DOI QR코드

DOI QR Code

Development of Return flow rate Prediction Algorithm with Data Variation based on LSTM

LSTM기반의 자료 변동성을 고려한 하천수 회귀수량 예측 알고리즘 개발연구

  • Lee, Seung Yeon (Hongik University Research Institute of Science and Technology) ;
  • Yoo, Hyung Ju (Dept. of Civil Engineering, Hongik University) ;
  • Lee, Seung Oh (Dept. of Civil Engineering, Hongik University)
  • 이승연 (홍익대학교 과학기술연구소) ;
  • 유형주 (홍익대학교 토목공학과) ;
  • 이승오 (홍익대학교 건설환경공학과)
  • Received : 2022.04.10
  • Accepted : 2022.06.10
  • Published : 2022.06.30

Abstract

The countermeasure for the shortage of water during dry season and drought period has not been considered with return flowrate in detail. In this study, the outflow of STP was predicted through a data-based machine learning model, LSTM. As the first step, outflow, inflow, precipitation and water elevation were utilized as input data, and the distribution of variance was additionally considered to improve the accuracy of the prediction. When considering the variability of the outflow data, the residual between the observed value and the distribution was assumed to be in the form of a complex trigonometric function and presented in the form of the optimal distribution of the outflow along with the theoretical probability distribution. It was apparently found that the degree of error was reduced when compared to the case not considering where the variance distribution. Therefore, it is expected that the outflow prediction model constructed in this study can be used as basic data for establishing an efficient river management system as more accurate prediction is possible.

가뭄 및 갈수시에 용수부족 현상이 발생하나 회귀수량을 고려한 대응이나 대책 마련이 진행되지 않고 있다. 이에 본 연구에서 자료기반의 기계학습 모형(LSTM)을 통해 회귀수량 중 하수종말처리장의 방류량을 예측하였다. 입력자료로 방류량, 유입량, 강수량, 수위를 사용하였고 예측 결과의 정확도를 개선하기 위하여 추가적으로 입력변수의 변동성 분포를 고려하였다. 방류량 자료의 변동성을 확인하기 위해서 관측값과 분포 사이의 잔차를 복합삼각함수 형태로 가정하여 이론적인 확률분포와 함께 방류량 최적의 분포 형태로 나타내었다. 변동성 분포를 고려한 입력자료를 이용한 결과와 그렇지 않는 결과를 비교한 결과, 오차정도가 감소함을 보였으며 이는 변동성 분포가 계절성을 상대적으로 잘 재현하였기 때문이라 판단된다. 따라서 본 연구에서 구축한 하수종말장처리장의 방류량 예측 모형을 활용할 경우 보다 정확한 회귀수량 예측이 가능하여 효율적인 하천수 관리 체계를 수립하는데 기초자료로 활용될 수 있을 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 환경부의 재원으로 한국환경산업기술원의 물관리연구사업(127572)에 의해 수행되었습니다.

References

  1. Arun, S. S. and Iyer, G. N. (2020). On the Analysis of COVID19-novel Corona Viral Disease Pandemic Spread Data Using Machine Learning Techniques. In 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE. pp.1222-1227.
  2. Gumbel, E. J. (1935). Les Valeurs Extremes Des Distributions Statis-tiques. Annales l'institut Henri Poincar'e. 5(2): 115-158.
  3. Hochreiter, S. and Schmidhuber, J. (1997). Long Short-term Memory. Neural Computation. 9(8): 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  4. Hyndman, R. J. and Athanasopoulos, G. (2018). Forecasting: Principles and Practice. OTexts.
  5. Jang, O. J. and Moon, Y. I. (2022). Predicting the Amount of Water Shortage during Dry Seasons Using Deep Neural Network with Data from RCP Scenarios. Journal of Korea Water Resources Association. 55(2): 121-133. https://doi.org/10.3741/JKWRA.2022.55.2.121
  6. Jung, S. H., Lee, D. E., and Lee, K. S. (2018). Prediction of River Water Level Using Deep-learning Open Library. Journal of the Korean Society of Hazard Mitigation. 18(1): 1-11. https://doi.org/10.9798/KOSHAM.2018.18.1.1
  7. Kim, D., Park, J., and Choi, J. (2014). A Comparative Study Between Stock Price Prediction Models Using Sentiment Analysis and Machine Learning Based on SNS and News Articles. Journal of Information Technology Services. 13(3): 221-233. https://doi.org/10.9716/KITS.2014.13.3.221
  8. Kim, J. H., Kim, K. T., and Han, J. K. (2015). Big Data Analysis based on Deep Learning for Baseball Game Data. Journal of Korea Institute of Communication Sciences. 2015(11): 262-265.
  9. Kim, J., Kang, M. S., and Kim, S. H. (2019). Comparing the Performance of Artificial Neural Networks and Long Short-Term Memory Networks for Rainfall-runoff Analysis. In Proceedings of the Korea Water Resources Association Conference. Korea Water Resources Association. pp.320-320.
  10. Kim, Y. and Kim, Y. M. (2021). Predicting Game Results using Machine Learning and Deriving Strategic Direction from Variable Importance. Journal of Korea Game Society. 21(4): 3-12. https://doi.org/10.7583/JKGS.2021.21.4.3
  11. Korea Meteorological Administration (KMA) (2021). Korea Climate Change Assessment Report 2021. Seoul: KMA.
  12. Lee, S. Y., Yoo, H. J., and Lee, S. O. (2021). Role of Unstructured Data on Water Surface Elevation Prediction with LSTM: Case Study on Jamsu Bridge, Korea. Journal of Korea Water Resources Association. 54(spc1): 1195-1204. https://doi.org/10.3741/JKWRA.2021.54.S-1.1195
  13. Lee, W. (2017). A Deep Learning Analysis of the KOSPI's Directions. Journal of the Korean Data and Information Science Society. 28(2): 287-295. https://doi.org/10.7465/jkdi.2017.28.2.287
  14. Ministry of Land Infrastructure and Transport (MOLIT) (2016). National Water Resources Plan (2011~2020) (3rd revision). Sejong: MOLIT.
  15. Oh, J. H., Ryu, K. S., Bok, J. S., Jang, Y. S., Bae, Y. D., and Lee, B. G. (2019). Water Supply-and-Demand Analysis Considering the Actual Water-Use System in the East Basin of Han River. Journal of the Korean Society of Hazard Mitigation. 19(7): 529-543. https://doi.org/10.9798/kosham.2019.19.7.529
  16. Ruxton, G. D. (2006). The Unequal Variance T-Test is an Underused Alternative to Student's T-Test and the Mann-Whitney U Test. Behavioral Ecology. 17(4): 688-690. https://doi.org/10.1093/beheco/ark016
  17. Seo, Y. J., Moon, H. W., and Woo, Y. T. (2019). A Win/Lose Prediction Model of Korean Professional Baseball Using Machine Learning Technique. Journal of the Korea Society of Computer and Information. 24(2): 17-24. https://doi.org/10.9708/JKSCI.2019.24.02.017
  18. Song, Y. J., Lee, J. W., and Lee, J. W. (2017). A Design and Implementation of Deep Learning Model for Stock Prediction Using Tensorflow. KIISE Transactions on Computing Practices. 23(11): 799-801.
  19. Tran, Q. T., Hao, L., and Trinh, Q. K. (2016). A Novel Procedure to Model and Forecast Mobile Communication Traffic by ARIMA/GARCH Combination Models. In 2016 International Conference on Modeling. Simulation and Optimization Technologies and Applications (MSOTA2016). Atlantis Press.
  20. Weibull, W. (1951). A Statistical Distribution Function of wide Applicability. Journal of Applied Mechanics.
  21. Yoo, H. J., Lee, S. O., Choi, S. H., and Park, M. H. (2020). Development of a Data-Driven Model for Forecasting Outflow to Establish a Reasonable River Water Management System. Journal of Korean Society of Disaster and Security. 13(4): 75-92. https://doi.org/10.21729/KSDS.2020.13.4.75
  22. Yoo, H., Lee, S. O., Choi, S., and Park, M. (2019). A Study on the Data Driven Neural Network Model for the Prediction of Time Series Data: Application of Water Surface Elevation Forecasting in Hangang River Bridge. Journal of Korean Society of Disaster and Security. 12(2): 73-82. https://doi.org/10.21729/KSDS.2019.12.2.73
  23. Zhang, D., Martinez, N., Lindholm, G., and Ratnaweera, H. (2018). Manage Sewer In-line Storage Control Using Hydraulic Model and Recurrent Neural Network. Water Resources Management. 32(6): 2079-2098. https://doi.org/10.1007/s11269-018-1919-3