한국수자원학회논문집 (Journal of Korea Water Resources Association)

  • 제51권11호
  • /
  • Pages.1021-1029
  • /
  • 2018
  • /
  • 2799-8746(pISSN)
  • /
  • 2799-8754(eISSN)
한국수자원학회 (Korea Water Resources Association)
권호 표지
DOI QR코드

DOI QR Code

가뭄 분석을 위한 지하수위 모니터링 및 예측기법 개발(II) - 표준강수지수, 표준지하수지수 및 인공신경망을 이용한 지하수 가뭄 예측

Development of groundwater level monitoring and forecasting technique for drought analysis (II) - Groundwater drought forecasting Using SPI, SGI and ANN

  • 이정주 (한국수자원공사 물정보종합센터) ;
  • 강신욱 (K-water융합연구원) ;
  • 김태호 (한국수자원공사 물정보종합센터) ;
  • 전근일 (한국수자원공사 물정보종합센터)
  • Lee, Jeongju (Water Data Collection and Analysis Department, K-water) ;
  • Kang, Shinuk (K-water Convergence Institute) ;
  • Kim, Taeho (Water Data Collection and Analysis Department, K-water) ;
  • Chun, Gunil (Water Data Collection and Analysis Department, K-water)
  • 투고 : 2018.07.04
  • 심사 : 2018.09.14
  • 발행 : 2018.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 미급수지역의 주요 수원인 지하수의 수위 변동 상황을 기반으로 한 미급수지역 가뭄 예보 기법 개발을 목적으로 하였다. 이를 위해 지역화된 표준지하수지수(SGI)와 표준강수지수들(SPIs)의 상관관계를 분석하였다. 관측 지하수위로부터 산정된 SGI의 자기회귀 특성 및 지속기간별 SPI와 SGI의 상관관계를 동시에 고려할 수 있는 NARX (nonlinear autoregressive exogenous model) 인공신경망 모형을 이용하여 지역별 예측모형을 구축하였다. 학습기간 동안 관측 SGI와 모델 출력 SGI의 상관계수는 0.7 이상인 곳이 전체 167개 지역별 모형 중 146개(87%)로 상관성이 높은 것으로 분석되었다. 적용기간에 대해서는 평균제곱근오차와 상관계수로 모형을 평가하였다. 본 연구를 통해 기상청에서 제공하는 59개 관측소별 강수량 전망 값으로부터 산정된 지속기간별 SPI와 관측된 지하수위를 이용한 지역별 SGI 전망이 가능하도록 하였으며, 미급수지역의 가뭄 예 경보를 위한 기초자료로 활용이 가능토록 하였다.

A primary objective of this study is to develop a drought forecasting technique based on groundwater which can be exploit for water supply under drought stress. For this purpose, we explored the lagged relationships between regionalized SGI (standardized groundwater level index) and SPI (standardized precipitation index) in view of the drought propagation. A regional prediction model was constructed using a NARX (nonlinear autoregressive exogenous) artificial neural network model which can effectively capture nonlinear relationships with the lagged independent variable. During the training phase, model performance in terms of correlation coefficient was found to be satisfactory with the correlation coefficient over 0.7. Moreover, the model performance was described by root mean squared error (RMSE). It can be concluded that the proposed approach is able to provide a reliable SGI forecasts along with rainfall forecasts provided by the Korea Meteorological Administration.

키워드

참고문헌

  1. Changnon, S. A., Huff, F. A., and Hsu, C. F. (1988). "Relations between precipitation and shallow groundwater in Illinois." Journal of Climate, Vol. 1, No. 12, pp. 1239-1250. https://doi.org/10.1175/1520-0442(1988)001<1239:RBPASG>2.0.CO;2
  2. Changnon, S. A., Jr. (1987). Detecting drought conditions in Illinois, Illinois State Water Survey, Champaign, Circular 169.
  3. Diaconescu, E. (2008). "The use of NARX neural networks to predict chaotic time series." WSEAS Transactions on Computer Research, Vol. 3, Issue 3, pp. 182-191. ISSN: 1991-8755.
  4. Hagan, M. T., Demuth, H. B., Beale, M. H., and Jesus, O. (2014). Neural network design (2nd edition), Oklahoma State University, Stillwater, Oklahoma, U.S.A. ISBN: 0971732116.
  5. Jan, C. D., Chen, T. H., and Lo, W. C. (2007). "Effect of rainfall intensity and distribution on groundwater level fluctuations." Journal of Hydrology, Vol. 332, Issues 3-4, pp. 348-360. https://doi.org/10.1016/j.jhydrol.2006.07.010
  6. Kim, G. B., Yun, H. H., and Kim, D. H. (2006). "Relationship between standardized precipitation index and groundwater levels: A proposal for establishment of drought index wells." Journal of KoSSGE, Vol. 11, No. 3, pp. 31-42.
  7. Kim, Y. (2014). "Time series prediction of dynamic response of a free-standing riser using quadratic Volterra Model." Journal of the Society of Naval Architects of Korea, Vol. 51, No. 4, pp. 274-282. https://doi.org/10.3744/SNAK.2014.51.4.274
  8. Lee, D. R., and Koo, H. (2000). "Analysis of groundwater recharge characteristics using relationship between rainfall and groundwater level." Journal of Korea Water Resources Association, Vol. 33, No. 1, pp. 51-59.
  9. McKee, T. B., Doesken, N. J., and Kleist, J. (1995). "Drought monitoring with multiple time scales." Proceedings Ninth Conference on Applied Climatology, American Meteorological Society, Jan15-20, 1995, Dallas TX, pp. 233-236.
  10. Park, E. (2007). "A development of groundwater level fluctuations due to precipitations and infiltrations." Journal of KoSSGE, Vol. 12, No. 4, pp. 54-59.
  11. Van Gerven, M., and Bohte, S. (2017). Editorial: Artificial neural networks as models of neural information processing. Front. Comput. Neurosci., doi: 10.3389/fncom.2017.00114, pp. 11-114.
  12. Van Loon, A. (2015). "Hydrological drought explained," Wiley Interdisciplinary Reviews: WIREs Water, Vol. 2, pp. 359-392. doi: 10.1002/wat2.1085.
  13. Yang, J. S., and Ahn, T. Y. (2008). "The analysis of the correlation between groundwater level and the moving average of precipitation in Kum river watershed." The Journal of Engineering Geology, Vol. 18, No. 1, pp. 1-6. https://doi.org/10.3969/j.issn.1004-9665.2010.01.001
  14. Yang, J. S., Lim, C. H., Park, J. H., and Park, C. K. (2006). "The correlation between groundwater level and GOI with snowmelt effect in Ssangchun watershed." Journal of Korea Water Resources Association, Vol. 39, No. 2, pp. 121-126. https://doi.org/10.3741/JKWRA.2006.39.2.121
  15. Yeh, H. F., Chang, C. F., Lee, J. W., and Lee, C. H. (2016). "SGI and SPI for drought characteristics in Gaoping river basin, Taiwan." Journal of Chinese Soil and Water Conservation, Vol. 47, No. 1, pp. 45-52.