Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Evaluating the groundwater prediction using LSTM model

LSTM 모형을 이용한 지하수위 예측 평가

  • 박창희 ((주)지오그린21 기업부설연구소) ;
  • 정일문 (한국건설기술연구원 국토보전연구본부)
  • Received : 2020.02.06
  • Accepted : 2020.03.18
  • Published : 2020.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Quantitative forecasting of groundwater levels for the assessment of groundwater variation and vulnerability is very important. To achieve this purpose, various time series analysis and machine learning techniques have been used. In this study, we developed a prediction model based on LSTM (Long short term memory), one of the artificial neural network (ANN) algorithms, for predicting the daily groundwater level of 11 groundwater wells in Hankyung-myeon, Jeju Island. In general, the groundwater level in Jeju Island is highly autocorrelated with tides and reflected the effects of precipitation. In order to construct an input and output variables based on the characteristics of addressing data, the precipitation data of the corresponding period was added to the groundwater level data. The LSTM neural network was trained using the initial 365-day data showing the four seasons and the remaining data were used for verification to evaluate the fitness of the predictive model. The model was developed using Keras, a Python-based deep learning framework, and the NVIDIA CUDA architecture was implemented to enhance the learning speed. As a result of learning and verifying the groundwater level variation using the LSTM neural network, the coefficient of determination (R2) was 0.98 on average, indicating that the predictive model developed was very accurate.

지하수자원의 변동성 및 취약성 평가를 위한 지하수위의 정량적 예측은 매우 중요하다. 이를 위해 다양한 시계열 분석 기법과 머신러닝 기법 등이 사용되어 왔다. 본 연구에서는 제주도 한경면 지역에 설치된 11개 지하수위 관측정의 일 수위자료를 대상으로 인공신경망 알고리즘의 하나인 Long short term memory (LSTM)에 기반한 예측 모델을 개발하였다. 제주도의 지하수위는 일반적으로 조석에 의한 자기상관성이 높고 강수에 의한 영향이 잘 반영되는 것으로 알려져 있다. 이러한 자료 특성을 고려한 입출력 텐서를 구성하기 위해 각 지하수 관측정의 수위변동 관측 자료와 같은 기간의 강수량 자료를 추가 입력자료로 선택하였다. 4계절을 나타내는 초기 365일 자료를 이용하여 LSTM 모델을 학습시켰으며 나머지 자료를 검증에 활용하여 예측 모델의 적합도를 평가하였다. 모델의 개발은 Python기반 딥러닝 프레임워크인 Keras를 이용하였고, 학습속도를 향상시키고자 NVIDIA CUDA 아키텍처를 도입하였다. LSTM 모델을 이용하여 지하수위 변화를 학습시키고 검증한 결과 결정계수가 평균 0.98로 나타나 개발된 예측모델의 적합성이 매우 높은 것으로 확인되었다.

Keywords

References

  1. Alley, W.M., Healy, R.W., LaBaugh, J.W., and Reilly, T.E. (2002). "Flow and storage in groundwater systems." Science, Vol. 296, No. 5575, pp. 1985-1990. https://doi.org/10.1126/science.1067123
  2. Behzad, M., Asghari, K., and Coppola, E.A. (2010). "Comparative study of SVMs and ANNs in aquifer water level prediction." Journal of Computing in Civil Engineering, Vol. 24, No. 5, pp. 408-413. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000043
  3. Brownlee, J. (2018). Better Deep Learning: Train Faster, Reduce Overfitting, and Make better Predictions. Machine Learning Mastery, p. 540.
  4. Chollet, F. (2017). Deep Learning with Python. Manning Publications, p. 384.
  5. Chu, H.J., and Chang, L.C. (2009). "Application of optimal control and fuzzy theory for dynamic groundwater remediation design." Water Resources Management, Vol. 23, No. 4, pp. 647-660. https://doi.org/10.1007/s11269-008-9293-1
  6. Coppola, E., Szidarovszky, F., Poulton, M., and Charles, E. (2003). "Artificial neural network approach for predicting transient water levels in a multilayered groundwater system under variable state, pumping, and climate conditions." Journal of Hydrologic Engineering, Vol. 8, No. 6, pp. 348-360. https://doi.org/10.1061/(ASCE)1084-0699(2003)8:6(348)
  7. Davis, J.C. (2002). Statistics and Data Analysis in Geology. 3rd editon, John Wiley & Sons, N.Y., U.S., p. 638.
  8. Helmus, J. (2018). TensorFlow in Anaconda, accessed 11 November 2018, .
  9. Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory." Neural Computation, Vol. 9, No. 8, pp.1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  10. Jung, S., Cho, H., Kim, J., and Lee, G. (2018). "Prediction of water level in a tidal river using a deep-learning based LSTM model." Journal of Korea Water Resources Association, Vol. 51, No. 12, pp. 1207-1216.
  11. Kingma, D., and Ba, J. (2015). "Adam: A method for stochastic optimization", The 3rd international Conference for Learning Representations, San Diego, C.A., U.S.
  12. Nikolos, I.K., Stergiadi, M., Papadopoulou, M.P., and Karatzas, G.P. (2008). "Artificial neural networks as an alternative approach to groundwater numerical modelling and environmental design." Hydrological Processes, Vol. 22, No. 17, pp. 3337-3348. https://doi.org/10.1002/hyp.6916
  13. NVIDIA (2016). NVIDIA Tesla P100 Whitepaper. NVIDIA, p. 45.
  14. Olah, C. (2015). Understanding LSTM Networks, accessed 11 November 2018, .
  15. Parkin, G., Birkinshaw, S.J., Younger, P.L., Rao, Z., and Kirk, S. (2007). "A numerical modelling and neural network approach to estimate the impact of groundwater abstractions on river flows." Journal of Hydrology, Vol. 339, No. 1-2, pp. 15-28. https://doi.org/10.1016/j.jhydrol.2007.01.041
  16. Sahoo, S., and Jha, M.K. (2013). "Groundwater-level prediction using multiple linear regression and artificial neural network techniques: A comparative assessment." Hydrogeology Journal, Vol. 21, No. 8, pp. 1865-1887. https://doi.org/10.1007/s10040-013-1029-5
  17. Sahoo, S., Russo, T.A., Elliott, J., and Foster, I. (2017). "Machine learning algorithms for modeling groundwater level changes in agricultural regions of the U.S." Water Resources Research, Vol. 53, pp. 3878-3895. https://doi.org/10.1002/2016WR019933
  18. Song, S.-H., Choi, K.-J., and Kim, J.-S. (2013). "Evaluation of regional characteristics using time-series data of groundwater level in Jeju Island." Journal of the Environmental Sciences International, Vol. 22, No. 5, pp. 609-623.
  19. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. (2014). "Dropout: A simple way to prevent neural networks from overfitting." Journal of Machine Learning Research, Vol. 15, pp.1929-1958.
  20. Sung, J., Lee, J., Chung, I.-M., and Heo, J.-H. (2017). "Hourly water level forecasting at tributary affected by main river condition." Water, Vol. 9, p. 644. https://doi.org/10.3390/w9090644
  21. Tran, Q., and Song, S. (2017). "Water level forecasting based on deep learning: A use case of trinity river-Texas-The United States." The Journal of Korean Institute of Information Scientists and Engineers, Vol. 44, No. 6, pp. 607-612.
  22. Yoon, H., Jun, S.-C., Hyun, Y., Bae, G.-O., and Lee, K.-K. (2011). "A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer." Journal of Hydrology, Vol. 396, No.1-2, pp. 128-138. https://doi.org/10.1016/j.jhydrol.2010.11.002
  23. Yoon, P., Yoon, H., Kim, Y., and Kim, G. (2014). "A comparative study on forecasting groundwater level fluctuations of national groundwater monitoring networks using TFNM, ANN, and ANFIS." Journal of soil and groundwater environment, Vol. 19, No. 3, pp. 123-133. https://doi.org/10.7857/JSGE.2014.19.3.123
  24. Zhang, Z., Zhu, Y., Zhang, X., Ye, M., and Yang, J. (2018). "Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural area." Journal of Hydrology, Vol. 561, pp. 918-929. https://doi.org/10.1016/j.jhydrol.2018.04.065