Comparative Study of Hybrid-Wavelet Artificial Intelligence Models for Monthly Groundwater Depth Forecasting in Extreme Arid Regions, Northwest China

Prediction of groundwater depth (GWD) is a critical task in water resources management. In this study, the practicability of predicting GWD for lead times of 1, 2 and 3 months for 3 observation wells in the Ejina Basin using the wavelet-artificial neural network (WA-ANN) and wavelet-support vector regression (WA-SVR) is demonstrated. Discrete wavelet transform was applied to decompose groundwater depth and meteorological inputs into approximations and detail with predictive features embedded in high frequency and low frequency. WA-ANN and WA-SVR relative of ANN and SVR were evaluated with coefficient of correlation (R), Nash-Sutcliffe efficiency (NS), mean absolute error (MAE), and root mean squared error (RMSE). Results showed that WA-ANN and WA-SVR have better performance than ANN and SVR models. WA-SVR yielded better results than WA-ANN model for 1, 2 and 3-month lead times. The study indicates that WA-SVR could be applied for groundwater forecasting under ecological water conveyance conditions.

[1]  Mehdi Vafakhah,et al.  A Wavelet-ANFIS Hybrid Model for Groundwater Level Forecasting for Different Prediction Periods , 2013, Water Resources Management.

[2]  Y. R. Satyaji Rao,et al.  Modelling groundwater levels in an urban coastal aquifer using artificial neural networks , 2008 .

[3]  Jan Adamowski,et al.  Wavelet‐based multiscale performance analysis: An approach to assess and improve hydrological models , 2014 .

[4]  I. Daubechies.  Ten Lectures on Wavelets , 1992 .

[5]  Shashi Mathur,et al.  Optimal design of an in-situ bioremediation system using support vector machine and particle swarm optimization. , 2013, Journal of contaminant hydrology.

[6]  R. Mata-González,et al.  Phreatophytic Vegetation and Groundwater Fluctuations: A Review of Current Research and Application of Ecosystem Response Modeling with an Emphasis on Great Basin Vegetation , 2005, Environmental management.

[7]  R. Deo,et al.  Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model , 2017, Stochastic Environmental Research and Risk Assessment.

[8]  Madan K. Jha,et al.  Efficacy of neural network and genetic algorithm techniques in simulating spatio‐temporal fluctuations of groundwater , 2015 .

[9]  R. Maheswaran,et al.  Wavelet–Volterra coupled model for monthly stream flow forecasting , 2012 .

[10]  J. Lenters,et al.  Quantifying the impact of groundwater depth on evapotranspiration in a semi-arid grassland region , 2009 .

[11]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[12]  F. Boadu.  Rock Properties and Seismic Attenuation: Neural Network Analysis , 1997 .

[13]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[14]  Qi Feng,et al.  Environmental changes after ecological water conveyance in the lower reaches of Heihe River, northwest China , 2009 .

[15]  Q. Feng,et al.  Impacts of river recharge on groundwater level and hydrochemistry in the lower reaches of Heihe River Watershed, northwestern China , 2010 .

[16]  Gwo-Fong Lin,et al.  Improving the forecasts of extreme streamflow by support vector regression with the data extracted by self‐organizing map , 2014 .

[17]  Gabrielle De Lannoy,et al.  Ensemble‐based assimilation of discharge into rainfall‐runoff models: A comparison of approaches to mapping observational information to state space , 2009 .

[18]  Pradeep Kurup,et al.  Neural Networks for Profiling Stress History of Clays from PCPT Data , 2002 .

[19]  Raja Muhammad Asif Zahoor,et al.  Design of stochastic solvers based on genetic algorithms for solving nonlinear equations , 2014, Neural Computing and Applications.

[20]  Rathinasamy Maheswaran,et al.  Long term forecasting of groundwater levels with evidence of non-stationary and nonlinear characteristics , 2013, Comput. Geosci..

[21]  Michael E. Schaepman,et al.  Correlation Between Annual Runoff in the Heihe River to the Vegetation Cover in the Ejina Oasis (China) , 2010 .

[22]  Yan-Fang Sang,et al.  A Practical Guide to Discrete Wavelet Decomposition of Hydrologic Time Series , 2012, Water Resources Management.

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

[24]  K. Davary,et al.  Application of NN-ARX Model to Predict Groundwater Levels in the Neishaboor Plain, Iran , 2013, Water Resources Management.

[25]  K. P. Sudheer,et al.  Using Artificial Neural Network Approach for Simultaneous Forecasting of Weekly Groundwater Levels at Multiple Sites , 2015, Water Resources Management.

[26]  Paresh Chandra Deka,et al.  Discrete wavelet neural network approach in significant wave height forecasting for multistep lead time , 2012 .

[27]  C. Colvin,et al.  A review of information on interactions between vegetation and groundwater , 1999 .

[28]  Paulin Coulibaly,et al.  Nonstationary hydrological time series forecasting using nonlinear dynamic methods , 2005 .

[29]  J. Adamowski,et al.  A wavelet neural network conjunction model for groundwater level forecasting , 2011 .

[30]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[31]  Ping Wang,et al.  Vegetation responses to integrated water management in the Ejina basin, northwest China , 2011 .

[32]  Jan Adamowski,et al.  Multiscale streamflow forecasting using a new Bayesian Model Average based ensemble multi-wavelet Volterra nonlinear method , 2013 .

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

[34]  F. Qi,et al.  Major ion chemistry of groundwater in the extreme arid region northwest China , 2009 .

[35]  Jun Wu,et al.  Wavelet and adaptive neuro-fuzzy inference system conjunction model for groundwater level predicting in a coastal aquifer , 2014, Neural Computing and Applications.

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

[37]  C. Jiansheng.  Study of Groundwater Supply of the Confined Aquifers in the Ejin Basin Based on Isotopic Methods , 2004 .

[38]  Jeffrey G. Arnold,et al.  HYDROLOGIC SIMULATION ON AGRICULTURAL WATERSHEDS: CHOOSING BETWEEN TWO MODELS , 2003 .

[39]  Bijaya K. Panigrahi,et al.  An integrated wavelet-support vector machine for groundwater level prediction in Visakhapatnam, India , 2014, Neurocomputing.

[40]  Mahesh Pal,et al.  Support vector machines‐based modelling of seismic liquefaction potential , 2006 .

[41]  Matthew A. Wilson,et al.  Neural Representation of Spatial Topology in the Rodent Hippocampus , 2013, Neural Computation.

[42]  Rathinasamy Maheswaran,et al.  Comparative study of different wavelets for hydrologic forecasting , 2012, Comput. Geosci..

[43]  Ping Wang,et al.  Impacts of environmental flow controls on the water table and groundwater chemistry in the Ejina Delta, northwestern China , 2011 .

[44]  Jing Su,et al.  Hydrochemical characteristics and salinity of groundwater in the Ejina Basin, Northwestern China , 2005 .

[45]  J. Arnold,et al.  VALIDATION OF THE SWAT MODEL ON A LARGE RWER BASIN WITH POINT AND NONPOINT SOURCES 1 , 2001 .

[46]  K. P. Sudheer,et al.  Artificial Neural Network Modeling for Groundwater Level Forecasting in a River Island of Eastern India , 2010 .

[47]  Q. Feng,et al.  Distribution and evolution of water chemistry in Heihe River basin , 2004 .

[48]  Emery Coppola,et al.  Comparative Study of SVMs and ANNs in Aquifer Water Level Prediction , 2010, J. Comput. Civ. Eng..

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

[50]  Jeffrey G. Arnold,et al.  Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations , 2007 .

[51]  Murat Kankal,et al.  Estimation of suspended sediment concentration from turbidity measurements using artificial neural networks , 2012, Environmental Monitoring and Assessment.

[52]  Mary P. Anderson,et al.  Applied groundwater modeling - simulation of flow and advective transport (4. pr.) , 1991 .

[54]  Wensheng Wang,et al.  Wavelet Network Model and Its Application to the Prediction of Hydrology , 2003 .

[55]  J. Adamowski.  Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis , 2008 .

[56]  Gwo-Fong Lin,et al.  Effective forecasting of hourly typhoon rainfall using support vector machines , 2009 .

[57]  A. K. Lohani,et al.  Comparative study of neural network, fuzzy logic and linear transfer function techniques in daily rainfall‐runoff modelling under different input domains , 2011 .

[58]  M. Sadeghi,et al.  Application of “panel-data” modeling to predict groundwater levels in the Neishaboor Plain, Iran , 2012, Hydrogeology Journal.

[59]  J. Shao,et al.  The Role of Ground Water in Arid/Semiarid Ecosystems, Northwest China , 2005, Ground water.

[60]  Evdokia Tapoglou,et al.  A spatio-temporal hybrid neural network-Kriging model for groundwater level simulation , 2014 .