The Journal of Engineering Geology (지질공학)

The Korean Society of Engineering Geology (대한지질공학회)
권호 표지
DOI QR코드

DOI QR Code

Application of groundwater-level prediction models using data-based learning algorithms to National Groundwater Monitoring Network data

자료기반 학습 알고리즘을 이용한 지하수위 변동 예측 모델의 국가지하수관측망 자료 적용에 대한 비교 평가 연구

  • 윤희성 (한국지질자원연구원 지구환경연구본부) ;
  • 김용철 (한국지질자원연구원 지구환경연구본부) ;
  • 하규철 (한국지질자원연구원 지구환경연구본부) ;
  • 김규범 (K-water연구원 수변지하수연구단)
  • Received : 2013.05.06
  • Accepted : 2013.06.24
  • Published : 2013.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

For the effective management of groundwater resources, it is necessary to predict groundwater level fluctuations in response to rainfall events. In the present study, time series models using artificial neural networks (ANNs) and support vector machines (SVMs) have been developed and applied to groundwater level data from the Gasan, Shingwang, and Cheongseong stations of the National Groundwater Monitoring Network. We designed four types of model according to input structure and compared their performances. The results show that the rainfall input model is not effective, especially for the prediction of groundwater recession behavior; however, the rainfall-groundwater input model is effective for the entire prediction stage, yielding a high model accuracy. Recursive prediction models were also effective, yielding correlation coefficients of 0.75-0.95 with observed values. The prediction errors were highest for Shingwang station, where the cross-correlation coefficient is lowest among the stations. Overall, the model performance of SVM models was slightly higher than that of ANN models for all cases. Assessment of the model parameter uncertainty of the recursive prediction models, using the ratio of errors in the validation stage to that in the calibration stage, showed that the range of the ratio is much narrower for the SVM models than for the ANN models, which implies that the SVM models are more stable and effective for the present case studies.

지하수자원의 효율적인 관리를 위해 강우에 대한 지하수위 변화를 예측하는 것은 중요한 문제이다. 본 연구에서는 자료기반 학습 알고리즘인 인공신경망과 지지벡터기계를 이용하여 시계열 예측 모델을 만들고 이를 국가지하수관측망 중 가산, 신광, 청성 관측소 지하수위 변화 예측에 적용하였다. 모델의 입력 성분 구성 방법에 따라 네 가지 모형을 설정하고 각 관측소 및 모델 별 예측 결과를 비교 평가하였다. 강우 입력 모형의 경우 지하수위 감쇠 및 기저 변화 예측을 위해 큰 규모의 입력 성분 구성이 필요하지만 강우 및 지하수위 입력 모형은 보다 작은 규모의 입력 성분으로 효과적으로 지하수위 변화를 예측하는 것으로 나타났다. 강우 및 지하수위 입력 모형의 활용성 증대를 위해 고안된 반복 예측 모형의 경우 관측값과 예측값 사이에 0.75~0.95의 상관계수를 보여 적용 가능성이 큰 것으로 판단된다. 전체적으로 강우-지하수위 교차상관계수가 낮은 신광 관측소의 예측 오차가 크게 나타났고 ANN 모델에 비해 SVM의 예측력이 다소 높은 것으로 조사되었다. 또한 반복 예측 모형의 모델 파라미터 선정 과정에서 보정 단계 오차에 대한 예측 단계 오차의 비의 분포를 조사한 결과 SVM의 경우가 더 작게 나타나 SVM이 본 연구 자료에 대해 보다 안정적이고 효율적인 모델임을 평가하였다.

Keywords

References

  1. Almasri, M. N. and Kaluarachchi, J. J., 2005, Modular neural networks to predict the nitrate distribution in ground water using the on-ground nitrate loading and recharge data. Environmental Modelling and Software, 20, 851-871. https://doi.org/10.1016/j.envsoft.2004.05.001
  2. Asefa, T., Kemblowski, M., McKee, M., and Khalil, A., 2006, Multi-time scale stream flow predictions: The support vector machines approach. Journal of Hydrology, 318, 7-16. https://doi.org/10.1016/j.jhydrol.2005.06.001
  3. Box, G. E. P. and Jenkins, G. M., 1976, Time Series Analysis- Forecasting and Control, Holden-Day, San Francisco, California, USA, 575p.
  4. Coppola, E., Rana, A. J., Poulton, M. M., Szidarovszky, F., and Uhl, V. V., 2005, A neural network model for predicting aquifer water level elevations, Ground Water 43(2), 231-241. https://doi.org/10.1111/j.1745-6584.2005.0003.x
  5. Hsu, K. L., Gupta, H. V., Gao, X. G., Sorooshian, S., and Imam, B., 2002, Self-organizing linear output map (SOLO): an artificial neural network suitable for hydrologic modeling and analysis, Water Resources Research, 38(12), 381-3817. https://doi.org/10.1029/2001WR001058
  6. Jain, A. and Kumar, A. M., 2007, Hybrid neural network models for hydrologic time series forecasting, Applied Soft Computing, 7, 585-592. https://doi.org/10.1016/j.asoc.2006.03.002
  7. Khan, M. S. and Coulibaly, P., 2006, Application of support vector machine in lake water level prediction, Journal of Hydrologic Engineering, 11(3), 199-205. https://doi.org/10.1061/(ASCE)1084-0699(2006)11:3(199)
  8. Knotters, M. and Bierkens, M. F. P., 2000, Physical basis of time series models for water table depths, Water Resources Research, 36(1), 181-188. https://doi.org/10.1029/1999WR900288
  9. Nayak, P. C., Satyaji Rao, Y. R., and Sudheer, K. P., 2006, Groundwater level forecasting in a shallow aquifer using artificial neural network approach, Water Resources Management, 20, 77-90. https://doi.org/10.1007/s11269-006-4007-z
  10. Park, E. and Parker, J. C., 2008, A simple model for water table fluctuations in response to precipitation, Journal of Hydrology, 356, 344-349. https://doi.org/10.1016/j.jhydrol.2008.04.022
  11. Platt, J. C., 1999, Fast training of support vector machines using sequential minimal optimization. In:Scholkopf, B., Burges, C.J.C., Smolar, A.J. (Eds.), Advances in Kernel Methods-Support Vector Learning, MIT Press, Cambridge, Massachusetts, USA, 376p.
  12. Rai, S. N. and Singh, R. N., 1995, Two-dimensional modelling of water table fluctuation in response to localized transient recharge, Journal of Hydrology, 167, 167-174. https://doi.org/10.1016/0022-1694(94)02607-D
  13. Rumelhart, D. E., McClelland, J. L., and The PDP Research Group, 1986, Parallel Distributed Processing:Explorations in the Microstructure of Cognition. MIT Press, Cambridge, Massachusetts, USA, 516p.
  14. Sahoo, G. B., Ray, C., and De Carlo, E. H., 2006, Use of neural network to predict flash flood and attendant water qualities of a mountainous stream on Oahu, Hawaii, Journal of Hydrology 327, 525-538. https://doi.org/10.1016/j.jhydrol.2005.11.059
  15. Suen, J. P. and Eheart, J. W., 2003, Evaluation of neural networks for modeling nitrate concentrations in rivers, Journal of Water Resources Planning and Management-ASCE 129(6), 505-510. https://doi.org/10.1061/(ASCE)0733-9496(2003)129:6(505)
  16. Scholkopf, B. and Smola, A. J., 2002, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge, Massachusetts, USA, 656p.
  17. Srivastava, K., Rai, S. N., and Singh, R. N., 2002, Modeling water-table fluctuations in a sloping aquifer with random hydraulic conductivity. Environmental Geology, 41(5), 520-524. https://doi.org/10.1007/s002540100385
  18. Tankersley, C. D., Graham, W. D., and Hatfield, K., 1993, Comparison of univariate and transfer function models of groundwater fluctuations. Water Resources Research, 29, 3517-3533. https://doi.org/10.1029/93WR01527
  19. van Geer, F. C. and Zuur, A. F., 1997, An extension of Box-Jenkins transfer/noise models for spatial interpolation of groundwater head series. Journal of Hydrology, 192, 65-80. https://doi.org/10.1016/S0022-1694(96)03113-7
  20. Vapnik, V. N., 1995, The Nature of Statistical Learning Theory, Springer-Verlag, New York, USA, 314p.
  21. Yi, M. J. and Lee, K. K., 2004, Transfer function-noise modeling of irregularly observed groundwater heads using precipitation data. Journal of Hydrology, 288, 272-287. https://doi.org/10.1016/j.jhydrol.2003.10.020
  22. Yoon, H., Jun, S. C., Hyun, Y., Bae, G. O., and Lee, K. K., 2011, A comparative study of artificial neural network and support vector machines for predicting groundwater levels in a coastal aquifer, Journal of Hydrology, 396, 128-138. https://doi.org/10.1016/j.jhydrol.2010.11.002
  23. Zealand, C. M., Burn, D. H., and Simonovic, S. P., 1999, Short-term streamflow forecasting using artificial neural networks, Journal of Hydrology, 214, 32-48. https://doi.org/10.1016/S0022-1694(98)00242-X

Cited by

  1. Abnormal Changes in Groundwater Monitoring Data Due to Small-Magnitude Earthquakes vol.25, pp.1, 2015, https://doi.org/10.9720/kseg.2015.1.21
  2. A Comparative Study on Forecasting Groundwater Level Fluctuations of National Groundwater Monitoring Networks using TFNM, ANN, and ANFIS vol.19, pp.3, 2014, https://doi.org/10.7857/JSGE.2014.19.3.123
  3. Gray Models for Real-Time Groundwater-Level Forecasting in Irrigated Paddy-Field Districts vol.142, pp.1, 2016, https://doi.org/10.1061/(ASCE)IR.1943-4774.0000940
  4. Status of Exploitable Groundwater Estimations in Korea vol.25, pp.3, 2015, https://doi.org/10.9720/kseg.2015.3.403
  5. Characterising Bedrock Aquifer Systems in Korea Using Paired Water-Level Monitoring Data vol.9, pp.6, 2017, https://doi.org/10.3390/w9060420
  6. A Method to Filter Out the Effect of River Stage Fluctuations using Time Series Model for Forecasting Groundwater Level and its Application to Groundwater Recharge Estimation vol.20, pp.3, 2015, https://doi.org/10.7857/JSGE.2015.20.3.074
  7. Application of machine learning technique-based time series models for prediction of groundwater level fluctuation to national groundwater monitoring network data vol.52, pp.3, 2016, https://doi.org/10.14770/jgsk.2016.52.3.187
  8. 인공신경망 모형을 이용한 제주 지하수위의 장기예측 vol.37, pp.6, 2013, https://doi.org/10.12652/ksce.2017.37.6.0981
  9. 전력 거래량 예측에서의 머신 러닝 성능 비교 vol.14, pp.5, 2013, https://doi.org/10.13067/jkiecs.2019.14.5.943
  10. ANFIS 알고리즘을 이용한 지하수수위 예측 vol.14, pp.6, 2013, https://doi.org/10.13067/jkiecs.2019.14.6.1235