Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction on the amount of river water use using support vector machine with time series decomposition

TDSVM을 이용한 하천수 취수량 예측

  • Choi, Seo Hye (Korea Institute of Civil Engineering and Building Technology) ;
  • Kwon, Hyun-Han (Department of Civil & Environmental Engineering, Sejong University) ;
  • Park, Moonhyung (Korea Institute of Civil Engineering and Building Technology)
  • 최서혜 (한국건설기술연구원 국토보전연구본부) ;
  • 권현한 (세종대학교 건설환경공학과 응용수문연구실) ;
  • 박문형 (한국건설기술연구원 국토보전연구본부)
  • Received : 2019.10.29
  • Accepted : 2019.12.09
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, as the incidence of climate warming and abnormal climate increases, the forecasting of hydrological factors such as precipitation and river flow is getting more complicated, and the risk of water shortage is also increasing. Therefore, this study aims to develop a model for predicting the amount of water intake in mid-term. To this end, the correlation between water intake and meteorological factors, including temperature and precipitation, was used to select input factors. In addition, the amount of water intake increased with time series and seasonal characteristics were clearly shown. Thus, the preprocessing process was performed using the time series decomposition method, and the support vector machine (SVM) was applied to the residual to develop the river intake prediction model. This model has an error of 4.1% on average, which is higher accuracy than the SVM model without preprocessing. In particular, this model has an advantage in mid-term prediction for one to two months. It is expected that the water intake forecasting model developed in this study is useful to be applied for water allocation computation in the permission of river water use, water quality management, and drought measurement for sustainable and efficient management of water resources.

최근 기후 온난화의 발생과 이상기후의 발생빈도가 증가함에 따라 강수량, 하천유량과 같은 수문학적 요소의 예측이 복잡해지고 있으며 물부족 발생 위험도 증가하고 있다. 따라서 본 연구에서는 중단기 하천 취수량을 예측하기 위한 모델을 개발하고자 하였다. 입력인자를 선정하기 위해 취수량과 기상인자들 간의 상관성분석을 수행한 결과 온도가 가장 영향이 큰 것으로 나타났다. 또한 취수량은 시계열에 따른 증가 경향과 계절적 특성이 뚜렷하게 나타나므로 시계열분해기법을 이용하여 전처리를 수행하고 잔차에 대해 서포트 벡터 머신(SVM)을 적용하여 취수량 예측 모델을 개발하였다. 이 모델은 평균적으로 4.1%의 오차율을 나타내며, 전처리를 하지 않은 SVM 모델에 비해 높은 정확도를 나타냈다. 특히, 1~2달에 대해 중단기 예측을 수행하였을 때 더 유리한 결과를 나타냈다. 본 연구에서 개발된 취수량 예측모델은 수자원의 지속가능하고 효율적인 관리를 위해 하천수 사용허가, 수질관리, 가뭄 대책 마련에 활용이 가능할 것으로 예상된다.

Keywords

References

  1. Altunkaynak, A., and Nigussie, T.A. (2017). "Monthly water consumption prediction using season algorithm and wavelet transform-based models." Journal of Water Resources Planning and Management, Vol. 143, No. 6, pp. 04017011-1-04017011-10. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000761
  2. Amari, S., and Wu, S. (1999). "Improving support vector machine classifiers by modifying kernel functions." In Proceedings of International Conference on Neural Networks, Vol. 12, No. 6, pp. 783-789.
  3. Bai, Y., Wang, P., Li, C., and Xie, J. (2014). "Dynamic forecast of daily urban water consumption using a variable-structure support vector regression model." Journal of Water Resources Planning and Management, Vol. 14, No. 3, pp. 04014058.
  4. Barioni, L.G., Bellocchi, G., Touhami, H.B., Conant, R., Chang, J., Coltri, P.P., Hassen, A., Martin, R., Silvestri, S., Sicerly, J., Tesfamariam, E.H., and Viovy, N. (2014). Report on modeldata comparison and improved model parameterisaion. INRA, France, p. 59 (hal-01611412).
  5. Barnett, M., Lee, T., Jentgen, L., Conrad, S., Kidder, H., Woolschlager, J., and Groff, C. (2004). "Real-time automation of water supply and distribution for the city of Jacksonville, Florida." USA. EICA, Vol. 9, No. 3, pp. 15-29.
  6. Benitez, R., Ortiz-Caraballo, C., Preciado, J.C., Conejero, J.M., Figueroa, F.S., and Rubio-Largo, A. (2019). "A short-term data based water consumption prediction approach." Energies, Vol. 12. No. 12, pp. 2359. https://doi.org/10.3390/en12122359
  7. Bolouri-Yazdeli, Y., Haddad, O.B., Fallah-Mehdipour, E., and Marino, M.A. (2014). "Evaluation of real-time operation rules in reservoir systems operation." Water resources management, Vol. 28, No. 3, pp. 715-729. https://doi.org/10.1007/s11269-013-0510-1
  8. Boser, B.E., Guyon, I.M., and Vapnik, V.N. (1992). "A training algorithm for optimal margin classifiers." In COLT '92: Proceeding of the fifth annual workshop on Computational learning theory, ACM, New York, NY, USA, pp. 144-152.
  9. Bougadis, J., Adamowski, K., and Diduch, R. (2005). "Short-term municipal water demand forecasting." Hydrological Processes: An International Journal, Vol. 19, No. 1, pp. 137-148. https://doi.org/10.1002/hyp.5763
  10. Byun, H., and Lee, S.W. (2002). "Applications of support vector machines for pattern recognition: a survey." International Workshop on Support Vector Machines. Springer, pp. 213-236.
  11. Candelieri, A. (2017). "Clustering and support vector regression for water demand forecasting and anomaly detection." Water, Vol. 9, No. 3, p. 224. https://doi.org/10.3390/w9030224
  12. Choi, B.S., Kang, H.C., Lee, K.Y., and Han, S.T. (2009). "A development of time-series model for city gas demand forecasting." Korean Journal of Applied Statistics, Vol. 22, No. 5, pp. 1019-1032. https://doi.org/10.5351/KJAS.2009.22.5.1019
  13. Cortes, C., and Vapnik, V. (1995). Support vector networks. Machine Learning, Vol. 20, pp. 273-297. https://doi.org/10.1007/BF00994018
  14. De Jager, J.M., (1994). "Accuracy of vegetation evaporation ratio formulae for estimating final wheat yield." Water SA, Vol. 20, pp. 307-314.
  15. Farriansyah, A., Juwono, P., Suhartanto, E., and Dermawan, V. (2018). "Water allocation computation model for river and multi-reservoir system with sustainability-efficiency-equity criteria." Water, Vol. 10, No. 11, pp. 1537. https://doi.org/10.3390/w10111537
  16. Gato, S., Jayasuriya, N., and Roberts, P. (2007). "Forecasting residential water demand: case study." Journal of Water Resources Planning and Management, Vol. 133, No. 4, pp. 309-319. https://doi.org/10.1061/(ASCE)0733-9496(2007)133:4(309)
  17. Goodfellow, I., Bengio, Y., and Courville, A. (2016). "Deep learning." MIT press.
  18. Jain, A., and Ormsbee, L.E. (2001). "A decision support system for drought characterization and management." Civil Engineering Systems, Vol. 18, No. 2, pp. 105-140. https://doi.org/10.1080/02630250108970296
  19. Khorasani, M., Ehteshami, M., Ghadimi, H., and Salari, M. (2016). "Simulation and analysis of temporal changes of groundwater depth using time series modeling." Model. Earth Syst. Environ., Vol. 2, No. 2, p. 90. https://doi.org/10.1007/s40808-016-0164-0
  20. Kim, H., Lee, D., Park, N., and Jung, K. (2008). "Analysis on statistical characteristics of household water end-uses." Journal of the Korean Society of Civil Engineers, Vol. 28, No. 5, pp. 603-614.
  21. Kwon, H., Kim, M., and Kim, W. (2012). "A development of water demand forecasting model based on Wavelet transform and Support vector machine." Journal of Korea Water Resources Association, Vol. 45, No. 11, pp. 1187-1199. https://doi.org/10.3741/JKWRA.2012.45.11.1187
  22. Meng, F., Fu, G., and Butler, D. (2017). "Cost-effective river water quality management using integrated real-time control technology." Environmental science & technology, Vol. 51, No. 17, pp. 9876-9886. https://doi.org/10.1021/acs.est.7b01727
  23. MLTM (2009). Manual for the Permit-to-Use of River Water.
  24. MOLIT (2016). Water Vision (2001-2020).
  25. Sohn, H., Jung, S., and Kim, S. (2016). "A study on electricity demand forecasting based on time series clustering in smart grid." The Korean Journal of Applied Statistics, Vol. 29, No. 1, pp. 193-203. https://doi.org/10.5351/KJAS.2016.29.1.193
  26. UN Water (2015). "The united nations world water development report 2015, water for a sustainable world." UNESCO, Paris, France.
  27. WMO (2019). "2018 Annual Report, WMO for the Twenty-first Century." WMO, Switzerland.