• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.353-353
• /
• 2022

본 연구에서는 CMIP5(The fifth phase of the Couple Model Intercomparison Project) 미래기후시나리오와 LSTM(Long Short-Term Memory) 모형 기반의 딥러닝 기법을 이용하여 하천유량 예측을 위한 최적 학습 기간을 제시하였다. 연구지역으로는 진안군(성산리) 지점을 선정하였다. 보정(2000~2002/2014~2015) 및 검증(2003~2005/2016~2017) 기간을 설정하여 연구지역의 실측 유량 자료와 LSTM 기반 모의유량을 비교한 결과, 전체적으로 모의값이 실측값을 잘 반영하는 것으로 나타났다. 또한, LSTM 모형의 장기간 예측 성능을 평가하기 위하여 LSTM 모형 기반 유량을 보정(2000~2015) 및 검증(2016~2019) 기간의 SWAT 기반 유량에 비교하였다. 비록 모의결과에일부 오차가 발생하였으나, LSTM 모형이 장기간의 하천유량을 잘 산정하는 것으로 나타났다. 검증 결과를 기반으로 2011년~2100년의 CMIP5 미래기후시나리오 기상자료를 이용하여 SWAT 기반 유량을 모의하였으며, 모의한 하천유량을 LSTM 모형의 학습자료로 사용하였다. 다양한 학습 시나리오을 적용하여 LSTM 및 SWAT 모형 기반의 하천유량을 모의하였으며, 최적 학습 기간을 제시하기 위하여 학습 시나리오별 LSTM/SWAT 기반 하천유량의 상관성 및 불확실성을 비교하였다. 비교 결과 학습 기간이 최소 30년 이상일때, 실측유량과 비교하여 LSTM 모형 기반 하천유량의 불확실성이 낮은 것으로 나타났다. 따라서 CMIP5 미래기후시나리오와 딥러닝 기반 LSTM 모형을 연계하여 미래 장기간의 일별 유량을 모의할 경우, 신뢰성 있는 LSTM 모형 기반 하천유량을 모의하기 위해서는 최소 30년 이상의 학습 기간이 필요할 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.114-114
• /
• 2021

본 연구에서는 Sentinel-1 SAR 센서 기반 이미지자료와 딥러닝기법을 이용하여 고해상도 토양수분을 산정하였다. 입력자료는 지표특성(모래함량, 점토함량, 경사도), 인공위성 기반의 강우와 LANDSAT 기반의 이미지자료(NDVI, LST, 공간분포 토양수분)를 사용하였다. 강우자료의 경우 GPM(Global Precipitation Measurement) 일강우 자료를 사용하였으며, 관측일 기준으로 5일전까지의 강우자료와 5일평균강우를 구분하여 사용하였다. LANDSAT 기반의 토양수분 이미지자료와 지점관측 토양수분을 이용하여 검·보정 이후 딥러닝 모형의 입력자료로 사용하였다. 입력자료는 30m × 30m 해상도로 Resample 하여 딥러닝 모형의 학습을 진행하였으며, 학습에 사용된 모형을 이용하여 Sentinel-1 기반의 고해상도(10m × 10m) 토양수분이미지를 산정하였다. 검증지점은 거창군 거창읍, 계룡시 두마면, 장수군 장수읍 및 무주군 무주읍 토양수분 관측지점을 선정하였다. 거창군 거창읍의 산정결과, LANDSAT 기반의 토양수분 이미지와 DNN 기반의 토양수분 이미지가 매우 유사하게 나타났으며, 모의값(DNN 기반 토양수분)이 실측값(LANDSAT 기반의 토양수분)을 잘 반영한 것(R: 0.875 ; RMSE: 0.013)으로 나타났다. 또한 학습모형을 토지피복이 유사한 지역에 적용하여 토양수분을 산정한 결과 검증지점 계룡시(R: 0.897 ; RMSE: 0.014), 장수군(R: 0.770 ; RMSE: 0.024) 및 무주군(R: 0.909 ; RMSE: 0.012)의 모의값이 실측값과 매우 유사한 것으로 나타났다. 이를 바탕으로 Seninel-1 SAR센서 이미지자료와 딥러닝기법을 연계한 고해상도 토양수분자료가 농업, 수문, 환경 등 다양한 분야에서 활용될 수 있을 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.274-274
• /
• 2021

토양수분은 가뭄, 홍수, 산불 및 산사태 등 자연재해 발생에 직간접적으로 영향을 미치기 때문에, 시·공간적으로 연속적인 토양수분 관측이 필요하다. 과거에는 TDR (Time Domain Reflectometry) 관측 장비를 설치하여 토양수분의 변화를 관측하였으나, 이러한 지점관측의 경우 하나의 관측지점에서 토양수분을 관측하기 때문에 공간적인 토양수분 변화를 나타내지 못한다. 최근 이러한 문제를 해결하기 위하여 인공위성 이미지 자료를 이용한 토양수분 산정에 관한 연구가 활발히 수행되고 있다. 그러나 SMOS (Soil Moisture and Ocean Salinity), SMAP (Soil Moisture Active Passive)와 같은 다양한 위성에서 관측된 토양수분은 낮은 공간해상도로 인한 불확실성이 커지는 단점이 있다. 최근 이러한 한계를 극복하기 위하여 광학위성영상과 달리 날씨의 영향을 받지 않으며 고해상도 이미지자료를 제공하는 Sentinel-1A/B 위성을 활용하여 토양수분을 관측하는 연구가 진행되고 있다. Sentinel-1은 10m의 높은 공간해상도를 제공하지만, 1~2주 주기로 영상취득이 가능하기 때문에 재방문시기와 같은 시간해상도 문제가 발생한다. 따라서 본 연구에서는 Sentinel-1A/B SAR 기반 후방산란계수와 농촌진흥청에서 제공하는 TDR 기반 토양수분 실측값을 이용하여 우리나라 토양수분 공간분포를 산정하였다. 산정된 Sentinel-1A/B 기반 토양수분과 토양수분자료동화기법을 연계하여 토양의 수리학적 매개변수를 추출하였으며, 추출된 매개변수와 기상자료를 이용하여 장기간(2001~2018) 일별 토양수분 공간분포를 산정하였다.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.25 no.4
• /
• pp.39-43
• /
• 2024

Little research has been done on investigating the specific characteristics of Jeju Ponies (Korean native horse) and Jeju Pony crossbreds. The authors performed evaluation of skin thickness of the skin of these breeds (n=205) at Jeju Race Park as a way of find of hippological difference. Results of this study showed that the Jeju Pony's skin were thicker than the Jeju Pony crossbred. The male's skin were thicker than the female's skin in two breeds respectively. Especially, in the Jeju Pony show significant differences (P < 0.05). In Jeju Pony crossbreds, as the skin thickness were thinner with age increase. 2-year-old group's skin significantly thinner than 3 and over 4-year-old groups. However, the Jeju Pony's skin were not significantly different by age. In conclusion, the authors thought that causes of the difference of the breeds were origin and genetic differences among the horse and the pony. Furthermore, the modified umbilical herniorrhaphy with rubber rings must be used cautiously in the Jeju Pony. It should be taken into account the animals' skin thickness when the leather goods created by using their skin.

• Journal of The Korean Association For Science Education
• /
• v.20 no.3
• /
• pp.396-410
• /
• 2000

In this study, the concept presentation form, the content coherence of sub-dimensional concepts and the number of concepts of the 6th and the 7th Korean curriculum were analyzed comparing the guide to developing the secondary biology curricula to develop biological literacy with BSCS. According to the result, the discrimination between concept levels in the frame of contents of the Korean curricula is insufficient, because each of concepts presented in the knowledge domain as upper level and sub-dimensional concept elements as lower level are simply arrayed. Considering too much concepts of ecosystem, genetics, reproduction and metabolism, there should be an effort to reform the biological curriculum to include concepts evenly, not in the biased state, to reflect all the 6 unifying principles by BSCS for developing students' biological literacy. Finally there should be an effort to reflect the characteristics of each subjects concretely among Science 10, Biology I and Biology IT in the 7th curriculum considering the result that essential concepts to develop biological literacy are presented more in some principles of Biology II than Biology I. Thinking the results of the present study, concrete discussions should be made to set up the standard reference about biological literacy and to present essential concepts for teaching and learning to develop it in the process of biology textbook development for meeting the 7th Korean curriculum and in the development of 8th Korean curriculum in advance.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.39 no.2
• /
• pp.105-113
• /
• 2019

A two-year study was conducted from 2017 to 2018 by the establishment of a test field at Chungju-si and Cheongyang-gun. Plant height, number of leaves, insects and diseases, and fresh and dry matter yields for corn hybrid('Kwangpyeongok') were investigated. Daily average, maximum, and minimum temperature, monthly average temperature, daily precipitation, and sunshine duration during the growing season were investigated. We selected climate-critical factors to corn productivity and conducted an evaluation of vulnerability to climate change from 1999 to 2018 for both regions. In 2018, the dry matter yield of forage corn was 6,475 and 7,511 kg/ha in Chungju and Cheongyang, respectively, which was half of that in 2017. The high temperature and drought phenomenon in the 2018 summer caused the corn yield to be low. As well as temperature, precipitation is an important climatic factor in corn production. As a result of climate impact vulnerability assessment, the vulnerability has increased recently compared to the past. It is anticipated that if the high temperature phenomenon and drought caused by climate change continues, a damage in corn production will occur.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.4
• /
• pp.1038-1047
• /
• 2018

This study confirmed possibility of cosmetic material for Espresso coffee grounds extracted at high temperature, high pressure, short time and Dutch coffee grounds extracted at low temperature, atmospheric pressure, long time. For this purpose, we evaluated the biological activities of antioxidant, anti-wrinkles and antimicrobial effects using ethanol extracts of Esproso and Dutch coffee grounds. The results of total polyphenolic compound contents was $90.39{\pm}0.04mg/g$ for Dutch coffee grounds extract, which was higher than $64.96{\pm}0.38mg/g$ for Espresso coffee grounds extract, based on $113.63{\pm}0.22mg/g$ for coffee beans extract as the reference one. DPPH radical scavenging activity and SOD-like activity of Dutch coffee grounds extract were found to be better than those of Espresso coffee grounds extracts, referenced on coffee bean extract. As a result of inhibition effect of Elastase activity, Dutch coffee grounds extract showed higher inhibition effect than Espresso coffee grounds extract, based on coffee bean extract. In addition, Dutch coffee grounds extract showed good anti-microbial effects at Escherichia coli, Bacillus, Propionibacterium acnes and there was little difference in the clear zone size between Dutch coffee grounds extract and coffee bean extract as a reference one. From the results of the experiments, it was confirmed that Dutch coffee grounds extract had excellent antioxidant, anti-wrinkle and antimicrobial effects and could be used as safe natural cosmetic material in the future.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.1
• /
• pp.15-33
• /
• 2021

In this study, the possibility of discriminating Fire blight (FB) infection tested using the hyperspectral imagery. The reflectance of healthy and infected leaves and branches was acquired with 5 nm of full width at high maximum (FWHM) and then it was standardized to 10 nm, 25 nm, 50 nm, and 80 nm of FWHM. The standardized samples were divided into training and test sets at ratios of 7:3, 5:5 and 3:7 to find the optimal bands of FWHM by the decision tree analysis. Classification accuracy was evaluated using overall accuracy (OA) and kappa coefficient (KC). The hyperspectral reflectance of infected leaves and branches was significantly lower than those of healthy green, red-edge (RE) and near infrared (NIR) regions. The bands selected for the first node were generally 750 and 800 nm; these were used to identify the infection of leaves and branches, respectively. The accuracy of the classifier was higher in the 7:3 ratio. Four bands with 50 nm of FWHM (450, 650, 750, and 950 nm) might be reasonable because the difference in the recalculated accuracy between 8 bands with 10 nm of FWHM (440, 580, 640, 660, 680, 710, 730, and 740 nm) and 4 bands was only 1.8% for OA and 4.1% for KC, respectively. Finally, adding two bands (550 nm and 800 nm with 25 nm of FWHM) in four bands with 50 nm of FWHM have been proposed to improve the usability of multispectral image sensors with performing various roles in agriculture as well as detecting FB with other combinations of spectral bands.

• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.

• Korean Journal of Breeding Science
• /
• v.40 no.3
• /
• pp.269-277
• /
• 2008

Amino acid composition in grain of Korean native rice core collections was evaluated to identify the useful genotypes for quality enhancing rice breeding and value-added food development. Large variations were found in the contents of 16 amino acids among 388 genotypes tested with 14.9% of the minimum coefficient of variation (CV), and the contents of methionine and histidine showed the highest CV and the second high, respectively. The average values of total amino acid, total essential amino acid, lysine and threonine contents of Korean native rice collections were almost similar with those of cultivating japonica rice, Saechucheong. Among 388 native core collections Baekkokna, Daesona and Saducho were identified as high amino acid germplasm in total amino acid, total essential amino acid, lysine and threonine contents. And Seoksanjo and Sodujo were identified as low amino acid collections. Rice collections showing purple apiculus color tended to distribute in lower serine, proline, glutamic acid, glycine, alanine, valine, leucine, phenylalanine, arginine, and total amino acid contents compared with those of yellowish apiculus color collections. The glutinous rice collections showed the tendency of higher contents of serine, glutamic acid, alanine, valine and leucine compared with those of non-glutinous collections.