DOI QR코드

DOI QR Code

Determination of the Groundwater Yield of horizontal wells using an artificial neural network model incorporating riverside groundwater level data

배후지 지하수위를 고려한 인공신경망 기반의 수평정별 취수량 결정 기법

  • Received : 2018.09.11
  • Accepted : 2018.11.17
  • Published : 2018.12.31

Abstract

Recently, concern has arisen regarding the lowering of groundwater levels in the hinterland caused by the development of high-capacity radial collector wells in riverbank filtration areas. In this study, groundwater levels are estimated using Modflow software in relation to the water volume pumped by the radial collector well in Anseongcheon Stream. Using the water volume data, an artificial neural network (ANN) model is developed to determine the amount of water that can be withdrawn while minimizing the reduction of groundwater level. We estimate that increasing the pumping rate of the horizontal well HW-6, which is drilled parallel to the stream direction, is necessary to minimize the reduction of groundwater levels in wells OW-7 and OB-11. We also note that the number of input data and the classification of training and test data affect the results of the ANN model. This type of approach, which supplements ANN modeling with observed data, should contribute to the future groundwater management of hinterland areas.

최근들어 방사형 집수정 방식의 대용량 강변여과수 개발에 따른 배후지의 지하수위 강하에 대한 우려가 존재하고 있다. 본 연구에서는 안성천의 방사형 집수정을 대상으로 Modflow를 활용하여 수평정의 취수량에 따른 배후지의 수위 강하를 예측하였으며, 이 데이터를 기반으로 배후지 수위 강하가 최소가 되는 수평정별 취수량을 결정하는 다층퍼셉트론 기반의 인공신경망 모델을 개발하였다. 하천 방향으로 굴착된 수평정 HW-6의 취수량을 높이는 것이 OW-7 및 OB-11 관측정의 지하수위를 높게 유지하는데 필요한 것으로 평가되었다. 또한, 모델 입력 자료의 수 및 훈련과 검증 자료의 분류는 인공신경망 모델 결과에 영향을 미치므로 유의하여야 한다. 향후 현장의 실제 운영 자료와 수치모델의 비교를 통하여 인공신경망 모델을 보완한다면 배후지의 지하수 관리에 기여할 것으로 본다.

Keywords

JJGHBG_2018_v28n4_583_f0001.png 이미지

Fig. 1. (a) Location of the study area and (b) location of the radial collector well and groundwater-monitoring wells (adapted from Kim et al., 2016)

JJGHBG_2018_v28n4_583_f0002.png 이미지

Fig. 2. Design of the numerical model and comparison of actual and estimated water levels.

JJGHBG_2018_v28n4_583_f0003.png 이미지

Fig. 3. Multilayer perceptron concept of an artificial neural network with a hidden layer.

JJGHBG_2018_v28n4_583_f0004.png 이미지

Fig. 4. Scatterplots of original versus estimated groundwater levels at the two monitoring wells.

JJGHBG_2018_v28n4_583_f0005.png 이미지

Fig. 5. Simulation results for 52 cases of the pumping rate of a collector well for the two monitoring wells.

JJGHBG_2018_v28n4_583_f0006.png 이미지

Fig. 6. Scatterplots of horizontal well yields (y-axis) versus groundwater levels (x-axis).

JJGHBG_2018_v28n4_583_f0007.png 이미지

Fig. 7. Estimations of groundwater level at the monitoring wells for three cases: (1) Case 1, nine data points; (2) Case 2, eight data points; and (3) Case 3, five data points.

Table 1. Specifications of the radial collector well and hydraulic features of the aquifer

JJGHBG_2018_v28n4_583_t0001.png 이미지

Table 2. Simulation results for collector well pumping and the numerically estimated groundwater levels for the monitored wells

JJGHBG_2018_v28n4_583_t0002.png 이미지

Table 2. Simulation results for collector well pumping and the numerically estimated groundwater levels for the monitored wells (Continued)

JJGHBG_2018_v28n4_583_t0003.png 이미지

Table 3. Representative cases of groundwater level estimation using the ANN model

JJGHBG_2018_v28n4_583_t0004.png 이미지

Table 4. Characteristics and structure of the ANN models for the three cases

JJGHBG_2018_v28n4_583_t0005.png 이미지

Table 5. Statistics of estimated groundwater levels at two monitored wells

JJGHBG_2018_v28n4_583_t0006.png 이미지

References

  1. Adamowski, J. and Chan, H.F., 2011, A wavelet neural network conjunction model for groundwater level forecasting, Journal of Hydrology, 407(1-4), 28-40. https://doi.org/10.1016/j.jhydrol.2011.06.013
  2. Daliakopoulos, I. N., Coulibaly, P., and Tsanis, I. K., 2005, Groundwater level forecasting using artificial neural networks, Journal of Hydrology, 309(1-4), 229-240. https://doi.org/10.1016/j.jhydrol.2004.12.001
  3. Devarajan, K. and Sindhu, G., 2015, Application of numerical and empirical models for groundwater level forecasting, International Journal of Research in Engineering and Technology, 4(11), 127-133.
  4. Kim, T. H., Lee, C. H., Lee, J. H., Oh, D. H., and Kim, G. B., 2016, Estimation of groundwater yield at a horizontal well using soil characteristics at riverbank filtration site, Journal of the Geological Society of Korea, 52(3), 291-301 (in Korean with English abstract). https://doi.org/10.14770/jgsk.2016.52.3.291
  5. Kisi, O., Alizamir, M., and Zounemat-Kermani, M., 2017, Modeling groundwater fluctuaitons by three different evolutionaly neural nework techniques using hydroclimatic data, Natural Hazards, 87(1), 367-381. https://doi.org/10.1007/s11069-017-2767-9
  6. MOCT (Ministry of Construction and Transportation), 2007, National Master Plan of Groundwater Management, Seoul, Korea.
  7. Sahoo, G. B., Ray, C., Wang, J. Z., Hubbs, S. T., Song, R., Jasperse, J., and Seymour, D., 2005, Use of artificial neural networks to evaluate the effectiveness of riverbank filtration, Water Research, 39(12), 2505-2516. https://doi.org/10.1016/j.watres.2005.04.020
  8. Shamsuddin, M. K. N., Kusin, F. M., Sulaiman, W. N. A., Ramli, M. F., Baharuddin, M. F. T., and Adnan, M. S., 2017, Forecasting of groundwater level using artificial neural network by incorporating river recharge and river bank infiltration, MATEC Web Conference, 103, DOI: https://doi.org/10.1051/matecconf/201710304007.
  9. Zakaria, M., Al-Shebany, M., and Sarhan, S., 2014, Artificial neural network: a brief review, International Journal of Engineering Research and Applications, 4(2), 7-12.