Neural Networks for Agrichemical Vulnerability Assessment of Rural Private Wells
Publication: Journal of Hydrologic Engineering
Volume 5, Issue 2
Abstract
Assessment of pesticide and nitrate contamination of rural private wells was conducted using artificial neural networks. Data from 192 drilled and driven wells and 115 large-diameter dug and bored wells, available from two earlier studies, were used for training and testing purposes. Four separate models, two for the two well types and one each for pesticide and nitrate, were developed. Parameters such as depth to aquifer material from land surface, well depth, and distance to cropland were used as input parameters, and the concentrations of nitrate or pesticides were the outputs. While the training efficiency of the network reached between 95 and 100% for these four models, the prediction accuracy for the four models ranged from a low of slightly above 50% for nitrate in dug and bored wells to a high of 90% for pesticides in drilled and driven wells. Sensitivity analyses were performed to examine the impact of network architecture, training and testing parameters, and the size and type of input parameters on model predictions. Multiple hidden layers with a large number of nodes did not appear to have a significant impact on model predictions in two of the four models. The relative importance of input parameters was tested by adding or removing certain key parameters to the model, and it was observed that the parameters had a different impact on drilled/driven versus dug/bored wells.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Balu, K., Cheplick, J. M., Holden, P. W., and Seidmann, R. H. ( 1995). “Summary of Ciba/State ground-water monitoring study for atrazine and its major degradation products in the United States with emphasis on data interpretation using a PC-based geographic information system.” Preprint of Paper Presented at 209th Am. Chemical Soc. Nat. Meeting, Washington, D.C., 294–297.
2.
Balu, K., Holden, P. W., and Johnson, L. C. ( 1996). “Summary of Ciba/State ground-water monitoring study for atrazine and its degradation products in the United States.” Paper Presented at Am. Chemical Soc. Nat. Meeting, Washington, D.C.
3.
Basheer, I. A., Reddi, L. N., and Najjar, Y. M. (1996). “Site characterization by neuronets: An application to the landfill siting problem.” Ground Water, 34, 610–617.
4.
Burkart, M. R, and Kolpin, D. W. (1993). “Hydrologic and land-use factors associated with herbicides and nitrate in near-surface aquifers.” J. Envir. Quality, 22, 646–656.
5.
Carsel, R. F., Smith, C. N., Mulkey, L. A., Dean, J. D., and Jowsie, P. (1984). “Pesticide root zone model (PRZM).” Release 1, EPA-600/3-84-109, U.S. Environmental Protection Agency, Washington, D.C.
6.
Fausett, L. (1994). Fundamentals of neural networks: Architectures, Algorithms, and Applications. Prentice-Hall, Englewood Cliffs, N.J.
7.
Goetsch, W. D., McKenna, D. P., and Bicki, T. J. (1992). “Statewide survey for agricultural chemicals in rural, private water-supply wells in Illinois.” Illinois Department of Agriculture, Springfield, Ill.
8.
Habiballah, W. A., Startzman, R. A., and Barrufet, M. A. (1996). “Use of neural networks for prediction of vapor/liquid equilibrium k values for light-hydrocarbon mixtures.” SPE Reservoir Engrg., (May), 121–126.
9.
Haykin, S. (1994). Neural networks: A comprehensive foundation. Macmillan, New York.
10.
Holden, L. R., et al. (1992). “Results of the national alachlor well water survey.” Envir. Sci. and Technol., 26, 935–946.
11.
Holden, L. R., and Graham, J. A. (1990). “The national alachlor well water survey: Project summary.” Monsanto Agricultural Company, St. Louis, Mo.
12.
Hsu, K.-L., Gupta, H. V., and Soroosian, S. (1995). “Artificial neural network modeling of the rainfall-runoff process.” Water Resour. Res., 31, 2517–2530.
13.
Kao, J.-J. (1996). “Neural net for determining DEM-based model drainage pattern.”J. Irrig. and Drain. Engrg., ASCE, 122(2), 112–121.
14.
Karny, J. R., Panczak, K. A., Wilson, S. D., and Hlinka, K. J. (1993). “Agricultural chemical contamination of shallow bored and dug wells.” Proc., 3rd Annu. Conf. Res. on Agric. Chemicals in Illinois Ground Water: Status and Future Dir. III, Southern Illinois University, Carbondale, Ill.
15.
Keefer, D. A. ( 1995). “Potential for agricultural chemical contamination of aquifers in Illinois: 1995 revision.” Environmental geology 148, Illinois State Geological Survey, Champaign, Ill.
16.
Khanna, T. (1990). Foundations of neural networks. Addison-Wesley, Reading, Mass.
17.
Klaseus, T. G., Buzicky, G. C., and Schneider, E. C. (1988). “Pesticides and groundwater: Survey of selected Minnesota wells.” Minnesota Department of Health and Agriculture, St. Paul, Minn.
18.
Klaseus, T. G., and Hines, J. W. (1989). “Pesticides and groundwater: Survey of selected private wells in Minnesota.” Minnesota Department of Health, St. Paul, Minn.
19.
Knisel, W. G. (1993). GLEAMS: Groundwater loading effects of agricultural management systems, Version 2.10. University of Georgia Coastal Plain Experiment Station, Tifton, Ga.
20.
Kolpin, D. W., Burkart, M. R., and Thurman, E. M. (1993). “Hydrogeologic, water quality, and land-use data for the reconnaissance of herbicides and nitrate in near-surface aquifers of the midcontinental United States, 1991.” U.S. Geological Survey Open-File Rep., U.S. Geological Survey, Menlo Park, Calif.
21.
Kolpin, D. W., Burkart, M. R., and Thurman, E. M. ( 1994). “Herbicides and nitrates in near-surface aquifers in the midcontinental United States, 1991.” U.S. Geological Survey Water Supply Paper 2413, U.S. Government Printing Office, Washington, D.C.
22.
Kolpin, D. W., Thurman, E. M., and Goolsby, D. A. (1996). “Occurrence of selected pesticides and their metabolites in near-surface aquifers of the Midwestern United States.” Envir. Sci. and Technol., 30, 335–350.
23.
Maier, H. R., and Dandy, G. C. (1996). “The use of artifical neural networks for the prediction of water quality parameters.” Water Resour. Res., 32, 1013–1022.
24.
“National pesticide survey: Phase I report.” (1990). EPA 570/9-90-015, Environmental Protection Agency, Washington, D.C.
25.
“Pesticides in ground water database: A compilation of monitoring studies: 1971–91.” (1992). EPA 734/12/-92-001, Environmental Protection Agency, Washington, D.C.
26.
Ray, C., and Schock, S. C. (1996). “Comparability of large-scale studies of agricultural chemical contamination of rural private wells.” Ground Water Monitoring and Remediation, 16(Spring), 92–102.
27.
“Root zone water quality model (RZQM) Volume 1.0. Technical documentation.” GSPR Rep. 2, U.S. Department of Agriculture-ARS Great Plains Systems Research Unit, Fort Collins, Colo.
28.
Rummelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Parallel distributed processing: Explorations in the microstructure of cognition, I, D. E. Rummelhart and J. L. McClelland, eds., MIT Press, Cambridge, Mass.
29.
Sarle, W. S. ( 1994). “Neural networks and statistical models.” Paper Presented at 19th Annu. SAS Users Group Int. Conf., SAS Institute, Cary, N. C., ftp://ftp.sas.com/pub/sugi19/neural/neural1.ps.
30.
Schaap, M. G., and Bouten, W. (1996). “Modeling water retention curves of sandy soils using neural networks.” Water Resour. Res., 32, 3033–3040.
31.
Schock, S. C., et al. (1992). “Pilot study: Agricultural chemicals in rural, private wells in Illinois.” Cooperative Ground Water Rep. 14, Department of Energy and Natural Resources, Springfield, Ill.
32.
Shamseldin, A. Y. (1997). “Application of a neural network technique to rainfall-runoff modeling.” J. Hydr., 199, 272–294.
33.
Shukla, M. B., Kok, R., Prasher, S. O., Clark, G., and Lacroix, R. ( 1996). “Use of artificial neural networks in transient drainage design.” Trans., ASAE, 39, 119–124.
34.
“State soil geographic database (STATSGO).” (1991). Miscellaneous Publ. No. 1492, U.S. Department of Agriculture, Soil Conservation Service, Washington, D.C.
35.
Wilson, S. D., Karny, J. R., and Hlinka, K. J. (1994). “Agricultural chemical contamination of shallow bored and dug wells.” Proc., 4th Annu. Conf. Res. on Agric. Chemicals in Illinois Ground Water: Status and Future Directions IV, Southern Illinois University, Carbondale, Ill.
36.
Yang, C.-C., Prasher, S. O., and Lacroix, R. ( 1996). “Application of artificial neural networks to land drainage engineering.” Trans., ASAE, 39, 525–533.
Information & Authors
Information
Published In
Journal of Hydrologic Engineering
Volume 5 • Issue 2 • April 2000
Pages: 162 - 171
History
Received: May 2, 1998
Published online: Apr 1, 2000
Published in print: Apr 2000
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.