Economic and Environmental Geology (자원환경지질)

The Korean Society of Economic and Environmental Geology (대한자원환경지질학회)
권호 표지
DOI QR코드

DOI QR Code

The Applicability of Conditional Generative Model Generating Groundwater Level Fluctuation Corresponding to Precipitation Pattern

조건부 생성모델을 이용한 강수 패턴에 따른 지하수위 생성 및 이의 활용에 관한 연구

  • Jeong, Jiho (Department of Geology, Kyungpook National University) ;
  • Jeong, Jina (Department of Geology, Kyungpook National University) ;
  • Lee, Byung Sun (Rural Research Institute, Korea Rural Community Corporation) ;
  • Song, Sung-Ho (Rural Research Institute, Korea Rural Community Corporation)
  • 정지호 (경북대학교 지질학과) ;
  • 정진아 (경북대학교 지질학과) ;
  • 이병선 (한국농어촌공사 농어촌연구원) ;
  • 송성호 (한국농어촌공사 농어촌연구원)
  • Received : 2021.01.08
  • Accepted : 2021.01.26
  • Published : 2021.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, a method has been proposed to improve the performance of hydraulic property estimation model developed by Jeong et al. (2020). In their study, low-dimensional features of the annual groundwater level (GWL) fluctuation patterns extracted based on a Denoising autoencoder (DAE) was used to develop a regression model for predicting hydraulic properties of an aquifer. However, low-dimensional features of the DAE are highly dependent on the precipitation pattern even if the GWL is monitored at the same location, causing uncertainty in hydraulic property estimation of the regression model. To solve the above problem, a process for generating the GWL fluctuation pattern for conditioning the precipitation is proposed based on a conditional variational autoencoder (CVAE). The CVAE trains a statistical relationship between GWL fluctuation and precipitation pattern. The actual GWL and precipitation data monitored on a total of 71 monitoring stations over 10 years in South Korea was applied to validate the effect of using CVAE. As a result, the trained CVAE model reasonably generated GWL fluctuation pattern with the conditioning of various precipitation patterns for all the monitoring locations. Based on the trained CVAE model, the low-dimensional features of the GWL fluctuation pattern without interference of different precipitation patterns were extracted for all monitoring stations, and they were compared to the features extracted based on the DAE. Consequently, it can be confirmed that the statistical consistency of the features extracted using CVAE is improved compared to DAE. Thus, we conclude that the proposed method may be useful in extracting a more accurate feature of GWL fluctuation pattern affected solely by hydraulic characteristics of the aquifer, which would be followed by the improved performance of the previously developed regression model.

본 연구에서는 Jeong et al. (2020)의 연구에서 수행된 지하수위 변동 패턴의 저차원 특징추출 과정의 문제점을 분석하고, 이에 대한 개선방안이 제안된다. 해당 연구에서는 Denoising autoencoder (DAE)를 이용해 전국의 연 단위 지하수위 변동 자료로부터 저차원 특징이 추출되며, 추출된 자료를 이용해 대수층의 수리 특성값을 예측하는 회귀 모델이 개발되었다. 그러나 특정 지역의 연도별 강수 패턴이 달라질 경우, 지하수위 변동 패턴 및 저차원 특징 또한 달라지며, 이에 따라 동일 지역임에도 불구하고 저차원 특징으로부터 추정되는 수리 특성값이 다양하게 나타날 수 있다. 이러한 문제를 해결하기 위해, 본 연구에서는 조건부 생성 모델인 Conditional variational autoencoder (CVAE)를 이용하였으며, 전국 71개 지역에서 10년 동안 획득된 지하수위 자료와 강수 자료 간 상관관계가 학습되었다. 학습된 모델을 통해 모든 지역에 대해 동일 강수 조건이 적용될 때의 지하수위 자료가 생성되었으며, 생성된 지하수위 자료로부터 저차원 특징이 추출되었다. CVAE를 이용해 동일 강수 조건으로 생성된 지하수위 자료의 저차원 특징과 기존 DAE를 통해 추출된 저차원 특징이 비교되었으며, 그 결과 CVAE를 이용해 추출된 저차원 특징 간 거리가 저차원 공간상에서 보다 가깝게 분포하는 것이 확인되었다. 따라서 제안된 방법을 이용할 경우 대수층 특성에만 영향을 받는 지역별 지하수위 자료 및 저차원 특징이 효과적으로 추출될 수 있으며, 이를 통해 기존 개발된 회귀 모델의 성능이 개선될 수 있을 것으로 판단된다.

Keywords

Acknowledgement

본 연구는 2020년도 산업통상자원부의 재원으로 한국에너지기술평가원(KETEP)의 지원을 받아 수행한 연구 과제입니다(20193210100130).

References

  1. Adamowski, J. and Chan, H.F. (2011) A wavelet neural network conjunction model for groundwater level forecasting. J. Hydrol., v.407(1-4), p.28-40. https://doi.org/10.1016/j.jhydrol.2011.06.013
  2. Almasri, M.N. and Kaluarachchi, J.J. (2005) Modular neural networks to predict the nitrate distribution inground water using the on-ground nitrate loading and recharge data. Environ. Model. Softw., v.20, p.851-871. https://doi.org/10.1016/j.envsoft.2004.05.001
  3. Bakker and Schaars (2019) Solving Groundwater Flow Problems with Time Series Analysis: You May Not Even Need Another Model. Ground Water, v.57(6), p.826-833. https://doi.org/10.1111/gwat.12927
  4. Bierkens (1998) Modeling water table fluctuations by means of a stochastic differential equation. Water Resour. Res., v.34(10), p.2485-2499. https://doi.org/10.1029/98WR02298
  5. Cooper, J.D., Gardner, C.M.K. and MacKenzie, N. (1990) Soil controls on recharge to aquifers. J. Soil Sci., v.41, p.613-630. https://doi.org/10.1111/j.1365-2389.1990.tb00231.x
  6. 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, v.43(2), p.231-241. https://doi.org/10.1111/j.1745-6584.2005.0003.x
  7. Coulibaly, P., Anctil, F. and Bobee, B. (2001) Multivariate reservoir inflow forecasting using temporal neural networks. J. Hydrol. Eng., v.6(5).
  8. Cuthbert, M.O., Mackay, R., Tellam, J.H. and Thatcher, K.E. (2010) Combining unsaturated and saturated hydraulic observations to understand and estimate groundwater recharge through glacial till. J. Hydrol., v.391(3-4), p.263-276. https://doi.org/10.1016/j.jhydrol.2010.07.025
  9. Delbart, C., Valdes, D., Barbecot, F. and Tognelli, A. (2014) Temporal variability of karst aquifer response time established by the sliding-windows cross-correlation method. J. Hydrol., v.511, p.580-588. https://doi.org/10.1016/j.jhydrol.2014.02.008
  10. Felisa, G., Ciriello, V., Antonellini, M., Federico, V.D. and Tartakovsky, D.M. (2015) Data-driven models of groundwater salinization in coastal plains. J. Hydrol., v.531(1), p.187-197. https://doi.org/10.1016/j.jhydrol.2015.07.045
  11. Han, D., Post, V.E.A. and Song, X. (2015) Groundwater salinization processes and reversibility of seawater intrusion in coastal carbonate aquifers. J. Hydrol., v.531(3), p.1067-1080. https://doi.org/10.1016/j.jhydrol.2015.11.013
  12. Jeong, J. and Park, E. (2017) A shallow water table fluctuation model in response to precipitation with consideration of unsaturated gravitational flow. Water Resour. Res., v.53(4), p.3505-3512. https://doi.org/10.1002/2016WR020177
  13. Jeong, J. and Park, E. (2019) Comparative applications of data-driven models representing water table fluctuations. J. Hydrol., v.572, p.261-273. https://doi.org/10.1016/j.jhydrol.2019.02.051
  14. Jeong. J., Jeong. J., Park. E., Lee, B.S., Song, S.H., Han, W.S. and Chung, S. (2020) Development of an efficient data-driven method to estimate the hydraulic properties of aquifers from groundwater level fluctuation pattern features. J. Hydrol., v.590, 125453. https://doi.org/10.1016/j.jhydrol.2020.125453
  15. Joo, Y., Brumback, B., Lee, K., Yun, S.T., Kim, K.H. and Joo, C. (2009) Clustering of temporal profiles using a bayesian logistic mixture model: analyzing groundwater level data to understand the characteristics of urban groundwater recharge. J. Agric. Biol. Environ. Stat., v.14(3), p.356-373. https://doi.org/10.1198/jabes.2009.07100
  16. Kingma, D.P. and Welling, M. (2014) Auto-encoding Variational Bayes. 2nd International Conference on Learning Representations (ICLR2014) arXiv:1312.6114, v.10.
  17. Knotters, M. and Bierkens, M.F.P. (2000) Physical basis of time series models for water table depth. Water Resour. Res., v.36(1), p.181-188. https://doi.org/10.1029/1999WR900288
  18. Kumar, T. Jeyavel Raja, Balasubramanian, A., Kumar, R.S., Dushiyanthan, C., Tiruneelakandan, B., Suresh, R., Karthikeyan, K. and Davidraju, D. (2016) Assessment of groundwater potential based on aquifer properties of hard rock terrain in the Chittar-Uppodai watershed Tamil Nadu, India. Appl. Water Sci., v.6, p.179-186. https://doi.org/10.1007/s13201-014-0216-4
  19. Lyandres, V. and Briskin S. (1993) On an approach to movingaverage filtering. Signal Process., v.34(2), p.163-178. https://doi.org/10.1016/0165-1684(93)90160-C
  20. Luo, L., Robock, A., Vinnikov, K.Y., Schlosser, C.A., Slater, A.G., Boone, A., Braden, H., Cox, P., Rosnay, P., Dicknison, R.E., Dai, Y., Duan, Q., Etchevers, P., HendersonSellers, A., Gedney, N., Gusev, Y.M., Habets, F., Kim, J., Kowalczyk, E., Mitchell, K., Nasonova, O.N., Noilhan, J., Pitman, A.J., Schaake, J., Shmakin, A.B., Smirnova, T.G., Wetzel, P., Xue, Y., Yang, Z.L. and Zeng, Q.C. (2002) Effects of frozen soil on soil temperature, spring infiltration, and runoff: results from the PILPS 2(d) experiment atvaldai, russia. J. Hydrometeorol., v.4, p.334-351. https://doi.org/10.1175/1525-7541(2003)4<334:EOFSOS>2.0.CO;2
  21. Maggirwar Bhagyashri, C. and Umrikar Bhavana, N. (2011) Influence of various factors on the fluctuation of groundwater level in hard rock terrain and its importance in the assessment of groundwater. J. Geol. Min. Res., v.3(11), p.305-317.
  22. Manzione, R.L. (2017) Physical-based time series model applied on water table depths dynamics characteristics simulation. Rev. Bras. Recur. Hidr., v.23. https://doi.org/10.1590/2318-0331.0318170071
  23. 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 Resour. Manag., v.20(1), p.77-90. https://doi.org/10.1007/s11269-006-4007-z
  24. Neto, D.C., Chang, H.K. and Van genuchten, M. (2015) A Mathematical View of Water Table Fluctuations in a Shallow Aquifer in Brazil. Ground Water, v.54(1), p.82-91.
  25. Nourani, V., Baghanam, A.H., Vousoughi, F.D. and Alami, M.T. (2012) Classification of groundwater level data using SOM to develop ANN-based forecasting model. Int. J. Soft Comp. Eng., v.2(1), p.464-469.
  26. Nourani, V., Alami, M.T. and Vousoughi, F.D. (2015) Waveletentropy data pre-processing approach for ANN-based groundwater level modeling. J. Hydrol., v.524, p.255-269. https://doi.org/10.1016/j.jhydrol.2015.02.048
  27. Park, E. and Parker, J.C. (2008) A simple model for water table fluctuations in response to precipitation. J. Hydrol., v.356(3-4), p.344-349. https://doi.org/10.1016/j.jhydrol.2008.04.022
  28. Price, M., Low, R.G. and McCann, C. (2000) Mechanisms of water storage and flow in the unsaturated zone of chalk aquifer. J. Hydrol. v.233, p.54-71. https://doi.org/10.1016/S0022-1694(00)00222-5
  29. Rai, S.N., Manglik, A. and Singh, V.S. (2006) Water table fluctuation owing to time-varying recharge, pumping and leakage. J. Hydrol., v.324(1-4), p.350-358. https://doi.org/10.1016/j.jhydrol.2005.09.029
  30. Scholkopf, B., Smola, A. and Muller, K-R. (1996) Nonlinear Component Ananysis as a Kernel Eigenvalue Problem., Max-Planck-Institut fur biologische Kybernetik. Technical Report No. 44.
  31. Smith, D.B., Wearn, P.L., Richards, H.J. and Rowe, P.C. (1970) Water movement in the unsaturated zone of high and low permeability strata by measuring natural tritium. IAEA, p.73-87.
  32. Sohn, K., Yan, X. and Lee, H. (2015) Learning structured output representation using deep conditional generative models, In: Proceedings of the Adv. Neural Inf. Process. Syst. NIPS), p.3483-3491.
  33. Welling, S.R. (1984) Recharge of the Upper Chalk aquifer at a site in Hampshire, England: 1. Water balance and unsaturated flow. J. Hydrol., v.69(1-4), p.259-273. https://doi.org/10.1016/0022-1694(84)90166-5
  34. Yeh, H.D. and Huang, Y.C. (2005) Parameter estimation for leaky aquifers using the extended Kalman filter, and considering model and data measurement uncertainties. J. Hydrol., v.302(1-4), p.28-45. https://doi.org/10.1016/j.jhydrol.2004.06.035
  35. Yoon, H., Jun, S., Hyun, Y., Bae, G. and Lee, L. (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J. Hydrol., v.396(1-2), p.128-138. https://doi.org/10.1016/j.jhydrol.2010.11.002