Modular neural networks to predict the nitrate distribution in ground water using the on-ground nitrogen loading and recharge data

Abstract Artificial neural networks have proven to be an attractive mathematical tool to represent complex relationships in many branches of hydrology. Due to this attractive feature, neural networks are increasingly being applied in subsurface modeling where intricate physical processes and lack of detailed field data prevail. In this paper, a methodology using modular neural networks (MNN) is proposed to simulate the nitrate concentrations in an agriculture-dominated aquifer. The methodology relies on geographic information system (GIS) tools in the preparation and processing of the MNN input–output data. The basic premise followed in developing the MNN input–output response patterns is to designate the optimal radius of a specified circular-buffered zone centered by the nitrate receptor so that the input parameters at the upgradient areas correlate with nitrate concentrations in ground water. A three-step approach that integrates the on-ground nitrogen loadings, soil nitrogen dynamics, and fate and transport in ground water is described and the critical parameters to predict nitrate concentration using MNN are selected. The sensitivity of MNN performance to different MNN architecture is assessed. The applicability of MNN is considered for the Sumas-Blaine aquifer of Washington State using two scenarios corresponding to current land use practices and a proposed protection alternative. The results of MNN are further analyzed and compared to those obtained from a physically-based fate and transport model to evaluate the overall applicability of MNN.

[1]  M. Yavuz Corapcioglu,et al.  Modeling the Effect of Chemical Fertilizers on Ground Water Quality in the Nile Valley Aquifer, Egypt , 2001 .

[2]  Holger R. Maier,et al.  Understanding the behaviour and optimising the performance of back-propagation neural networks: an empirical study , 1998 .

[3]  Linda Jeanette Arnade,et al.  Seasonal Correlation of Well Contamination and Septic Tank Distance , 1999 .

[4]  David V. Stasney.  Hydrostratigraphy, groundwater flow, and nitrate transport within the Abbotsford Sumas aquifer, Whatcom County, Washington , 2000 .

[5]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[6]  Richard C. Peralta,et al.  Optimal design of aquifer cleanup systems under uncertainty using a neural network and a genetic algorithm , 1999 .

[7]  L. Nanus,et al.  Nitrate distributions and source identification in the Abbotsford-Sumas Aquifer, northwestern Washington State. , 2003, Journal of environmental quality.

[8]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[9]  John F. Devlin,et al.  The effects of electron donor and granular iron on nitrate transformation rates in sediments from a municipal water supply aquifer , 2000 .

[10]  R. K. Hubbard,et al.  Nitrates in groundwater in the southeastern USA , 1994 .

[11]  Jagath J. Kaluarachchi,et al.  Assessment and management of long-term nitrate pollution of ground water in agriculture-dominated watersheds , 2004 .

[12]  L. L. Rogers,et al.  Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling , 1994 .

[13]  W. Kinzelbach.  Applied groundwater modeling — Simulation of flow and advective transport , 1992 .

[14]  T. Skaggs,et al.  Recovering the release history of a groundwater contaminant , 1994 .

[15]  S. Korom.  Natural denitrification in the saturated zone: a review , 1992 .

[16]  David L. Lorenz,et al.  Estimation of nitrate contamination of an agro-ecosystem outwash aquifer using a nitrogen mass-balance budget , 1999 .

[17]  B. Nolan,et al.  Nutrients in groundwaters of the conterminous United States, 1992-1995. , 2000 .

[18]  Sven Kralisch,et al.  A neural network approach for the optimisation of watershed management , 2003, Environ. Model. Softw..

[19]  L. Tianhong,et al.  Integration of large scale fertilizing models with GIS using minimum unit , 2003, Environ. Model. Softw..

[20]  Jagath J. Kaluarachchi,et al.  Application of artificial neural network and genetic algorithm in flow and transport simulations , 1998 .

[21]  Stephen E. Cox,et al.  Ground-water quality data from the Abbotsford-Sumas aquifer of southwestern British Columbia and northwestern Washington State, February 1997 , 1999 .

[22]  J. Jager,et al.  Odour monitoring by the combination of sensores and neural networks , 1999, Environ. Model. Softw..

[23]  Arthur J. Gold,et al.  Influence of Overwatering and Fertilization on Nitrogen Losses from Home Lawns , 1988 .

[24]  François Anctil,et al.  Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting models , 2004, Environ. Model. Softw..

[25]  J. J. Vaccaro,et al.  Hydrogeologic Framework of the Puget Sound Aquifer System, Washington and British Columbia , 1998 .

[26]  Emil O. Frind,et al.  Modeling of multicomponent transport with microbial transformation in groundwater: The Fuhrberg Case , 1990 .

[27]  Jean-François Mas,et al.  Modelling deforestation using GIS and artificial neural networks , 2004, Environ. Model. Softw..

[28]  Virginia M. Johnson,et al.  Accuracy of Neural Network Approximators in Simulation-Optimization , 2000 .

[29]  Jagath J. Kaluarachchi,et al.  IMPLICATIONS OF ON‐GROUND NITROGEN LOADING AND SOIL TRANSFORMATIONS ON GROUND WATER QUALITY MANAGEMENT 1 , 2004 .

[30]  B. L. Howes,et al.  Nitrogen transport and transformations in a shallow aquifer receiving wastewater discharge: A mass balance approach , 1998 .

[31]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[32]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

[33]  F. Gümrah,et al.  The Application of Artificial Neural Networks for the Prediction of Water Quality of Polluted Aquifer , 2000 .

[34]  W. Alley.  Regional ground-water quality , 1993 .

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

[36]  B. P. McGrail.  Inverse reactive transport simulator (INVERTS): an inverse model for contaminant transport with nonlinear adsorption and source terms , 2001, Environ. Model. Softw..

[37]  Thomas Harter,et al.  Shallow groundwater quality on dairy farms with irrigated forage crops. , 2002, Journal of contaminant hydrology.

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

[39]  A. Olness,et al.  Farming, Fertilizers and the Nitrate Problem , 1993 .

[40]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[41]  Lars Prange,et al.  Non-point source critical area analysis in the Gisselö watershed using GIS , 2003, Environ. Model. Softw..

[42]  Slobodan P. Simonovic,et al.  Short term streamflow forecasting using artificial neural networks , 1998 .

[43]  Arlen W. Harbaugh,et al.  User's documentation for MODFLOW-96, an update to the U.S. Geological Survey modular finite-difference ground-water flow model , 1996 .

[44]  Virginia M. Johnson,et al.  Location Analysis in Ground‐Water Remediation Using Neural Networks , 1995 .

[45]  Chandra A. Madramootoo,et al.  Modeling nitrate leaching using neural networks , 1998 .

[46]  Istvan Bogardi,et al.  Nitrate Risk Management under Uncertainty , 1992 .

[47]  D. Postma,et al.  Nitrate Reduction in an Unconfined Sandy Aquifer: Water Chemistry, Reduction Processes, and Geochemical Modeling , 1991 .

[48]  Robert Flynn,et al.  Manure Best Management practices , 1999 .

[49]  Luke E. K. Achenie,et al.  Estimation of aquifer hydraulic conductivities: a neural network approach , 1995 .

[50]  I. P. Murarka,et al.  Contamination of Groundwaters , 1994 .

[51]  F. Voss,et al.  Predicting the Probability of Elevated Nitrate Concentrations in the Puget Sound Basin: Implications for Aquifer Susceptibility and Vulnerability , 1997 .

[52]  Keith E. Schilling,et al.  Contribution of Base Flow to Nonpoint Source Pollution Loads in an Agricultural Watershed , 2001 .

[53]  J. Eheart,et al.  Neural network-based screening for groundwater reclamation under uncertainty , 1993 .

[54]  P. Bedient,et al.  Ground Water Contamination: Transport and Remediation , 1994 .

[55]  N. Null.  Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[56]  E A Sudicky,et al.  Numerical simulation of a fine-grained denitrification layer for removing septic system nitrate from shallow groundwater. , 2001, Journal of contaminant hydrology.

[57]  Chittaranjan Ray,et al.  NEURAL NETWORKS FOR AGRICHEMICAL VULNERABILITY ASSESSMENT OF RURAL PRIVATE WELLS , 2000 .

[58]  A. Tesoriero,et al.  Mechanism and rate of denitrification in an agricultural watershed: Electron and mass balance along groundwater flow paths , 2000 .

[59]  Sharon Gelinas.  An exploratory statistical analysis of the ground water in the Abbotsford-Sumas aquifer , 2000 .

[60]  Rao S. Govindaraju,et al.  Prediction of watershed runoff using Bayesian concepts and modular neural networks , 2000 .

[61]  J. Kaluarachchi,et al.  Parameter estimation using artificial neural network and genetic algorithm for free‐product migration and recovery , 1998 .

[62]  S. Fletcher,et al.  Evaluating factors influencing groundwater vulnerability to nitrate pollution: developing the potential of GIS. , 2003, Journal of environmental management.

[63]  Aly I. El-Kadi,et al.  A lumped parameter model for nitrogen transformation in the unsaturated zone , 1998 .

[64]  W. Showers,et al.  Application of classification-tree methods to identify nitrate sources in ground water. , 2002, Journal of environmental quality.

[65]  Sue C. Kahle,et al.  Hydrogeology, ground-water quality, and sources of nitrate in lowland glacial aquifers of Whatcom County, Washington, and British Columbia, Canada , 1999 .

[66]  B. Ruddy,et al.  Probability of nitrate contamination of recently recharged groundwaters in the conterminous United States. , 2002, Environmental science & technology.

[67]  Y. Pachepsky,et al.  Artificial Neural Networks to Estimate Soil Water Retention from Easily Measurable Data , 1996 .

[68]  Jonathan A. Patz,et al.  Reactive Nitrogen and Human Health:Acute and Long-term Implications , 2002, Ambio.

[69]  Markus Hoffmann,et al.  SOILNDB: a decision support tool for assessing nitrogen leaching losses from arable land , 2002, Environ. Model. Softw..

[70]  Paul P. Wang,et al.  MT3DMS: A Modular Three-Dimensional Multispecies Transport Model for Simulation of Advection, Dispersion, and Chemical Reactions of Contaminants in Groundwater Systems; Documentation and User's Guide , 1999 .

[71]  Michael Georgiopoulos,et al.  Applications of Neural Networks in Electromagnetics , 2001 .

[72]  D. M. Jansen,et al.  Ex-ante assessment of costs for reducing nitrate leaching from agriculture-dominated regions , 1999, Environ. Model. Softw..

[73]  J. Schepers,et al.  Controlling nitrate leaching in irrigated agriculture. , 2001, Journal of environmental quality.

[74]  Paul F. Hudak,et al.  Regional trends in nitrate content of Texas groundwater. , 2000 .

[75]  Reimund P. Rötter,et al.  The integrated modeling system STONE for calculating nutrient emissions from agriculture in the Netherlands , 2003, Environ. Model. Softw..