DOI QR코드

DOI QR Code

백록담 강수량 관측자료가 제주도 중산간지역 지하수위 예측 향상에 미치는 영향

Impact of Baekrokdam precipitation observation data on improving groundwater level prediction in mid-mountainous region of Jeju Island

  • 신문주 (제주특별자치도개발공사 먹는물연구소) ;
  • 김정훈 (제주특별자치도개발공사 먹는물연구소) ;
  • 강수연 (제주특별자치도개발공사 먹는물연구소) ;
  • 문수형 (제주특별자치도개발공사 먹는물연구소) ;
  • 현은희 (제주특별자치도개발공사 R&D혁신본부)
  • Shin, Mun-Ju (Drinking Water Research Laboratory, Jeju Special Self-Governing Province Development Corporation) ;
  • Kim, Jeong-Hun (Drinking Water Research Laboratory, Jeju Special Self-Governing Province Development Corporation) ;
  • Kang, Su-Yeon (Drinking Water Research Laboratory, Jeju Special Self-Governing Province Development Corporation) ;
  • Moon, Soo-Hyoung (Drinking Water Research Laboratory, Jeju Special Self-Governing Province Development Corporation) ;
  • Hyun, Eun Hee (R&D Innovation Division, Jeju Special Self-Governing Province Development Corporation)
  • 투고 : 2024.08.14
  • 심사 : 2024.09.23
  • 발행 : 2024.10.31

초록

지하수는 지표수와 함께 다양한 용수로 사용되는 중요한 수자원이며, 특히 제주도의 경우 대부분의 용수를 지하수에 의존하고 있기 때문에 지속가능한 지하수의 이용을 위해 지하수량의 예측 및 관리는 매우 중요하다. 본 연구에서는 정확한 지하수위 예측을 위해 백록담 기후변화관측소의 강수량 데이터를 추가적으로 사용하여 제주도 표선유역 중산간 지역에 위치한 2개 관측정에 대해 ANN 모델과 LSTM 모델의 월 단위 지하수위 예측성능 개선효과를 비교분석 하였다. 그 결과, 백록담 강수량 데이터를 사용하지 않은 경우 두 인공지능 모델의 NSE 값은 0.871 이상을 보여 높은 지하수위 예측성능을 보였다. LSTM 모델은 ANN 모델보다 고수위 및 저수위에서 상대적으로 높은 예측성능을 나타내었으며, 관측지하수위의 변동폭이 커 변동특성이 복잡할수록 예측성능이 낮아짐을 확인하였다. 백록담 강수량 데이터를 추가적으로 사용한 경우 두 인공지능 모델의 NSE 값은 0.907 이상을 보여 개선된 예측성능을 나타내었으며, NSE 값은 최대 0.036만큼 개선되었다. 이것은 상류지역의 강수량을 추가적으로 사용 시 지하수위 해석에 도움이 되는 정보가 많아져 인공지능 모델은 지하수위의 변동특성을 더욱 적절히 해석할 수 있다는 것을 의미한다. 또한 관측지하수위 변동폭이 더 커 지하수위 예측이 상대적으로 어려운 관측정일수록 그리고 지하수위 예측성능이 상대적으로 낮은 인공지능 모델일수록 백록담 강수량 데이터의 추가사용시 지하수위 예측 개선에 더욱 도움이 되었다. 특히, 특정 관측정에 대해 백록담 강수량 데이터를 추가적으로 사용 시 ANN 모델의 지하수위 예측성능은 LSTM 모델과 대등한 수준으로 개선되었다. 본 연구의 방법 및 결과는 향후 인공지능 모델을 활용한 연구에서 유용하게 사용될 수 있다.

Groundwater is an important water resource used for various purposes along with surface water. Jeju Island relies on groundwater for most of its water use, so predicting and managing groundwater volume is very important for sustainable use of groundwater. In this study, precipitation data from the Baekrokdam Climate Change Observatory was additionally used to accurately predict groundwater levels. We compared and analyzed the improvement in monthly groundwater level prediction performance of the ANN and LSTM models for two observation wells located in the mid-mountainous area of the Pyoseon watershed in Jeju Island. As a result, when Baekrokdam precipitation data was not used, the NSE values of the two artificial intelligence models were over 0.871, showing very high groundwater level prediction performance. The LSTM model showed relatively higher prediction performance at high and low groundwater levels than the ANN model. We found that the prediction performance decreases as the variation characteristics of the groundwater level become more complex. When Baekrokdam precipitation data was additionally used, the NSE values of the two artificial intelligence models were above 0.907, indicating improved prediction performance, and the NSE value was improved by up to 0.036. This means that when additional rainfall in the upstream area is used, the artificial intelligence model can more appropriately interpret the fluctuating characteristics of the groundwater level. In addition, the additional use of Baekrokdam precipitation data further helped improve groundwater level prediction for observation well, where groundwater level prediction is relatively difficult, and artificial intelligence models, which have relatively low groundwater level prediction performance. In particular, when Baekrokdam precipitation data was additionally used for a specific observation well, the groundwater level prediction performance of the ANN model was improved to a level comparable to that of the LSTM model. The methods and results of this study can be useful in future research using artificial intelligence models.

키워드

과제정보

본 연구는 제주지방기상청에서 백록담 기후변화관측소의 기상자료를 제공받아 연구에 사용하였습니다. 자료 제공에 감사드립니다.

참고문헌

  1. Adamowski, J., and Chan, H.F. (2011). "A wavelet neural network conjunction model for groundwater level forecasting." Journal of Hydrology, Vol. 407, No. 1-4, pp. 28-40. https://doi.org/10.1016/j.jhydrol.2011.06.013
  2. Alizamir, M., Kisi, O., and Zounemat-Kermani, M. (2018). "Modelling long-term groundwater fluctuations by extreme learning machine using hydro-climatic data." Hydrological Sciences Journal, Vol. 63, No. 1, pp. 63-73. https://doi.org/10.1080/02626667.2017.1410891
  3. Barthel, R., and Banzhaf, S. (2016). "Groundwater and surface water interaction at the regional-scale - a review with focus on regional integrated models." Water Resources Management, Vol. 30, No. 1, pp. 1-32. https://doi.org/10.1007/s11269-015-1163-z
  4. Bengio, Y., Simard, P., and Frasconi, P. (1994). "Learning long-term dependencies with gradient descent is difficult." IEEE Transactions on Neural Networks, Vol. 5, No. 2, pp. 157-166. https://doi.org/10.1109/72.279181
  5. Bizhanimanzar, M., Leconte, R., and Nuth, M. (2019). "Modelling of shallow water table dynamics using conceptual and physically based integrated surface-water - groundwater hydrologic models." Hydrology and Earth System Sciences, Vol. 23, No. 5, pp. 2245-2260. https://doi.org/10.5194/hess-23-2245-2019
  6. Chollet, F., and Allaire, J.J. (2018). Deep learning with R. Manning Publications, Shelter Island, NY, U.S., p. 360.
  7. Davoudi Moghaddam, D., Rahmati, O., Haghizadeh, A., and Kalantari, Z. (2020). "A modeling comparison of groundwater potential mapping in a mountain bedrock aquifer: QUEST, GARP, and RF models." Water, Vol. 12, No. 3, 679.
  8. Falbel, D., Allaire, J.J., Chollet, F., Tang, Y., Van Der Bijl, W., Studer, M., Keydana, S. (2019). R Interface to 'Keras'. R Package Version 2.2.4.1, accessed 5 April 2019, <https://CRAN.R-project.org/package=keras>.
  9. Fallah-Mehdipour, E., Haddad, O.B., and Marino, M.A. (2013). "Prediction and simulation of monthly groundwater levels by genetic programming." Journal of Hydro-Environment Research, Vol. 7, No. 4, pp. 253-260. https://doi.org/10.1016/j.jher.2013.03.005
  10. Gharehbaghi, A., Ghasemlounia, R., Ahmadi, F., and Albaji, M. (2022). "Groundwater level prediction with meteorologically sensitive Gated Recurrent Unit (GRU) neural networks." Journal of Hydrology, Vol. 612, 128262.
  11. Gholizadeh, H., Zhang, Y., Frame, J., Gu, X., and Green, C.T. (2023). "Long short-term memory models to quantify long-term evolution of streamflow discharge and groundwater depth in Alabama." Science of the Total Environment, Vol. 901, 165884.
  12. Gong, Y., Zhang, Y., Lan, S., and Wang, H. (2016). "A comparative study of artificial neural networks, support vector machines and adaptive neuro fuzzy inference system for forecasting groundwater levels near Lake Okeechobee, Florida." Water Resources Management, Vol. 30, pp. 375-391.
  13. Hahnloser, R.H., Sarpeshkar, R., Mahowald, M.A., Douglas, R.J., and Seung, H.S. (2000). "Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit." Nature, Vol. 405, No. 6789, pp. 947-951. https://doi.org/10.1038/35016072
  14. Haykin, S. (2009). Neural networks and learning machines, Pearson Prentice Hall, Upper Saddle River, NJ, U.S.
  15. 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
  16. Jeihouni, E., Mohammadi, M., Eslamian, S., and Zareian, M.J. (2019). "Potential impacts of climate change on groundwater level through hybrid soft-computing methods: a case study - Shabestar Plain, Iran." Environmental Monitoring and Assessment, Vol. 191, No. 10, 620.
  17. Jeju Special Self-Governing Province (JSSGP) (2022). Basic plan for integrated water management for Jeju Special Self-Governing Province. pp. 1-485.
  18. Jha, M.K., and Sahoo, S. (2014). "Efficacy of neural network and genetic algorithm techniques in simulating spatio-temporal fluctuations of groundwater." Hydrological Processes, Vol. 29, No. 5, pp. 671-691.
  19. Kim, D., Jang, C., Choi, J., and Kwak, J. (2023). "A case study: Groundwater level forecasting of the gyorae area in actual practice on jeju island using deep-learning technique." Water, Vol. 15, No. 5, 972.
  20. Kim, I., and Lee, J. (2022). "Performance analysis of ANN prediction for groundwater level considering regional- specific influence components." Groundwater, Vol. 60, No. 3, pp. 344-361. https://doi.org/10.1111/gwat.13156
  21. Kim, T.W., and Valdes, J.B. (2003). "Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks." Journal of Hydrologic Engineering, Vol. 8, No. 6, pp. 319-328. https://doi.org/10.1061/(ASCE)1084-0699(2003)8:6(319)
  22. Kingma, D.P., and Ba, J. (2014). "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980.
  23. Kow, P.Y., Liou, J.Y., Sun, W., Chang, L.C., and Chang, F.J. (2024). "Watershed groundwater level multistep ahead forecasts by fusing convolutional-based autoencoder and LSTM models." Journal of Environmental Management, Vol. 351, 119789.
  24. Lallahem, S., Mania, J., Hani, A., and Najjar, Y. (2005). "On the use of neural networks to evaluate groundwater levels in fractured media." Journal of Hydrology, Vol. 307, No. 1-4, pp. 92-111. https://doi.org/10.1016/j.jhydrol.2004.10.005
  25. Le, X.H., Ho, H.V., Lee, G., and Jung, S. (2019). "Application of long short-term memory (LSTM) neural network for flood forecasting." Water, Vol. 11, No. 7, 1387.
  26. Maier, H.R., and Dandy, G.C. (2000). "Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications." Environmental Modelling & Software, Vol. 15, No. 1, pp. 101-124. https://doi.org/10.1016/S1364-8152(99)00007-9
  27. McDonald, M.G., and Harbaugh, A.W. (1988). A modular three-dimensional finite-difference ground-water flow model. Vol. 6. US Geological Survey, Reston, VA, U.S.
  28. Mirarabi, A., Nassery, H.R., Nakhaei, M., Adamowski, J., Akbarzadeh, A.H., and Alijani, F. (2019). "Evaluation of data-driven models (SVR and ANN) for groundwater-level prediction in confined and unconfined systems." Environmental Earth Sciences, Vol. 78, No. 15, pp. 1-15. https://doi.org/10.1007/s12665-018-7995-0
  29. Mohanty, S., Jha, M.K., Kumar, A., and Panda, D.K. (2013). "Comparative evaluation of numerical model and artificial neural network for simulating groundwater flow in Kathajodi - Surua Inter-basin of Odisha, India." Journal of Hydrology, Vol. 495, pp. 38-51. https://doi.org/10.1016/j.jhydrol.2013.04.041
  30. Mohanty, S., Jha, M.K., Kumar, A., and Sudheer, K.P. (2010). "Artificial neural network modeling for groundwater level forecasting in a river island of eastern India." Water Resources Management, Vol. 24, pp. 1845-1865.
  31. Moriasi, D.N., Arnold, J.G., Van Liew, M.W., Bingner, R.L., Harmel, R.D., and Veith, T.L. (2007). "Model evaluation guidelines for systematic quantification of accuracy in watershed simulations." Transactions of the ASABE, Vol. 50, No. 3, pp. 885-900. https://doi.org/10.13031/2013.23153
  32. Muller, J., Park, J., Sahu, R., Varadharajan, C., Arora, B., Faybishenko, B., and Agarwal, D. (2021). "Surrogate optimization of deep neural networks for groundwater predictions." Journal of Global Optimization, Vol. 81, No. 1, pp. 203-231. https://doi.org/10.1007/s10898-020-00912-0
  33. Nash, J.E., and Sutcliffe, J.V. (1970). "River flow forecasting through conceptual models part I - A discussion of principles." Journal of Hydrology, Vol. 10, No. 3, pp. 282-290. https://doi.org/10.1016/0022-1694(70)90255-6
  34. Payne, K., Chami, P., Odle, I., Yawson, D.O., Paul, J., Maharaj-Jagdip, A., and Cashman, A. (2022). "Machine learning for surrogate groundwater modelling of a small carbonate island." Hydrology, Vol. 10, No. 1, 2.
  35. Prechelt, L. (2012) "Early stopping - but when?" Neural networks: tricks of the trade, Edited by Montavon, G., Orr, G.B., and Muller, KR., Springer, Heidelberg, Germany, pp. 53-67.
  36. Rajaee, T., Ebrahimi, H., and Nourani, V. (2019). "A review of the artificial intelligence methods in groundwater level modeling." Journal of Hydrology, Vol. 572, pp. 336-351. https://doi.org/10.1016/j.jhydrol.2018.12.037
  37. Rakhshandehroo, G.R., Vaghefi, M., and Aghbolaghi, M.A. (2012). "Forecasting groundwater level in Shiraz plain using artificial neural networks." Arabian Journal for Science and Engineering, Vol. 37, No. 7, pp. 1871-1883. https://doi.org/10.1007/s13369-012-0291-5
  38. Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986). "Learning representations by back-propagating errors." Nature, Vol. 323, No. 6088, pp. 533-536. https://doi.org/10.1038/323533a0
  39. Sahoo, S., Russo, T.A., Elliott, J., and Foster, I. (2017). "Machine learning algorithms for modeling groundwater level changes in agricultural regions of the US." Water Resources Research, Vol. 53, No. 5, pp. 3878-3895. https://doi.org/10.1002/2016WR019933
  40. Seidu, J., Ewusi, A., Kuma, J.S.Y., Ziggah, Y.Y., and Voigt, H.J. (2023). "Impact of data partitioning in groundwater level prediction using artificial neural network for multiple wells." International Journal of River Basin Management, Vol. 21, No. 4, pp. 639-650. https://doi.org/10.1080/15715124.2022.2079653
  41. Seifi, A., Ehteram, M., Singh, V.P., and Mosavi, A. (2020). "Modeling and uncertainty analysis of groundwater level using six evolutionary optimization algorithms hybridized with ANFIS, SVM, and ANN." Sustainability, Vol. 12, No. 10, 4023.
  42. Shin, M.J., Kim, J.W., Moon, D.C., Lee, J.H., and Kang, K.G. (2021). "Comparative analysis of activation functions of artificial neural network for prediction of optimal groundwater level in the middle mountainous area of Pyoseon watershed in Jeju Island." Journal of Korea Water Resources Association, Vol. 54, No. 12, pp. 1143-1154. https://doi.org/10.3741/JKWRA.2021.54.S-1.1143
  43. Shin, M.J., Moon, S.H., Kang, K.G., Moon, D.C., and Koh, H.J. (2020). "Analysis of groundwater level variations caused by the changes in groundwater withdrawals using long short-term memory network." Hydrology, Vol. 7, No. 3, 64.
  44. Sit, M., Demiray, B.Z., Xiang, Z., Ewing, G.J., Sermet, Y., and Demir, I. (2020). "A comprehensive review of deep learning applications in hydrology and water resources." Water Science and Technology, Vol. 82, No. 12, pp. 2635-2670. https://doi.org/10.2166/wst.2020.369
  45. Sun, J., Hu, L., Li, D., Sun, K., and Yang, Z. (2022). "Data-driven models for accurate groundwater level prediction and their practical significance in groundwater management." Journal of Hydrology, Vol. 608, 127630.
  46. Sun, Y., Wendi, D., Kim, D.E., and Liong, S.Y. (2016). "Application of artificial neural networks in groundwater table forecasting - a case study in a Singapore swamp forest." Hydrology and Earth System Sciences, Vol. 20, No. 4. pp. 1405-1412. https://doi.org/10.5194/hess-20-1405-2016
  47. Tao, H., Hameed, M.M., Marhoon, H.A., Zounemat-Kermani, M., Heddam, S., Kim, S., Sulaiman, S.O., Tan, M.L., Sa'adi, Z., Mehr, A.D., Allawi, M.F., Abba, S.I., Zain, J.M., Falah, M.W., Jamei, M., Bokde, N.D., Bayatvarkeshi, M., Al-Mukhtar, M., Bhagat, S.K., Tiyasha, T., Yaseen, Z.M. (2022). "Groundwater level prediction using machine learning models: A comprehensive review." Neurocomputing, Vol. 489, pp. 271-308. https://doi.org/10.1016/j.neucom.2022.03.014
  48. Yin, J., Medellin-Azuara, J., Escriva-Bou, A., and Liu, Z. (2021). "Bayesian machine learning ensemble approach to quantify model uncertainty in predicting groundwater storage change." Science of The Total Environment, Vol. 769, 144715.