Comparative prediction of stream water total nitrogen from land cover using artificial neural network and multiple linear regression approaches

• Autorzy: Amiri B J , Nakane K.
• Języki publikacji: EN

Abstrakty

EN

Performance of two data-driven models that were developed using Artificial Neural Networks (ANNs) and Multiple Linear Regression (MLR) approaches were investigated in prediction of Total Nitrogen (TN) concentration in twenty-one river basins in Chugoku district of Japan. Comparison of TN concentration predictions, which were carried out using an ANN-based model and MLR-based model indicated that prediction of the former model (r²=0.94, p<0.01) was more accurate than that of the latter model (r²=0.85, p<0.01). Lack of a sufficient data set that might be considered an obstacle for cross-validating models that are developed was dealt with using a Monte Carlo-based sensitivity analysis of the developed models. This initiative could provide reliable information for judging predictive capacity of the developed models stochastically. Result of sensitivity analysis revealed that predictive capacity of the ANN-based model varied between 0-2 mg/L. Moreover, prediction of the negative outputs was not observed. using the ANN-based model for TN concentration in stream water.

Słowa kluczowe

EN

Japan; Chugoku district; river basin; stream water; nitrogen concentration; total nitrogen; artificial neural network; multiple linear regression; water quality; Geographic Information System; multivariate statistics

• Wydawca: -
• Czasopismo: Polish Journal of Environmental Studies
• Rocznik: 2009
• Tom: 18
• Numer: 2
• Opis fizyczny: p.151-160,fig.,ref.

Twórcy

autor

Amiri B J

• Hiroshima University, 1-7-1 Kagamiyama, Higashi-Hiroshima 739-8521 Japan

autor

Nakane K.

Bibliografia

• 1. JOHNES K. B., NEALE A. C., NASH M. S., VAN REMORTEL R. D., WICKHAM J. D., RIITTERS H., O’NEILL R. V. Predicting nutrient and sediment loadings to streams from landscape metrics: A multiple watershed study from the United States Mid-Atlantic Region. Landscape Ecology 16, 301, 2001.
• 2. SLIVA L., WILLIAMS D. D. Buffer zone versus whole catchment approaches to studying land use impact on river water quality. Water Research, 35 (14), 3462, 2001.
• 3. JARVIE H. P., OGUCHI T., NEAL C. Exploring the linkage between river water chemistry and watershed characteristics using GIS-based catchment and locality analyses. Regional Environment Change, 3, 36, 2002.
• 4. AHEARN D.S., SHEIBLEY R.W, DAHLGREN R.A., ANDERSON M., JOHNSON J., TATE K.W., 2005.Land use and land cover influence on water quality in the last freeflowing river draining the western Sierra Nevada, California, Journal of Hydrology 313, 234, 2005.
• 5. BASNYAT P., TEETER L. D., FLYNN K. M., LOCKABY B. G. Relationships between landscape characteristics and nonpoint source pollution inputs to coastal estuaries. Environmental Management, 23 (4), 539, 1999.
• 6. JEONG K. S., KIM D. K., CHON T. S., JOO G. J. Mashine learning application to the Korean freshwater ecosystems, Korean J. Ecol. 28 (6), 405, 2005.
• 7. MAIER H. R., DANDY G. C. Neural network based modelling of environmental Variables: A systematic approach, Mathematical and Computer Modelling 23, 669, 2001.
• 8. HANSEN J. V., NELSON R. D. Neural networks and traditional time series methods: A synergistic combination in state economic forecasts. IEEE Transactions on Neural Networks 8(4), 863, 1997.
• 9. JAPANESE STATISTICS BUREAU of MINISTRY OF INTERNAL AFFAIRS AND COMMUNICATION: http://www.stat.go.jp/data/kokusei/2000/final/zuhyou/008-01.xls
• 10. JAPANESE STANDARD ASSOCIATION. Testing methods for industrial wastewater: K0102, Tokyo. 1998.
• 11. ESRI (Environmental Systems Research Institute). ArcView GIS Software, Redlands, California, USA. 1999.
• 12. INTEGRATED LAND AND WATER INFORMATION SYSTEM (ILWIS). The Remote sensing and GIS software. ITC, the Netherlands. 2004.
• 13. LEK S, GUIRESSE, GIRAUDEL J. L. Predicting stream nitrogen concentration from watershed features using neural networks, Wat. Res. 33(16), 3469, 1999.
• 14. SPITZ F., LEK S. environmental impact prediction using neural network modeling: an example for wildlife damage, Journal of applied Ecology, 36, 317, 1999.
• 15. RUDI Y., SETAIWN I. Backpropagation Neural Network 1.0, Bogor Agricultural University. Indonesia. Personal Correspondence. 2003.
• 16. RECH G. Forecasting with Artificial Neural Network Models, SSE/EFI Working Paper Series in Economics and Finance, No. 491, 38 , 2002.
• 17. ILIADIS L. S., MARIS F. An Artificial Neural Network model for mountainous water-resources management: The case of Cyprus mountainous watersheds, Environmental Modelling & Software 7 (22), 1066, 2007.
• 18. HECHT-NIELSEN R. Kolmogorov’s mapping neural network existence theorem. Proceedings of the First IEEE International Joint Conference on Neural Networks, San Diego, California, pp. 11-14, IEEE, New York. 1987.
• 19. NETER J., KUNTER H.M., NACHTSHEIM C.J. WASSERMAN W. Applied Linear Statistical Models, Irwin, Chicago, Illinois, USA. 1996.
• 20. CHATTERJEE S., HADI A.S., PRICE B., The Use of Regression Analysis by Example, John Wiley and Sons, New York, USA. 2000.
• 21. RUMELHART D.E., HINTON G.E., WILLIAMS R.J. Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (Eds.), Parallel Distributed Processing. MIT Press, Cambridge. 1986.
• 22. KOZAK A., KOZAK R. Does cross validation provide additional information in the evaluation of regression models?. Can. J. For. Res. 33, 976, 2003.
• 23. WITWER J.W. 2004. Monte Carlo Simulation Basics, http://vertex42.com/ExcelArticles/mc/MonteCarloSimulation. html, downloaded on 2007/11/15.