TDSVM을 이용한 하천수 취수량 예측 = Prediction on the amount of river water use using support vector machine with time series decomposition

다국어 초록 (Multilingual 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.

국문 초록 (Abstract)

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.

참고문헌 (Reference)

1 손흥구, "스마트 그리드에서의 시계열 군집분석을 통한 전력수요 예측 연구" 한국통계학회 29 (29): 193-203, 2016

2 최보승, "도시가스 수요량 예측을 위한 시계열 모형 개발" 한국통계학회 22 (22): 1019-1032, 2009

3 김화수, "가정용수 용도별 사용량의 통계적 특성 분석" 대한토목학회 28 (28): 603-614, 2008

4 권현한, "Wavelet Transform 방법과 SVM 모형을 활용한 상수도 수요량 예측기법 개발" 한국수자원학회 45 (45): 1187-1199, 2012

5 Farriansyah, A., "Water allocation computation model for river and multi-reservoir system with sustainability-efficiency-equity criteria" 10 (10): 1537-, 2018

6 MOLIT, "Water Vision (2001~2020)"

7 UN Water, "The united nations world water development report 2015, water for a sustainable world" UNESCO 2015

8 Cortes, C., "Support vector networks" 20 : 273-297, 1995

9 Khorasani, M., "Simulation and analysis of temporal changes of groundwater depth using time series modeling" 2 (2): 90-, 2016

10 Bougadis, J., "Short-term municipal water demand forecasting" 19 (19): 137-148, 2005

11 Barioni, L. G., "Report on modeldata comparison and improved model parameterisaion" INRA 59-, 2014

12 Barnett, M., "Real-time automation of water supply and distribution for the city of Jacksonville, Florida. USA" 9 (9): 15-29, 2004

13 Altunkaynak, A., "Monthly water consumption prediction using season algorithm and wavelet transform-based models" 143 (143): 04017011-1-04017011-10, 2017

14 MLTM, "Manual for the Permit-to-Use of River Water"

15 Amari, S., "Improving support vector machine classifiers by modifying kernel functions" 12 (12): 783-789, 1999

16 Gato, S., "Forecasting residential water demand: case study" 133 (133): 309-319, 2007

17 Bolouri-Yazdeli, Y., "Evaluation of real-time operation rules in reservoir systems operation" 28 (28): 715-729, 2014

18 Bai, Y., "Dynamic forecast of daily urban water consumption using a variable-structure support vector regression model" 14 (14): 04014058-, 2014

19 Goodfellow, I., "Deep learning" MIT press 2016

20 Meng, F., "Cost-effective river water quality management using integrated real-time control technology" 51 (51): 9876-9886, 2017

21 Candelieri, A., "Clustering and support vector regression for water demand forecasting and anomaly detection" 9 (9): 224-, 2017

22 Byun, H., "Applications of support vector machines for pattern recognition: a survey" Springer 213-236, 2002

23 De Jager, J. M., "Accuracy of vegetation evaporation ratio formulae for estimating final wheat yield" 20 : 307-314, 1994

24 Boser, B.E., "A training algorithm for optimal margin classifiers" ACM 144-152, 1992

25 Benitez, R., "A short-term data based water consumption prediction approach" 12 (12): 2359-, 2019

26 Jain, A., "A decision support system for drought characterization and management" 18 (18): 105-140, 2001

27 WMO, "2018 Annual Report, WMO for the Twenty-first Century" WMO 2019