정보통신 기술의 발전으로 농업분야에서도 다량의 데이터로부터 가치 있는 정보를 생성하고 그 활용을 위해 빅데이터 기술을 적용하는 연구가 활발히 진행되고 있다. 농업에서 재배 가능한 작물과 품종은 기온, 강수량, 일조시간 등의 자연환경의 영향에 따라 결정된다. 본 논문은 마늘의 생육과정과 일별로 측정되는 기상변수를 활용하여 농작물 생산에 영향을 미치는 기상기후 요인을 도출하고 마늘을 대상으로 단위면적당 생산량 예측(단수) 모형을 도출하였다. 기상변수는 마늘의 생육단계를 고려하여 빅데이터 분석 기법을 이용하였다. 탐색적 자료 분석과정에서는 통계청, 농촌진흥청, 농촌경제연구원으로부터 생산량, 도매시장 반입량, 생육 데이터 등 다양한 농산물 생산 데이터를 제공받아 활용하였다. 또한 기상청으로부터 AWS, ASOS, 특보현황 등 다양한 기상관측 데이터를 수집하여 활용하였다. 상관관계 분석 과정은 변수선택, 후보모형 도출, 모형진단, 시나리오 예측 등을 통해 도출한 모형의 모형 적합도와 생산량 예측력을 비교하여 마늘생산단수예측 모형을 설계하였다. 수많은 기상요인 변수는 요인분석을 이용하여 차원을 감소시키고 설명변수로 선정하였다. 이 방법을 이용함으로써 회귀분석에서 발생할 수 있는 다중공선성과 낮은 자유도의 문제를 효과적으로 통제할 수 있었으며 회귀분석의 적합도와 예측력을 높일 수 있었다.
정보통신 기술의 발전으로 농업분야에서도 다량의 데이터로부터 가치 있는 정보를 생성하고 그 활용을 위해 빅데이터 기술을 적용하는 연구가 활발히 진행되고 있다. 농업에서 재배 가능한 작물과 품종은 기온, 강수량, 일조시간 등의 자연환경의 영향에 따라 결정된다. 본 논문은 마늘의 생육과정과 일별로 측정되는 기상변수를 활용하여 농작물 생산에 영향을 미치는 기상기후 요인을 도출하고 마늘을 대상으로 단위면적당 생산량 예측(단수) 모형을 도출하였다. 기상변수는 마늘의 생육단계를 고려하여 빅데이터 분석 기법을 이용하였다. 탐색적 자료 분석과정에서는 통계청, 농촌진흥청, 농촌경제연구원으로부터 생산량, 도매시장 반입량, 생육 데이터 등 다양한 농산물 생산 데이터를 제공받아 활용하였다. 또한 기상청으로부터 AWS, ASOS, 특보현황 등 다양한 기상관측 데이터를 수집하여 활용하였다. 상관관계 분석 과정은 변수선택, 후보모형 도출, 모형진단, 시나리오 예측 등을 통해 도출한 모형의 모형 적합도와 생산량 예측력을 비교하여 마늘생산단수예측 모형을 설계하였다. 수많은 기상요인 변수는 요인분석을 이용하여 차원을 감소시키고 설명변수로 선정하였다. 이 방법을 이용함으로써 회귀분석에서 발생할 수 있는 다중공선성과 낮은 자유도의 문제를 효과적으로 통제할 수 있었으며 회귀분석의 적합도와 예측력을 높일 수 있었다.
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 envi...
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 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.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
제안 방법
In addition, we shall explore the data types and characteristics to utilize the exploratory data analysis step to select the models to analyze. The models are then complemented to enhance its performance to derive the optimal model.
This paper analyzed only the meteorological factors that affect the production of garlic and developed the prediction model of garlic yields. In future research, climate variables such as temporary typhoons and hail should be used later.
This study consists of the steps to prepare data, create analysis sets, predict models through exploratory data analysis, and to visualize knowledge. Overview of these process is described in Fig.
이론/모형
Exploratory data analysis techniques were examined. Factor analysis and regression analysis were applied as main analysis methods. Chapter 3 analyzes and designs garlic yield prediction model.
In order to compare the performance of the 3candidate prediction models, the LOOCV (leave-one-out cross validation) method was employed. The LOOCV showed that the Model 3 has the lowest estimate of error rate with 7.
Second, the AWS ID and ASOS ID do not match, so the ASOS ID nearest to the AWS ID is used in order for matching using the distance weighted calculation method of Expression (2). The climate values observed in the Gun-unit of meteorological observation systems (ASOS) are converted into Do-unit ones.
Regression analysis is to determine the regression equation best represents the sample collected to estimate the parameters, and to analyze the causal relationship between structures. This method uses the Minimum Square Method to search for regression equations that create a minimum square root between the measured and calculated values using the regression equation.
Weather factors include average temperature, maximum temperature, minimum temperature, wind speed, precipitation, wind cooling index, daylight hours, and humidity. Using big data analytics, this study analyzes various weather factors that affect the garlic production and final prediction model for garlic production are proposed through model comparison method.
후속연구
In future research, climate variables such as temporary typhoons and hail should be used later. Further analysis should be made of pest and farmer technological changes in addition to climate changes. In future research, it is also necessary to verify the predicted results of the developed garlic yield prediction model using actual data.
참고문헌 (13)
Korea Institute for Industrial Economics & Trade, http://www.kiet.go.kr/servlet/isearch, 2014.
J. K. Koh, J. H. Kim, "Have local officials recognized the importance of adaptive policy," Journal of the Korean Urban Management Association, vol. 24, no. 3, pp. 51-72, 2011.
O. S. Kwon, H. K. Cho, E. B. Cho, K. S. Roh, "Climate Variables and Rice Productivity: A Semiparametric Analysis Using Panel Regional Date," Korean Journal of Agricultural Economics, vol. 54, no. 3, pp. 71-94, 2013.
L. You, M. W. Rosegrant, S. Wood, D. Sun, "Impact of growing season temperature on wheat productivity in china," Agricultural for Meteorology, vol. 149, pp. 1009-1014, 2009. DOI: https://doi.org/10.1016/j.agrformet.2008.12.004
S. H. Han, B. H. Lee, M. S. Park, J. h. Seoung, H. S. Yang, S. C. Shin, "A Study of building Crop Yield Forecasting Model Considering Meteorological elements," Korea Rural Economic Institute, p.152, 2011.
T. B. John, C. H. Yu, "Exploratory Data Analysis," Wiley, 2003.
Y. Kano, H. Akira, "Stepwise variable selection in factor analysis," Psychometrika, vol. 65, no. 1, pp. 7-22, 2000. DOI: https://doi.org/10.1007/BF02294182
T. A. Brown, "Confirmatory Factor Analysis for Applied Research", 2nd Edi. (Methodology in the Social Sciences), Jan 8, 2015.
R. L. Gorsuch, "Factor Analysis: Classic Edition", Psychology Press, Dec 24, 2014.
G. Ciaburro, "Regression Analysis with R: Design and develop statistical nodes to identify unique relationships within data at scale", Jan 31, 2018.
L. D. Schroeder and D. L. Sjoquist, "Understanding Regression Analysis: An Introductory Guide", Quantitative Applications in the Social Sciences, Nov 24, 2016.
D. E. Farrar and R. R Glauber, "Multicollinearity in Regression Analysis; the Problem Revisited", Aug 24, 2017.
Wikipedia contributors, "Focus On: Regression Analysis: Dependent and independent Variables, Multicollinearity, Simple linear Regression, Heteroscedasticity, Lasso (statistics), ... Estimation, Errors and Residuals, etc.", Feb 22, 2018.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.