• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.480-488
• /
• 2018

The development of information and communication technology has been carried out actively in the field of agriculture to generate valuable information from large amounts of data and apply big data technology to utilize it. Crops and their varieties are determined by the influence of the natural environment such as temperature, precipitation, and sunshine hours. This paper derives the climatic factors affecting the production of crops using the garlic growth process and daily meteorological variables. A prediction model was also developed for the production of garlic per unit area. A big data analysis technique considering the growth stage of garlic was used. In the exploratory data analysis process, various agricultural production data, such as the production volume, wholesale market load, and growth data were provided from the National Statistical Office, the Rural Development Administration, and Korea Rural Economic Institute. Various meteorological data, such as AWS, ASOS, and special status data, were collected and utilized from the Korea Meteorological Agency. The correlation analysis process was designed by comparing the prediction power of the models and fitness of models derived from the variable selection, candidate model derivation, model diagnosis, and scenario prediction. Numerous weather factor variables were selected as descriptive variables by factor analysis to reduce the dimensions. Using this method, it was possible to effectively control the multicollinearity and low degree of freedom that can occur in regression analysis and improve the fitness and predictive power of regression analysis.

• The Journal of the Korea Contents Association
• /
• v.15 no.12
• /
• pp.483-492
• /
• 2015

This study involved elementary schoolchildren in Busan Metropolitan city and assumed the foundation of social cooperative associations that provide education services for meteorological fields, then we analyzed expected profits in a year for successful operation of first year. Twelve variables relating to profits and expenses were derived, and we used the decision tree for analyzing optimal expected profits. Profit-related variables were lecture's fee per hour and price of textbooks. Expense-related variables were production costs for the textbooks, annual salary for a teacher, education costs for a teacher, developing costs for the textbooks, traveling expenses, rental fees, and operating costs. Besides, by adding education demands, the number of grades, and the number of teachers, we analyzed changes in expected profits, considering variability of profits and expenses. As a result, despite of expected lower demands, to increase price of textbooks and education costs per hour was of advantage to enhance expected profits. The reason is that the more demand, the more increased production costs for textbooks, which is because not to make enough profits to offset the increased expenses due to lowered price of textbooks and education costs. Considering the value of public interest for social cooperative associations, price determination only concerning increase in demands will be avoided.

• Journal of Environmental Health Sciences
• /
• v.45 no.5
• /
• pp.497-510
• /
• 2019

Objectives: The aim of this study was to secure the reliability of using the CalTOX model when evaluating LADD (or ADD) and Risk (or HQ) among local residents for the emission of BTEX (Benzene, Toluene, Ethylbenzene, Xylene) and by closely examining the difference in the confidence interval of the assessment outcomes according to the difference in the probability density function of input variables. Methods: The assessment was made by dividing it according to the method ($I^{\dagger}$) of inputting the probability density function in meteorological variables of the model with log-normal distribution and the method of inputting ($II^{\ddagger}$) after grasping the optimal probability density function using @Risk. A T-test was carried out in order to analyze the difference in confidence interval of the two assessment results. Results: It was evaluated to be 1.46E-03 mg/kg-d in LADD of Benzene, 1.96E-04 mg/kg-d in ADD of Toluene, 8.15E-05 mg/kg-d in ADD of Ethylbenzene, and 2.30E-04 mg/kg-d in ADD of Xylene. As for the predicted confidence interval in LADD and ADD, there was a significant difference between the $I^{\dagger}$ and $II^{\ddagger}$ methods in $LADD_{Inhalation}$ for Benzene, and in $ADD_{Inhalation}$ and ADD for Toluene and Xylene. It appeared to be 3.58E-05 for risk in Benzene, 3.78E-03 for HQ in Toluene, 1.48E-03 for HQ in Ethylbenzene, and 3.77E-03 for HQ in Xylene. As a result of the HQ in Toluene and Xylene, the difference in confidence interval between the $I^{\dagger}$ and $II^{\ddagger}$ methods was shown to be significant. Conclusions: The human risk assessment for BTEX was made by dividing it into the method ($I^{\dagger}$) of inputting the probability density function of meteorological variables for the CalTOX model with log-normal distribution, and the method of inputting ($II^{\ddagger}$) after grasping the optimal probability density function using @Risk. As a result, it was identified that Risk (or HQ) is the same, but that there is a significant difference in the confidence interval of Risk (or HQ) between the $I^{\dagger}$ and $II^{\ddagger}$ methods.

• Journal of Animal Science and Technology
• /
• v.65 no.5
• /
• pp.939-950
• /
• 2023

This study was conducted to assess the impact of growing condition variables on alfalfa (Medicago sativa L.) productivity. A total of 197 alfalfa yield results were acquired from the alfalfa field trials conducted by the South Korean National Agricultural Cooperative Federation or Rural Development Administration between 1983 and 2008. The corresponding climate and soil data were collected from the database of the Korean Meteorological Administration. Twenty-three growing condition variables were developed as explaining variables for alfalfa forage biomass production. Among them, twelve variables were chosen based on the significance of the partial-correlation coefficients or potential agricultural values. The selected partial correlation coefficients between the variables and alfalfa forage biomass ranged from -0.021 to 0.696. The influence of the selected twelve variables on yearly alfalfa production was summarized into three dominant factors through factor analysis. Along with the accumulated temperature variables, the loading scores of the daily mean temperature higher than 25℃ were over 0.88 in factor 1. The sunshine duration at temperature between 0℃-25℃ was 0.939 in factor 2. Precipitation days were 0.82, which was the greatest in factor 3. Stepwise regression applied with the three dominant factors resulted in the coefficients of factors 1, 2, and 3 for 0.633, 0.485, and 0.115, respectively, and the R-square of the model was 0.602. The environmental conditions limiting alfalfa growth, such as daily temperature higher than 25℃ or daily mean temperature affected annual alfalfa production most substantially among the growing condition variables. Therefore, future cultivar selection should consider the capability of alfalfa to be tolerant to extreme summer weather along with biomass production potential.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.798-800
• /
• 2003

The time shift processing of ground measured surface temperature with the meteorological variables has no evaluated function. We introduce new evaluating function. To use this evaluating function, the algorithm of time-shift processing will be able to be reliable and get error-bar for all moving measured point's data. We will finally obtain the area averaged surface temperature by land observation.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1881-1890
• /
• 2021

Particulate matter (PM) affects the human, ecosystems, and weather. Motorized vehicles and combustion generate fine particulate matter (PM_2.5), which can contain toxic substances and, therefore, requires systematic management. Consequently, it is important to monitor and predict PM_2.5 concentrations, especially in large cities with dense populations and infrastructures. This study aimed to predict PM_2.5 concentrations in large cities using meteorological and chemical variables as well as satellite-based aerosol optical depth. For PM_2.5 concentrations prediction, a random forest (RF) model showing excellent performance in PM concentrations prediction among machine learning models was selected. Based on the performance indicators R², RMSE, MAE, and MAPE with training accuracies of 0.97, 3.09, 2.18, and 13.31 and testing accuracies of 0.82, 6.03, 4.36, and 25.79 for R², RMSE, MAE, and MAPE, respectively. The variables used in this study showed high correlation to PM_2.5 concentrations. Therefore, we conclude that these variables can be used in a random forest model to generate reliable PM_2.5 concentrations predictions, which can then be used to assess the vulnerability of schools to PM_2.5.

• Journal of Bio-Environment Control
• /
• v.26 no.2
• /
• pp.87-99
• /
• 2017

Recently the increase in an abnormal climate events and meteorological disasters which causes a great damage to greenhouse facilities. To minimize and evaluate the expected damages it is necessary to prepare countermeasures and a management system in advance. For this purpose, a quantitative analysis of weather and abnormal climate are needed to investigate protected cultivation areas which are vulnerable to natural disasters. This study focused on protected cultivation areas in Jeolla province, South Korea. Surrogate variables were calculated to analyze the vulnerable areas to meteorological disasters, and spatial distribution analysis was also performed by using GIS to present vulnerable areas on map. The map thus created and was compared with actual data of damages by meteorological disasters which occurred in target areas. The result of the comparison is as follows: About 50% of the target areas showed an agreement between the map created in this study and the actual data, these areas includes Gwangju metropolitan city, Naju city, Yeongam County, Jangseong County, Hampyeong County, and Haenam County. On the other hand, other areas, including Gunsan city, Mokpo city, and Muan County, suffered low damage in spite of high levels of vulnerability to meteorological disasters. This result was considered to be affected by such variables as different structural designs and management systems of greenhouses by region. This study carried out an analysis of meteorological data to find out more detailed vulnerability to protected cultivation area and to create a map of vulnerable protected cultivation areas. In addition, the map was compared with the record of natural disasters to identify actual vulnerable areas. In conclusion, this study can be utilized as basic data for preventing and reducing damages by meteorological disasters in terms of design and management of greenhouses.

• Journal of Korean Society of Rural Planning
• /
• v.24 no.3
• /
• pp.25-31
• /
• 2018

This study analyzed factors influencing cultivation area of two major apple cultivars, Fuji and Hongro, applying the panel SUR model to survey data from farms. Characteristics of farms, distribution factors, and weather factors were the independent variables of the model. The analysis indicated that characteristics of farms, distribution factors, and weather factors influence the cultivation area of Hongro and Fuji. The independent variables were also found to have different levels of influence on increase and decrease of the cultivated area. Helping predict changes in cultivation area of Hongro and Fuji, the research results can be used as primary data to support efforts to prevent price fluctuations due to changes in supply.

• Journal of Information Technology Services
• /
• v.18 no.1
• /
• pp.173-186
• /
• 2019

Recently, as the amount of fine dust has risen rapidly, our interest is increasing day by day. It is virtually impossible to remove fine dust. However, it is best to predict the concentration of fine dust and minimize exposure to it. In this study, we developed a mathematical model that can predict the concentration of fine dust using various information related to the weather and air quality, which is provided in real time in 'Air Korea (http://www.airkorea.or.kr/)' and 'Weather Data Open Portal (https://data.kma.go.kr/).' In the mathematical model, various domestic seasonal variables and atmospheric state variables are extracted by multiple regression analysis. The parameters that have significant influence on the fine dust concentration are extracted, and using ANN (Artificial Neural Network) and SVM (Support Vector Machine), which are machine learning techniques, we proposed a prediction model. The proposed model can verify its effectiveness by using past dust and weather big data.

• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.319-331
• /
• 2022

In this paper, we develop a new statistical model to forecast the PM_2.5 level in Seoul, South Korea. The proposed model is based on the extreme quantile regression model with lasso penalty. Various meteorological variables and air pollution variables are considered as predictors in the regression model, and the lasso quantile regression performs variable selection and solves the multicollinearity problem. The final prediction model is obtained by combining various extreme lasso quantile regression estimators and we construct a binary classifier based on the model. Prediction performance is evaluated through the statistical measures of the performance of a binary classification test. We observe that the proposed method works better compared to the other classification methods, and predicts 'very bad' cases of the PM_2.5 level well.