Abstract
The purpose of this study is to develop the feed-forward back-propagation neural network (FFBPNN) to estimate the groundwater level (GL) of next hour according the current GL and past precipitation depth in the hillslope. The 72-h precipitation depth and the real-time groundwater levels are used as the model output layer determination variables. The output variables, are type 1, the GL, which has been used in many researches, and type 2, the groundwater level fluctuation (GLF), which is the difference between the current-time and the next-time groundwater level. The order of the water level fluctuation is less than that of the groundwater level by about one order of magnitude (ten times). The landslide area at the downstream of Wu-She Reservoir, Nantou County, Taiwan, is adopted as a field test area. Total 328 cases of Sinlaku typhoon were used to establish the prediction model of real-time GL. Another 327 cases of Jangmi typhoon were adopted to illustrate the model application. The result of model application shows that root-mean-square error of type 2 (=0.104 m) is smaller than that of type 1 (=0.408 m). In conclusion, the forecasting method used GLF gives a much better agreement with the measured values than that of GL.
This is a preview of subscription content, log in via an institution to check access.
References
Caris JPT, Van Asch TWJ (1991) Geophysical, geotechnical and hydrological investigations of a small landslide in the French Alps. Eng Geol 31(3–4):249–276
Carvalho LM, Jones C, Liebmann B (2002) Extreme precipitation events in southeastern South America and large-scale convective patterns in the South Atlantic convergence zone. J Clim 15(17):2377–2394
Central Weather Bureau (2014) http://www.cwb.gov.tw/V7/climate/monthlyMean/Taiwan_tx.htm (in Chinese)
Coppola E, Anthony JR, Poulton M, Szidarovszky F, Vincent W (2005) A neural network model for predicting aquifer water levels elevations. Groundwater 43(2):231–241
Corominas J, Moya J, Ledesma A, Lloret A, Gili JA (2005) Prediction of ground displacements and velocities from groundwater level changes at the Vallcebre landslide (eastern Pyrenees, Spain). Landslides 2(2):83–96
Coulibaly P, Anctil F, Aravena R, Bobee B (2001) ANN modeling of water table depth fluctuations. Water Resource Research 37:885–896
Daliakopoulos IN, Coulibaly P, Tsanis I (2005) GL forecasting using artificial neural networks. J Hydrol 309:229–240
De Luca DL, Versace P (2017) A comprehensive framework for empirical modeling of landslides induced by rainfall: the Generalized FLaIR Model (GFM). Landslides 14(3):1009–1030
Hong YM, Wan S (2011a) Forecasting GLFs for rainfall-induced landslide. Nat Hazards 57:167–184
Hong YM, Wan S (2011b) An information-based system identification for measurements on GLF of hillslope. Hydrogeol J 19:1335–1149
Demuth H, Beale M, Hagan M (2008) Neural network toolbox™ 6.User’s guide, 37–55
Kantardzic M (2003) Data mining—concepts, models, methods, and algorithms, IEEE. Wiley-interscience, USA, pp 196–217
Krishna B, Satyaji Rao YR, Vijaya T (2008) Modelling GLs in an urban coastal aquifer using artificial neural networks. Hydrol Process 22(8):1180–1188
Kurt H, Maxwell S, Halbert W (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Lee LJE, Lawrence DSL, Price M (2006) Analysis of water-level response to rainfall and implications for recharge pathways in the chalk aquifer, SE England. J Hydrol 330:604–620
Liu HB, Xie DT, Wu W (2008) Soil water content forecasting by ANN and SVM hybrid architecture. Environ Monit Assess 143:187–193
Mantovani F, Pasuto A, Silvano S, Zannoni A (2000) Collecting data to define future hazard scenarios of the Tessina landslide. Int J Appl Earth Obs Geoinf 2(1):33–40
Nayak PC, Satyaji Rao YR, Sudheer KP (2006) GL forecasting in a shallow aquifer using artificial neural network approach. Water Resour Manag 20:77–90
Nourani V, Mogaddam AA, Nadiri AO (2008) An ANN based model for spatiotempral GL forecasting. Hydrol Process 22(26):5054–5066
Park E, Parker JC (2008) A simple model for water table fluctuations in response to precipitation. J Hydrol 356:344–349
Raiman O (1991) Order of magnitude reasoning. Artif Intell 51:11–38
Şenkal O, Yıldız BY, Şahin M, Pestemalcı V (2012) Precipitable water modelling using artificial neural network in Çukurova region. Environ Monit Assess 184(1):141–147
Stephane B, Herve J, Thomas L, Yves G, Emmanuel T, Catherine B, Jacques M (2007) Experimental analysis of groundwater flow through a landslide slip surface using natural and artificial water chemical tracers. Hydrol Process 21(25):3463–3472
Trigo RM, Zêzere JL, Rodrigues ML, Trigo IF (2005) The influence of the North Atlantic Oscillation on rainfall triggering of landslides near Lisbon. Nat Hazards 36:331–354
Van Asch TWJ, Buma J, Van Beek LPH (1999) A view on some hydrological triggering systems in landslides. Geomorphology 30:25–32
Von Asmuth JR, Knotters M (2004) Characterising groundwater dynamics based on a system identification approach. J Hydrol 296:118–134
Zhang, GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50:159–175.
Acknowledgements
The authors gratefully acknowledge Taiwan Power Company and Sinotech Engineering Consultants for providing the experimental field and related supports. The present work was financially supported by the Ministry of Science and Technology, Taiwan. (MOST 105-2313-B-343-002).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hong, YM. Feasibility of using artificial neural networks to forecast groundwater levels in real time. Landslides 14, 1815–1826 (2017). https://doi.org/10.1007/s10346-017-0844-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-017-0844-5