fiber and unknown usefulness plants included 234 taxa, 213 taxa, 174 taxa, 62 taxa, 16 taxa, 12 taxa, 11 taxa and 167 taxa, respectively. In addition, 32 taxa of naturalized plants were observed.

A Study on the Prediction of Mortality Rate after Lung Cancer Diagnosis for Men and Women in 80s, 90s, and 100s Based on Deep Learning (딥러닝 기반 80대·90대·100대 남녀 대상 폐암 진단 후 사망률 예측에 관한 연구)

  • Kyung-Keun Byun;Doeg-Gyu Lee;Se-Young Lee
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.16 no.2
    • /
    • pp.87-96
    • /
    • 2023
  • Recently, research on predicting the treatment results of diseases using deep learning technology is also active in the medical community. However, small patient data and specific deep learning algorithms were selected and utilized, and research was conducted to show meaningful results under specific conditions. In this study, in order to generalize the research results, patients were further expanded and subdivided to derive the results of a study predicting mortality after lung cancer diagnosis for men and women in their 80s, 90s, and 100s. Using AutoML, which provides large-scale medical information and various deep learning algorithms from the Health Insurance Review and Assessment Service, five algorithms such as Decision Tree, Random Forest, Gradient Boosting, XGBoost, and Logistic Registration were created to predict mortality rates for 84 months after lung cancer diagnosis. As a result of the study, men in their 80s and 90s had a higher mortality prediction rate than women, and women in their 100s had a higher mortality prediction rate than men. And the factor that has the greatest influence on the mortality rate was analyzed as the treatment period.

Floristic Study of Tamjin River Estuary in Gangjin-gun, Korea (탐진강 하구역 일대(강진군)의 관속식물상)

  • Jang, Hyun-Do;Leem, Hyosun;Han, Seahee;Oh, Ami;Oh, Byoung-Un;Yang, Sungyu
    • Journal of Environmental Science International
    • /
    • v.29 no.6
    • /
    • pp.579-603
    • /
    • 2020
  • In order to provide fundamental information about the floristic composition of the area along with an assessment of the environmental impact, a floristic study of the vascular plants in the Tamjin River estuary in Gangjin-gun was conducted for a total of nine days, in the period from June 2014 to September 2014. We found that the vascular plants in this region comprised 424 taxa belong to 102 families, 281 genera, 390 species, 5 subspecies, 26 varieties, and 3 forma. Five taxa of Korean endemic plants including Weigela subsessilis (Nakai) L.H.Bailey, Lespedeza maximowiczii var. tricolor (Nakai) Nakai, and Clematis trichotoma Nakai were collected. Two least concern (LC) taxa of rare plants (as designated by the Korea Forest Service) were collected: Hydrocharis dubia (Blume) Backer and Platycladus orientalis (L.) Franco. Ten the floristic regional indicator taxa from the third to the fifth grade were identified: two taxa belonged to grade IV, and eight taxa belonged to grade III. Twenty-four taxa of salt-tolerant plants, including Artemisia fukudo Makino, Carex rugulosa Kuk., and Suaeda glauca (Bunge) Bunge, as well as 44 taxa of aquatic plants, including Najas marina L., Nuphar oguraensis Miki, and Nymphoides indica (L.) Kuntze, were investigated in this region. Fifty-nine taxa of naturalized plants were recorded, among which the following six taxa were plants that caused ecosystem disturbance: Ambrosia artemisiifolia L., Humulus scandens (Lour.) Merr., Lactuca scariola L., Rumex acetosella L., Solidago altissima L., and Symphyotrichum pilosum (Willd.) G.L.Nesom.

Effects of altering medium strength and sucrose concentration on in vitro germination and seedling growth of Cypripedium macranthos Sw.

  • Huh, Yoon Sun;Lee, Joung Kwan;Nam, Sang Young;Hong, Eui Yon;Paek, Kee Yoeup;Son, Sung Won
    • Journal of Plant Biotechnology
    • /
    • v.43 no.1
    • /
    • pp.132-137
    • /
    • 2016
  • The genus Cypripedium, known as lady's slipper orchid, has been considered to have a considerable marketability as a potted and garden plant with beautiful flowers; however, this species is becoming endangered and, in some places extinct, due to habitat destruction and illegal collections. As such, an optimized artificial propagation system is necessary for its conservation and horticultural cultivation. For the establishment of the in vitro proliferation of the endangered Cypripedium macranthos Sw., native to Korea, the effects of medium strength and sucrose concentrations on germination, protocorm formation and seedling growth were investigated through asymbiotic seed culture. The highest germination rate and protocorm formation rate were obtained with a 1/4 MS medium; higher MS medium strengths did not generate the favorable conditions required for germination and protocorm growth. The overall growth characteristics of roots and buds developed from protocorms were best in cultures of 1/4 MS medium. On this medium containing $10g{\cdot}L^{-1}$ sucrose, both the germination rate and protocorm formation rate increased significantly. The general growth properties of seedlings developed on the medium with $10g{\cdot}L^{-1}$ sucrose were best, showing the highest bud formation rate and root number. Our results demonstrate that the 1/4 MS medium, supplemented with $10g{\cdot}L^{-1}$ sucrose, could improve in vitro germination, and facilitate the growth of seedlings developed from the protocorms of C. macranthos Sw.

An Example of Changed Design through the Face Mapping and Slope Analysis (절토사면 현황도 작성 및 분석에 따른 설계변경 사례연구)

  • Lee, Byung-Joo;Chae, Byung-Gon;Lee, Kyoung-Mi
    • The Journal of Engineering Geology
    • /
    • v.24 no.1
    • /
    • pp.137-146
    • /
    • 2014
  • The geology of the study area which is located in Samkoe-dong, Dong-gu, Daejeon city comprises black slate, limestone, and pebble-bearing phyllitic rock as meta-sedimentary rocks; and biotite granite and quartz porphyry intrusions. Face mapping revealed sliding in three or four sites of contained coaly slate, where the dip of the foliation and other discontinuities is parallel to the surface slope. The cause of the slope sliding is this parallelism as well as the swelling of the coaly slate when wet. In contrast, the slop on the opposite side of the road is relatively stable because the dip of the foliation and other discontinuities are oblique or normal to the surface slope. To ensure slope stability, a cut-and-cover tunnel was designed and constructed for the new road.