DOI QR코드

DOI QR Code

Development of Naïve-Bayes classification and multiple linear regression model to predict agricultural reservoir storage rate based on weather forecast data

기상예보자료 기반의 농업용저수지 저수율 전망을 위한 나이브 베이즈 분류 및 다중선형 회귀모형 개발

  • Kim, Jin Uk (Department of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Jung, Chung Gil (Department of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Lee, Ji Wan (Department of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Kim, Seong Joon (Department of Civil, Environmental and Plant Engineering, Konkuk University)
  • 김진욱 (건국대학교 공과대학 사회환경플랜트공학과) ;
  • 정충길 (건국대학교 공과대학 사회환경플랜트공학과) ;
  • 이지완 (건국대학교 공과대학 사회환경플랜트공학과) ;
  • 김성준 (건국대학교 공과대학 사회환경플랜트공학과)
  • Received : 2018.07.25
  • Accepted : 2018.08.09
  • Published : 2018.10.31

Abstract

The purpose of this study is to predict monthly agricultural reservoir storage by developing weather data-based Multiple Linear Regression Model (MLRM) with precipitation, maximum temperature, minimum temperature, average temperature, and average wind speed. Using Naïve-Bayes classification, total 1,559 nationwide reservoirs were classified into 30 clusters based on geomorphological specification (effective storage volume, irrigation area, watershed area, latitude, longitude and frequency of drought). For each cluster, the monthly MLRM was derived using 13 years (2002~2014) meteorological data by KMA (Korea Meteorological Administration) and reservoir storage rate data by KRC (Korea Rural Community). The MLRM for reservoir storage rate showed the determination coefficient ($R^2$) of 0.76, Nash-Sutcliffe efficiency (NSE) of 0.73, and root mean square error (RMSE) of 8.33% respectively. The MLRM was evaluated for 2 years (2015~2016) using 3 months weather forecast data of GloSea5 (GS5) by KMA. The Reservoir Drought Index (RDI) that was represented by present and normal year reservoir storage rate showed that the ROC (Receiver Operating Characteristics) average hit rate was 0.80 using observed data and 0.73 using GS5 data in the MLRM. Using the results of this study, future reservoir storage rates can be predicted and used as decision-making data on stable future agricultural water supply.

본 연구의 목적은 기상자료(강수량, 최고기온, 최저기온, 평균기온, 평균풍속) 기반의 다중선형 회귀모형을 개발하여 농업용저수지 저수율을 예측하는 것이다. 나이브 베이즈 분류를 활용하여 전국 1,559개의 저수지를 지리형태학적 제원(유효저수량, 수혜면적, 유역면적, 위도, 경도 및 한발빈도)을 기준으로 30개 군집으로 분류하였다. 각 군집별로, 기상청 기상자료와 한국농어촌공사 저수지 저수율의 13년(2002~2014) 자료를 활용하여 월별 회귀모형을 유도하였다. 저수율의 회귀모형은 결정계수($R^2$)가 0.76, Nash-Sutcliffe efficiency (NSE)가 0.73, 평균제곱근오차가 8.33%로 나타났다. 회귀모형은 2년(2015~2016) 기간의 기상청 3개월 기상전망자료인 GloSea5 (GS5)를 사용하여 평가되었다. 현재저수율과 평년저수율에 의해 산정되는 저수지 가뭄지수(Reservoir Drought Index, RDI)에 의한 ROC (Receiver Operating Characteristics) 분석의 적중률은 관측값을 이용한 회귀식에서 0.80과 GS5를 이용한 회귀식에서 0.73으로 나타났다. 본 연구의 결과를 이용해 미래 저수율을 전망하여 안정적인 미래 농업용수 공급에 대한 의사결정 자료로 사용할 수 있을 것이다.

Keywords

References

  1. Ahn, S. R., Park, M. J., Park, G. A., and Kim S. J. (2007). "The effect of meteorological factors on the temporal variation of agricultural reservoir storage." Journal of the Korean Society of Agricultural Engineers, Vol. 49, No. 4, pp. 3-12. https://doi.org/10.5389/KSAE.2007.49.4.003
  2. Bae, D. H., Ahn, J. B., Kim, H. K., Kim, H. A., Son, K. H., Cho, S. R., and Jung, U. S. (2013). "Development & evaluation of real-time ensemble drought prediction system." Korean Meteorological Society-Atmosphere, Vol. 23, No. 1, pp. 113-121.
  3. Choi, S. Y., Han, K. Y., and Kim, B. Y. (2012). "Comparison of different multiple linear regression models for real-time flood stage forecasting." Journal of the Korean Society of Civil Engineers B, Vol. 32, No. 1B, pp. 9-20.
  4. Han, E. H., and Cha, H. T. (2017). "Iterative Naive-Bayes classifier design method for effective emotion classification." The Institute of Electronics and Information Engineers, Vol. 54, No. 12, pp. 119-126. https://doi.org/10.5573/ieie.2017.54.12.119
  5. Hong, J. H., and Cho, S. B. (2008). "Rank-based multiclass gene selection for cancer classification with Naive-Bayes classifiers based on gene expression profiles." Korea Information Science Society, Vol. 35, No. 7 ․ 8, pp. 372-377.
  6. Kang, J. W. (2013). "Forecasting of seasonal inflow to reservoir using multiple linear regression." Journal of Environmental Science International, Vol. 22, No. 8, pp. 953-963. https://doi.org/10.5322/JESI.2013.22.8.953
  7. Kim, D. R., and Kim, S. J. (2017). "A study on parameter estimation for SWAT calibration considering streamflow of long-term drought periods." Journal of the Korean Society of Agricultural Engineers, Vol. 59, No. 2, pp. 19-27. https://doi.org/10.5389/KSAE.2017.59.2.019
  8. Kim, J. K., and Lee, J. S. (2011). "Virtual machine provisioning scheduling with conditional probability inference for trnasport information service in cloud environment." Journal of the Korea Society for Simulation, Vol. 20, No. 4, pp. 139-147. https://doi.org/10.9709/JKSS.2011.20.4.139
  9. Kim, K. P., and Kwon, Y. S. (2005). "Performance comparison of Naive-Bayesian learning and centroid-based classification for e-mail classification." IE Interfaces, Vol. 18, No. 1, pp. 10-21.
  10. Kim, S. M., and Kim, S. M. (2013). "Evaluation of applicability and hydrologic parameter calibration for HSPF model using expert system for HSPF." Journal of the Korean Society of Agricultural Engineers, Vol. 55, No. 4, pp. 13-20. https://doi.org/10.5389/KSAE.2013.55.4.013
  11. Kim, S. R., Jang, M. W., Kim, S. J., and Bae, S. J. (2017). "Spatial and temporal analysis of drought using the storage data of agricultural reservoirs in Chungnam province in 2015." Journal of the Korean Society of Agricultural Engineers, Vol. 59, No. 2, pp. 29-36. https://doi.org/10.5389/KSAE.2017.59.2.029
  12. Kim, S. U., and Lee, K. S. (2008). "Regional low flow frequency analysis using bayesian multiple regression."Journal of Korea Water Resources Association, Vol. 41, No. 3, pp. 325-340. https://doi.org/10.3741/JKWRA.2008.41.3.325
  13. Korea Meteorological Administration (KMA) (2012). Construction of the abnormal climate probability forecast system using the joint seasonal forecast system between KMA and Met Office.
  14. Korea Rural Community Corporation (KRC). Rural Infrastructure Management System (RIMS). http://rims.ekr.or.kr.
  15. Korean Rural Community and Agriculture Corporation (KRC) (2017). Statistical yearbook of land and water development for agriculture. Ministry for food, Agriculture, Forestry and Fisheries, Republic of South Korea (in Korean).
  16. Lee, C. B., Jung, N. S., Park, S. K., and Jeon, S. O. (2015). "A study on the typology of agricultural reservoir for effective safety inspection systems." Journal of the Korean Society of Agricultural Engineers, Vol. 57, No. 5, pp. 89-99. https://doi.org/10.5389/KSAE.2015.57.5.089
  17. Lee, J. T., Yun, S. H., and Park. M. E. (1995). "Relationships between seasonal duration of sunshine and air temperature in Korea." Korean Journal of Environmental Agriculture, Vol. 14, No. 2, pp. 155-162.
  18. Lee, K. S., Yoon, K. S., Kim, H. J., and Kim, H. I. (2003). "A program of water quality management for agricultural reservoirs by trophic state." Korean Journal of Environmental Agriculture, Vol. 22, No. 2, pp. 166-171. https://doi.org/10.5338/KJEA.2003.22.2.166
  19. Li, C., Scaife, A. A., Lu, R., Arribas, A., Brookshaw, A., Comer, R. E., Li, J., MacLachlan, C., and Wu, P. (2016). "Skillful seasonal prediction of Yangtze river valley summer rainfall." Environmental Research Letters, No.11, 094002
  20. Park, D. I., and Yoon, S. H. (2017). "Clustering and classification to characterize daily electricity demand." Journal of the Korean Data & Information Science Society, Vol. 28, No. 2, pp. 395-406. https://doi.org/10.7465/jkdi.2017.28.2.395
  21. Park, J. C. (2015). "Development of a BROOK90-R hydrological model for water balance estimation of a irrigation reservoir." Journal of the Korean Geomorphological Association, Vol. 22, No. 2, pp. 101-105.
  22. Park, U. Y. (2012). "Comparison of Naive-Bayesian classifier and self organizing maps model for selecting the retaining wall methods." Journal of the Architectural Institute of Korea Structure & Construction, Vol. 28, No. 12, pp. 111-118. https://doi.org/10.5659/JAIK_SC.2012.28.12.111
  23. Rim, C. S. (2017). "Estimation of small pan evaporation using temperature data," Journal of Korea Water Resources Association, Vol. 50, No. 1, pp. 37-53. https://doi.org/10.3741/JKWRA.2017.50.1.37
  24. Shin, E. C., and Lee, J. K. (2012). "Safety management improving way of small agricultural reservoir." Journal of Korean Geosynthetics Society, Vol. 12, No. 3, pp. 53-58.
  25. So, J. M., Oh, T. S., and Bae, D. H. (2017). "Estimation and assessment of long-term drought outlook information using the long-term forecasting data." Journal of Korea Water Resources Association, Vol. 50, No. 10, pp. 691-701. https://doi.org/10.3741/JKWRA.2017.50.10.691
  26. Son, K. H., Bae, D. H., and Cheong, H. S. (2015). "Construction & evaluation of GloSea5-Based hydrological drought outlook system." Korean Meteorological Society-Atmosphere, Vol. 25, No. 2, pp. 271-281.
  27. Song, J. H., Cho, Y. H., Kim, I. S., and Yi, J. H. (2017). "Development of decision support system for water resources management using GloSea5 long-term rainfall forecasts and K-DRUM rainfall-runoff model." Journal of Satellite, Information and Communications, Vol. 12, No. 3, pp. 22-34.
  28. Song, J. H., Kang, M. S., Song, I., Hwang, S. H., Park, J., and Ahn, J. H. (2013). "Surface drainage simulation model for irrigation districts composed of paddy and protected cultivation." Journal of the Korean Society of Agricultural Engineers, Vol. 55, No. 3, pp. 63-73. https://doi.org/10.5389/KSAE.2013.55.3.063
  29. Thornton, P. E., and Running, S. W. (1999). "An improved algorithm for estimating incident daily solar radiation from measurement of temperature." Humidity, and Precipitation, Agricultural and Forest Meteorology, Vol. 93, pp. 211-218. https://doi.org/10.1016/S0168-1923(98)00126-9
  30. Yi, J. E., and Choi, S. G. (2007). "Optimal multi-reservoir system operation using fuzzy DP (II) - Application for multipurpose dam." Journal of the Korean Society of Civil Engineers, Vol. 27, No. 1B, pp. 71-77.
  31. Yim, J. Y., and Hwang, B. Y. (2014). "Predicting movie success based on machine learning using twitter." KIPS Tr. Software and Data Engineering, Vol. 3, No. 7, pp. 263-270. https://doi.org/10.3745/KTSDE.2014.3.7.263
  32. Yoo, C. S., and Park, H. K. (2007). "Analysis of morphological characteristics of farm dams in Korea." Journal of Korean Geographical Society, Vol. 42, No. 6, pp. 940-954.
  33. Yoo, S. H., Choi, J. Y., Nam, W. H., Kim, T. G., and Go. G. D. (2012). "Developing model of drought climate scenarios for agricultural drought mitigation." Journal of the Korean Society of Agricultural Engineers, Vol. 54, No. 2, pp. 67-75. https://doi.org/10.5389/KSAE.2012.54.2.067
  34. Yun, H. S., Um, M. J., Cho, W. C., and Heo, J. H. (2009). "Orographic precipitation analysis with regional frequency analysis and multiple linear regression." Journal of Korea Water Resources Association, Vol. 42, No. 6, pp. 465-480. https://doi.org/10.3741/JKWRA.2009.42.6.465