Spatiotemporal groundwater level modeling using hybrid artificial intelligence-meshless method

Summary Uncertainties of the field parameters, noise of the observed data and unknown boundary conditions are the main factors involved in the groundwater level (GL) time series which limit the modeling and simulation of GL. This paper presents a hybrid artificial intelligence-meshless model for spatiotemporal GL modeling. In this way firstly time series of GL observed in different piezometers were de-noised using threshold-based wavelet method and the impact of de-noised and noisy data was compared in temporal GL modeling by artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). In the second step, both ANN and ANFIS models were calibrated and verified using GL data of each piezometer, rainfall and runoff considering various input scenarios to predict the GL at one month ahead. In the final step, the simulated GLs in the second step of modeling were considered as interior conditions for the multiquadric radial basis function (RBF) based solve of governing partial differential equation of groundwater flow to estimate GL at any desired point within the plain where there is not any observation. In order to evaluate and compare the GL pattern at different time scales, the cross-wavelet coherence was also applied to GL time series of piezometers. The results showed that the threshold-based wavelet de-noising approach can enhance the performance of the modeling up to 13.4%. Also it was found that the accuracy of ANFIS-RBF model is more reliable than ANN-RBF model in both calibration and validation steps.

[1]  Frank T.-C. Tsai,et al.  Bayesian model averaging for groundwater head prediction and uncertainty analysis using multimodel and multimethod , 2009 .

[2]  Dong Wang,et al.  The relation between periods’ identification and noises in hydrologic series data , 2009 .

[3]  T. Eldho,et al.  Groundwater flow simulation in unconfined aquifers using meshless local Petrov–Galerkin method , 2014 .

[4]  R. E. Carlson,et al.  The parameter R2 in multiquadric interpolation , 1991 .

[5]  Vahid Nourani,et al.  Integration of Artificial Neural Networks with Radial Basis Function Interpolation in Earthfill Dam Seepage Modeling , 2013, J. Comput. Civ. Eng..

[6]  Jun Guo,et al.  Monthly streamflow forecasting based on improved support vector machine model , 2011, Expert Syst. Appl..

[7]  Vahid Nourani,et al.  A geomorphology-based ANFIS model for multi-station modeling of rainfall–runoff process , 2013 .

[8]  Y. C. Hon,et al.  Boundary knot method for 2D and 3D Helmholtz and convection–diffusion problems under complicated geometry , 2003 .

[9]  Aslak Grinsted,et al.  Nonlinear Processes in Geophysics Application of the Cross Wavelet Transform and Wavelet Coherence to Geophysical Time Series , 2022 .

[10]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.

[11]  I. Babuska,et al.  The Partition of Unity Method , 1997 .

[12]  B. Bobée,et al.  Artificial neural network modeling of water table depth fluctuations , 2001 .

[13]  Kamal Djidjeli,et al.  Thin-plate spline radial basis function scheme for advection-diffusion problems , 2002 .

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  Kwok-wing Chau,et al.  Improving Forecasting Accuracy of Annual Runoff Time Series Using ARIMA Based on EEMD Decomposition , 2015, Water Resources Management.

[16]  K. Hoffmann,et al.  Computational Fluid Dynamics for Engineers , 1989 .

[17]  Vahid Nourani,et al.  Wavelet-entropy data pre-processing approach for ANN-based groundwater level modeling , 2015 .

[18]  Kwok-wing Chau,et al.  Neural network river forecasting with multi-objective fully informed particle swarm optimization , 2015 .

[19]  Özgür Kisi,et al.  Modeling rainfall-runoff process using soft computing techniques , 2013, Comput. Geosci..

[20]  Oden,et al.  An h-p adaptive method using clouds , 1996 .

[21]  Vahid Nourani,et al.  Wavelet Based Artificial Intelligence Approaches for Prediction of Hydrological Time Series , 2015, ACALCI.

[22]  Özgür Kisi,et al.  Predicting groundwater level fluctuations with meteorological effect implications - A comparative study among soft computing techniques , 2013, Comput. Geosci..

[23]  R. E. Carlson,et al.  Improved accuracy of multiquadric interpolation using variable shape parameters , 1992 .

[24]  J. Bear.  Hydraulics of Groundwater , 1979 .

[25]  R. L. Hardy.  Multiquadric equations of topography and other irregular surfaces , 1971 .

[26]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[27]  Zi Li,et al.  Global multiquadric collocation method for groundwater contaminant source identification , 2011, Environ. Model. Softw..

[28]  C. L. Wu,et al.  Methods to improve neural network performance in daily flows prediction , 2009 .

[29]  Vahid Nourani,et al.  A Multivariate ANN-Wavelet Approach for Rainfall–Runoff Modeling , 2009 .

[30]  Catie Chang,et al.  Time–frequency dynamics of resting-state brain connectivity measured with fMRI , 2010, NeuroImage.

[31]  R. Wyatt,et al.  Radial basis function interpolation in the quantum trajectory method: optimization of the multi-quadric shape parameter , 2003 .

[32]  Ozgur Kisi,et al.  Global cross-station assessment of neuro-fuzzy models for estimating daily reference evapotranspiration , 2013 .

[33]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[34]  Wing Kam Liu,et al.  Reproducing kernel particle methods , 1995 .

[35]  Vahid Nourani,et al.  Evaluation of Wavelet-Based De-noising Approach in Hydrological Models Linked to Artificial Neural Networks , 2014 .

[36]  R. L. Hardy.  Theory and applications of the multiquadric-biharmonic method : 20 years of discovery 1968-1988 , 1990 .

[37]  E. Kansa.  MULTIQUADRICS--A SCATTERED DATA APPROXIMATION SCHEME WITH APPLICATIONS TO COMPUTATIONAL FLUID-DYNAMICS-- II SOLUTIONS TO PARABOLIC, HYPERBOLIC AND ELLIPTIC PARTIAL DIFFERENTIAL EQUATIONS , 1990 .

[38]  Y. Chen,et al.  Mesh-free method for groundwater modeling , 2002 .

[39]  M. Golberg,et al.  Improved multiquadric approximation for partial differential equations , 1996 .

[40]  null null,et al.  Artificial Neural Networks in Hydrology. II: Hydrologic Applications , 2000 .

[41]  Vahid Nourani,et al.  An ANN‐based model for spatiotemporal groundwater level forecasting , 2008 .

[42]  B. Fornberg,et al.  A numerical study of some radial basis function based solution methods for elliptic PDEs , 2003 .

[43]  Linda See,et al.  Data preprocessing for river flow forecasting using neural networks: Wavelet transforms and data partitioning , 2006 .

[44]  Hyun Gyu Kim,et al.  A critical assessment of the truly Meshless Local Petrov-Galerkin (MLPG), and Local Boundary Integral Equation (LBIE) methods , 1999 .

[45]  Chuen-Tsai Sun,et al.  Neuro-fuzzy And Soft Computing: A Computational Approach To Learning And Machine Intelligence [Books in Brief] , 1997, IEEE Transactions on Neural Networks.

[46]  T. I. Eldho,et al.  Two-dimensional contaminant transport modeling using meshfree point collocation method (PCM) , 2012 .

[47]  Ozgur Kisi,et al.  Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review , 2014 .

[48]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .