http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
‘부지화’의 SPAD 데이터로부터 질소함량을 추정하는 머신러닝 모델
박원표 ( Won Pyo Park ),허성 ( Seong Heo ) 강원대학교 농업생명과학연구원 2022 강원 농업생명환경연구 Vol.34 No.1
‘부지화’ 잎의 SPAD측정값을 기반으로 잎의 질소함량을 추정하고자 여러 머신러닝 모델을 적용해 보았다. 모델 평가지표 및 실측치·예측치 데이터 산포도를 종합적으로 고려할 때, GB가 가장 적합한 모델로 선정되었다. 결정계수가 가장 1에 가까우며, MSE, RMSE, MAE도 모두 0에 수렴하여 실측치와 예측치의 오차가 가장 적었음을 알 수 있었다. In recent years, to investigate the nitrogen content in plant leaves, the use of non-destructive and simple methods is preferred to that of destructive, time-consuming, and expensive methods. In this study, several machine learning models (linear and polynomial regressions, stochastic gradient descent, artificial neural network, support vector machine, k-nearest neighbors, random forest, and gradient boosting) were applied to estimate the nitrogen content in leaves based on the linear relationship between the SPAD reading value and the nitrogen content in leaves of Shiranuhi (Citrus unshiu × C. sinensis). As the data of nitrogen content measured under the laboratory condition was insufficient, the data was increased using the bootstrapping method. Considering the model evaluation metrics, the gradient boosting model was selected as the most accurate model. The coefficient of determination of this model was the closest to 1 and the MSE, RMSE, and MAE all converged to 0, indicating that the error between the measured and predicted values was the smallest.
박원표,강호준 한국토양비료학회 2019 한국토양비료학회지 Vol.52 No.1
The objective of this study is to determine the effects of physical properties of soils on soil erosion under arainfall simulator. The soil samples were collected from five sites of dark brown soil (DBS), six sites of verydark brown volcanic ash soil (VDBAS), and eight sites of black volcanic ash soil (BVAS) in Jeju Island. Therainfall simulator, which ran for 30 minutes at a slope gradient of 10%, determined the amounts of soilerosion, infiltrated water, and runoff water. The particle size distribution, water-stable aggregates distribution,bulk density, organic matter content, and saturated hydraulic conductivity in soils were analyzed as well. Theamounts of soil erosion gradually increased and reached a steady state after 20 minutes. The amounts of soilerosion in BVAS were higher than that in other soils. It also correlated positively with the amounts of runoffwater and related negatively to the amounts of infiltrated water. The amounts of soil erosion in DBS andBVAS had a significant negative correlation with some particle size fractions and saturated hydraulicconductivity (p < 0.05). A significant positive correlation was observed between the amounts of soil erosionand the water-stable aggregates with the size smaller than 1 mm in DBS and VDVAS (p < 0.05). The bulkdensity and organic matter content did not significantly affect the amount of soil erosion. These resultsconcluded that the physical properties of soils affecting the amount of soil erosion varied among the color ofsoils in Jeju Island. It is suggested that the values of soil erodibility factor for the volcanic ash soils of JejuIsland need to be estimated with an alternative algorithm to predict the amount of soil erosion.
부지화 잎의 화학성분에 기반한 질소결핍 여부 구분 머신러닝 모델 개발
박원표(Won Pyo Park),허성(Seong Heo) 한국자원식물학회 2022 한국자원식물학회지 Vol.35 No.2
Nitrogen is the most essential macronutrient for the growth of fruit trees and is important factor determining the fruit yield. In order to produce high-quality fruits, it is necessary to supply the appropriate nitrogen fertilizer at the right time. For this, it is a prerequisite to accurately diagnose the nitrogen status of fruit trees. The fastest and most accurate way to determine the nitrogen deficiency of fruit trees is to measure the nitrogen concentration in leaves. However, it is not easy for citrus growers to measure nitrogen concentration through leaf analysis. In this study, several machine learning models were developed to classify the nitrogen deficiency based on the concentration measurement of mineral nutrients in the leaves of tangor Shiranuhi (Citrus unshiu × C. sinensis). The data analyzed from the leaves were increased to about 1,000 training dataset through the bootstrapping method and used to train the models. As a result of testing each model, gradient boosting model showed the best classification performance with an accuracy of 0.971.
박원표,장공만,구본준,현해남 한국토양비료학회 2017 한국토양비료학회지 Vol.50 No.6
Copper(II) acetate spectrophotometry method (CASM) was used for the rapid and convenient determinationof cation exchange capacity (CEC) in soils. This method is composed of a single-step exchange reaction thatadsorbs copper and is measured through spectrophotometry. The CEC of 16 Korean soils were measuredusing 1M ammonium acetate method (AAM) and the CASM. The CEC values determined by CASM andAAM were not significantly different, and were highly correlated (r = 0.966**). Due to the convenience, costeffectiveness, and time saving analysis of CASM, this method is recommended for most soil laboratories tomeasure CEC in Korean soils. However, CASM may not be applicable for soils that have a much higher CEC(greater than 20 cmolc kg-1).
박원표,신연미,최진상 경상대학교 농업생명과학연구원 2015 농업생명과학연구 Vol.49 No.4
압착 추출방법에 의한 동백, 들깨, 비자, 피마자 및 참깨 종자유의 이화학적 특성을 분석한 결과는 다음과 같다. 각종 종자유의 물리적 특성으로 비중은 0.913~0.965, 점도는 37.08~719.60cP, 명도는 30.62~32.26, 적색도는 –0.06~0.67, 황색도는 1.56~5.57 범위였다. 화학적 특성 중 산가는 비자유가 13.60±0.08mg/g으로 많은 함량이었다. 과산화물가는 들기름이 상대적으로 높은 53.03±0.56meq/kg로 측정되었다. TBA가는 피마자 종자유가 24.88±0.45mg/kg로 가장 낮았고, 참기름이 119.23±0.94mg/kg으로 가장 높은 값을 나타내었다. 요오드가는 들기름이 207.09±0.11g으로 피마자유 보다 3배나 많은 양이었다. 검화가는 181.29~236.38g의 범위로서 비슷한 결과를 확인하였다. 지방산은 포화지방산 9종과 불포화지방산 14종을 포함하여 총 23종이 검출되었다. 지방산 총량에 대한 포화지방산의 비율은 9.37~19.94%였으며, 피마자유는 약 20%로서 가장 높은 비율이었다. 그 중 palmitic acid와 stearic acid가 다른 포화지방산에 비해 많았다. 종자유의 불포화지방산은 oleic acid와 linoleic acid가 약 72~87% 함량을 나타내었는데, 들기름은 예외적으로 ω-3 지방산에 해당하는 linolenic acid 53.44%와 oleic acid 22.38%의 구성을 나타내었다. Camellia seed, perilla seed, nutmeg nut seed, caster seed and sesame seed oil extracted by pressure method and those were investigated of some physicochemical properties. The result is as follows. Physical properties of all sorts of seed oil were that the range of gravity was 0.913~0.965, of viscosity was 37.08~719.60cP and of lightness was 30.62~32.26. Acid value in chemical properties was much in nutmeg nut oil as 13.60±0.08mg/g. Peroxide value’s was high in perilla seed oil as 53.06±0.56meq/kg, about 10times more than others. In castor seed oil showed the lowest TBA value as 24.88±0.45mg/kg but in sesame oil, it was highest as 119.23±0.94mg/kg. Iodine value in perilla seed oil was as 207.09±0.11g, about 3 times more than castor seed oil. But in saponification value showed little difference range as 181.29~236.83g. Some seeds oil were composed totally 23 varieties of fatty acids such as saturated fatty acids of 9 varieties and unsaturated fatty acids of 14 varieties. Saturated fatty acids ratio were 9.37~19.94% in each oils but castor seed oil’s content was the highest ratio than others as about 20%. Especially, palmitic acid and stearic acid were more than other content in saturated fatty acids. Unsaturated fatty acids composed as oleic acid and linoleic acid about 72~87% in all oils, but an exception case was perilla seed oil as 53.44% of linolenic acid(C18:3, ω-3) and 22.38% of oleic acid.