[논문]다중회귀모형과 인공신경망모형을 이용한 금강권역 강수량 장기예측

김철겸; 이정우; 이정은; 김현준

doi:10.3741/jkwra.2022.55.10.723

다중회귀모형과 인공신경망모형을 이용한 금강권역 강수량 장기예측
Application of multiple linear regression and artificial neural network models to forecast long-term precipitation in the Geum River basin 원문보기

Journal of Korea Water Resources Association = 한국수자원학회논문집, v.55 no.10, 2022년, pp.723 - 736

김철겸 (한국건설기술연구원 수자원하천연구본부) , 이정우 (한국건설기술연구원 수자원하천연구본부) , 이정은 (한국건설기술연구원 수자원하천연구본부) , 김현준 (한국건설기술연구원 수자원하천연구본부)

초록
AI-Helper

본 연구에서는 금강권역을 대상으로 최대 12개월까지 선행예측이 가능한 월 강수량 예측모형을 구축하였으며, 예측모형 구축에는 다중회귀분석과 인공신경망의 두 가지 통계적 기법을 적용하였다. 예측인자 후보로 NOAA에서 제공하는 글로벌 기후패턴 39종과 금강권역에 대한 기상인자 8종 등 총 47종의 기후지수를 활용하였다. 예측대상월을 기준으로 과거 40년간의 월 강수량과 기후지수와의 지연상관성 분석을 통해 상관도가 높은 기후지수를 예측인자로 활용하여 다중회귀모형 및 인공신경망 모형을 구축하였다. 1991~2021년에 대해 매월 예측결과의 평균값과 관측값과의 적합도를 분석한 결과, 다중회귀모형은 PBIAS -3.3~-0.1%, NSE 0.45~0.50, r 0.69~0.70으로 분석되었으며, 인공신경망모형은 PBIAS -5.0~+0.5%, NSE 0.35~0.47, r 0.64~0.70로, 다중회귀모형에 의해 도출된 예측치의 평균값이 인공신경망모형보다 관측치에 좀 더 근접한 것으로 나타났다. 각 월의 예측범위 안에 관측치가 포함될 확률을 분석한 결과에서는 다중회귀모형이 57.5~83.6%(평균 72.9%), 인공신경망모형의 경우에는 71.5~88.7%(평균 81.1%)로 인공신경망모형 결과가 우수한 것으로 나타났다. 3분위 예측확률을 비교한 결과는 다중회귀모형의 경우에는 25.9~41.9%(평균 34.6%), 인공신경망모형은 30.3~39.1%(평균 34.7%)로 비슷하며, 두 모형 모두 평균 33.3% 이상으로 월 강수량에 대한 장기예측성을 확인 할 수 있었다. 이상과 같이 두 모형의 예측성 차이는 비교적 크지 않은 것으로 나타났으나, 예측범위에 대한 적중률이나 3분위 예측확률로부터 판단할 때 예측성에 대한 월별 편차는 인공신경망모형의 결과가 상대적으로 작게 나타났다.

Abstract ▼ AI-Helper

In this study, monthly precipitation forecasting models that can predict up to 12 months in advance were constructed for the Geum River basin, and two statistical techniques, multiple linear regression (MLR) and artificial neural network (ANN), were applied to the model construction. As predictor candidates, a total of 47 climate indices were used, including 39 global climate patterns provided by the National Oceanic and Atmospheric Administration (NOAA) and 8 meteorological factors for the basin. Forecast models were constructed by using climate indices with high correlation by analyzing the teleconnection between the monthly precipitation and each climate index for the past 40 years based on the forecast month. In the goodness-of-fit test results for the average value of forecasts of each month for 1991 to 2021, the MLR models showed -3.3 to -0.1% for the percent bias (PBIAS), 0.45 to 0.50 for the Nash-Sutcliffe efficiency (NSE), and 0.69 to 0.70 for the Pearson correlation coefficient (r), whereas, the ANN models showed PBIAS -5.0~+0.5%, NSE 0.35~0.47, and r 0.64~0.70. The mean values predicted by the MLR models were found to be closer to the observation than the ANN models. The probability of including observations within the forecast range for each month was 57.5 to 83.6% (average 72.9%) for the MLR models, and 71.5 to 88.7% (average 81.1%) for the ANN models, indicating that the ANN models showed better results. The tercile probability by month was 25.9 to 41.9% (average 34.6%) for the MLR models, and 30.3 to 39.1% (average 34.7%) for the ANN models. Both models showed long-term predictability of monthly precipitation with an average of 33.3% or more in tercile probability. In conclusion, the difference in predictability between the two models was found to be relatively small. However, when judging from the hit rate for the prediction range or the tercile probability, the monthly deviation for predictability was found to be relatively small for the ANN models.

주제어

표/그림 (17)

그림 Fig. 1. Study area
표 Table 1. ASOS stations used in this study
표 Table 2. Predictors used in this study (Kim et al., 2021b)
그림 Fig. 2. Results of the correlation analysis with climate indices for forecasting monthly precipitation
그림 Fig. 3. Structure of an artificial neural network model
그림 Fig. 4. Correlations of the climate indices used for monthly precipitation forecasting in 2020
그림 Fig. 5. Climate indices highly correlated with monthly precipitation for each season
그림 Fig. 6. Monthly precipitation forecasts for January to December 2020 by MLR models
그림 Fig. 7. Monthly precipitation forecasts for January to December 2020 by ANN models
그림 Fig. 8. Monthly precipitation forecasts for January to December 2021 by MLR models
그림 Fig. 9. Monthly precipitation forecasts for January to December 2021 by ANN models
그림 Fig. 10. Monthly precipitation forecasts from 1991 to 2021 by MLR models
그림 Fig. 11. Monthly precipitation forecasts from 1991 to 2021 by ANN models
그림 Fig. 12. Result of the goodness-of-fit test for monthly precipitation forecasts by MLR models
그림 Fig. 13. Result of the goodness-of-fit test for monthly precipitation forecasts by ANN models
그림 Fig. 14. Hit rate for the forecast range of precipitation
그림 Fig. 15. Hit rate for the tercile probability of precipitation forecasts

참고문헌 (26)

Ahn, J.-B., and Kim, H.-J. (2005). "Correlation between large-scale circulation patterns and temperature and precipitation over Busan." Asia-Pacific Journal of Atmospheric Science, Vol. 41, No. 6, pp. 1101-1110.
Ahn, S.-K., Choi, W., Shin, H., and Heo, J.-H. (2015). "Correlation analysis between climate indices and Korean precipitation and temperature using empirical model decomposition: II. Correlation analysis." Journal of Korea Water Resources Association, Vol. 49, No. 3, pp. 207-215.
Cho, J., Jung, I.W., Kim, C.G., and Kim, T.G. (2016). "One-month lead dam inflow forecast using climate indices based on teleconnection." Journal of Korea Water Resources Association, Vol. 49, No. 5, pp. 361-372.
Choi, J.-W., Park, K.-J., Lee, K., Kim, J.-Y., and Kim, B.-J. (2015). "Features of Korean rainfall variability by Western Pacific teleconnection pattern." Journal of Environmental Science International, Vol. 24, No. 7, pp. 893-905.
Choi, K.-S., Kang, S.-D., and Kim, H.-D. (2013a). "Spatiotemporal variability of April rainfall in Korea by western Pacific teleconnection pattern." International Journal of Climatology, Vol. 33, pp. 1168-1177.

상세보기
Choi, K.S., Kim, B.J., and Lee, J.H. (2013b). "Relationship between rainfall in Korea and Antarctic Oscillation in June." Journal of Korean Earth Science Society, Vol. 34, No. 2, pp. 136-147.
Choi, K.-S., Shrestha, R., Kim, B.-J., Lu, R., Kim, J.-Y., Park, K.-J., Jung, J.-H., and Nam, J.-C. (2014). "A study of teleconnection between the South Asian and East Asian monsoons: Comparison of summer monsoon precipitation of Nepal and South Korea." Journal of Environmental Science International, Vol. 23, No. 10, pp. 1719-1729.

원문보기 상세보기
Daejeon Regional Office of Meteorology (DROM) (2021). 2020 Daejeon/Sejong/Chungnam weather and climate report.
Evans, J.D. (1996). Straightforward statistics for the Behavioral sciences. Thomson Brooks/Cole Publishing Co., CA, U.S.
Ham, Y.-G., Chikamoto, Y., Kug, J.-S., Kimoto, M., and Mochizuki, T. (2017). "Tropical Atlantic-Korea teleconnection pattern during boreal summer season." Climate Dynamics, Vol. 49, pp. 2649-2664.

상세보기
Jo, S., and Ahn, J.-B. (2017). "Statistical forecast of early spring precipitation over South Korea using multiple linear regression." Journal of Climate Research, Vol. 12, No. 1, pp. 53-71.

상세보기
Kim, C.-G., Lee, J., Lee, J.E., and Kim, H. (2021a). "Long-term forecasting reference evapotranspiration using statistically predicted temperature information." Journal of Korea Water Resources Association, Vol. 54, No. 12, pp. 1243-1254.
Kim, C.-G., Lee, J., Lee, J.E., Kim, N.W., and Kim, H. (2020). "Monthly precipitation forecasting in the Han River basin, South Korea, using large-scale teleconnections and multiple regression models." Water, Vol. 12, No. 6, 1590. doi: 10.3390/w12061590.

상세보기
Kim, C.-G., Lee, J., Lee, J.E., Kim, N.W., and Kim, H. (2021b). "Monthly temperature forecasting using large-scale climate teleconnections and multiple regression models." Journal of Korea Water Resources Association, Vol. 54, No. 9, pp. 731-745.
Kim, J.-S., Seo, G.-S., Jang, H.-W., and Lee, J.-H. (2017). "Correlation analysis between Korean spring drought and large-scale teleconnection patterns for drought forecasting." KSCE Journal of Civil Engineering, Vol. 21, No. 1, pp. 458-466.

상세보기
Kim, J.Y., and Park, H.J. (2010). "Impacts of Northern-hemisphere teleconnection patterns on precipitation in Korea." Water for Future, KWRA, Vol. 43, No. 7, pp. 57-61.
Kim, M.-K., Kim, Y.-H., and Lee, W.-S. (2007). "Seasonal prediction of Korean regional climate from preceding large-scale climate indices." International Journal of Climatology, Vol. 27, pp. 925-934.

상세보기
Kim, S., Park, C.-K., and Kim, M.-K. (2005). "The regime shift of the northern Hemispheric circulation responsible for the spring drought in Korea." Asia-Pacific Journal of Atmospheric Science, Vol. 41, No. 4, pp. 571-585.
Kim, Y.-H., Kim, M.-K., and Lee, W.-S. (2008). "An investigation of large-scale climate indices with the influence on temperature and precipitation variation in Korea." Korean Meteorological Society, Atmosphere, Vol. 18, No. 2, pp. 83-95.
Lee, J., Kim, C.-G., Lee, J.E., Kim, N.W., and Kim, H. (2020). "Medium-term rainfall forecasts using artificial neural networks with monte-carlo cross-validation and aggregation for the Han River basin, Korea." Water, Vol. 12, No. 6, 1743. doi:10.3390/w12061743.

상세보기
Lee, K.-J., and Kwon, M. (2015). "A prediction of Northeast Asian summer precipitation using teleconnection." Korean Meteorological Association, Atmosphere, Vol. 25, No. 1, pp. 179-183.
Lee, S., and Choi, Y. (2013). "Study on the relationship between Arctic oscillation and temperature, precipitation and extreme climate events during spring over the Republic of Korea." The Geographical Journal of Korea, Vol. 47, No. 4, pp. 453-464.
Lee, S.-J., and Chang, Y.-S. (2021). "Correlation analysis between the variation of net surface heat flux around the East Asian seas and the air temperature and precipitation over the Korean Peninsula." Ocean and Polar Research, Vol. 43, No. 1, pp. 15-30.
Li, J., and Zeng, Q. (2002). "A unified monsoon index." Geophysical Research Letters, Vol. 29, No. 8, pp. 115-1-115-4.
Moriasi, D.N., Arnold, J.G., Liew, M.W., Bingner, R.L., Harmel, R.D., and Veith, T.L. (2007). "Model evaluation guidelines for systematic quantification of accuracy in watershed simulations." Transactions of the ASABE, Vol. 50, No. 3, pp. 885-900.

상세보기
Park, M.-G., Kang, S.-U., Lee, J.-J., Lee, H.-H., and Kim, H.-J. (2018). "Seasonal precipitation forecast using big data." Water for Future, KWRA, Vol. 51, No. 11, pp. 6-12.

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증