Implementation of Data Jittering Technique for Seepage Analysis of Earth fill Dam Using Ensemble of AI Models

Authors

Department of Water Resources Engineering, Faculty of Civil Engineering, University of Tabriz, Tabriz, Iran

Abstract

Recently, it has been shown that Artificial Intelligence (AI) methods such as Feed forward neural network and Support vector regression have great capability in modeling of non-linear hydraulic time series. AI methods offer effective approaches for handling large amounts of dynamic, non-linear and noisy data. Hence in this paper, seepage of Sattarkhan earth fill dam using two AI models of Feed forward neural network and Support vector regression was simulated, based on 2 scenarios with different combination of inputs. Afterwards, as a pre-processing method for improving the model performance, normally distributed noises with the mean of zero and various standard deviations were generated and added to the time series to form different jittered training data sets, for AI modeling of seepage. Further, as another method for improving the model performance, an ensemble post-processing model was developed using outputs of sole models. Non-linear neural averaging method was considered for model ensembling. The obtained results indicated that simultaneous application of the both jittering and model ensembling methods improved the model accuracy up to 32% in the verification step.

Keywords

References

Barzegar R, Asghari Moghaddam A and Fijani E, 2019. Forecasting monthly water level fluctuations of Lake Urmia using supervised committee machine artificial intelligence model. Water and Soil Science-University of Tabriz 29(1): 165-177. (In Persian)
Bates JM and Granger CWJ, 1969. The combination of forecasts. Operational Research Quarterly 20: 451–468.
Cortes C and Vapnik V, 1995. Support-vector networks. Machine Learning 20: 273-297.
Emami S, Arvanaghi H and Parsa J, 2017. Forcasting of seepage from body of earthfill dam using artificial neural network (Case study: Shahid Kazemi Boukan dam). Journal of Dam and Hydroelectric PowerPlant 14: 24-34. (In Persian)
Eskandari A, Solgi A and Zarei H, 2018. Simulating fluctuations of groundwater level using combination of support vector machine and wavelet transform. Irrigation Sciences and Engineering 41(1): 165-180. (In Persian)
Hornik K, Stinchcombe M and White H, 1989. Multilayer feedforward networks are universal approximators. Neural Networks 2(5): 359-66.
Liu Y and Pender G, 2015. A flood inundation modeling using v-support vector machine regression model. Engineering Applications of Artificial Intelligence 46: 223–231.
Moayeri MM, Nikpoor R, Hoseinzadeh Dalir A and Farsadizadeh D, 2009. Comparison of artificial neural networks, adaptive neuro-fuzzy and sediment rating curve models for estimating suspended sediment load of Ajichay River. Water and Soil Science-University of Tabriz 20(2): 71-82. (In Persian)
Noori R, Karbassi AR and Moghaddamnia A, 2011. Assessment of input variables determination on the SVM model performance using PCA, gamma test and forward selection techniques for monthly stream flow prediction. Journal of Hydrology 401: 177–189.
Nourani V, 2015. Basics of Hydroinformatics. Tabriz University Press. (In Persian)
Nourani V and Partoviyan A, 2017. Hybrid denoising-jittering data pre-processing approach to enhance multi-step-ahead rainfall–runoff modeling. Stochastic Environmental Research and Risk Assessment 1-18.
Nourani V, Sharghi E and Aminfar MH, 2012. Integrated ANN model for earthfill dams seepage analysis: Sattarkhan Dam in Iran. Artificial Intelligence Research 1(2): 22-37.
Shamseldin AY, O’Connor KM and Liang GC, 1997. Methods for combining the outputs of different rainfall-runoff models. Journal of Hydrology 197: 203-229.
Tayfure G, Swiatek D, Wita A and Singh VP, 2005. Case study: finite element method and artificial neural network models for flow through Jeziorsko earthfill dam in Poland. Journal of Hydraulic Engineering 131(6): 431–440.
Vafaeian M, 2015. Earth Dams & Rockfill Dams. Arkan Danesh, Isfahan. (In Persian)
Yongbiao L, 2012. Prediction methods to determine stability of dam if there is piping. IERI Procedia 1: 131-137.
Yeganeh Fard M and Zahabiyoun B, 2014. Artificial flow production using artificial neural networks. Amirkabir Journal of Science & Research 46(1): 1-10. (In Persian)
Zhang GP, 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50: 159–175.
Zhang GP, 2007. A neural network ensemble method with jittered training data for time series forecasting. Information Sciences 177: 5329–5346.
Zhang LM, Xu Y and Jia JS, 2009. Analysis of earth dam failures: A database approach. Georisk 3(3): 184-189.
Water and Soil Science
Volume 30, Issue 1
May 2020
Pages 29-41

Files

Share

How to cite

Statistics