Combining principal component regression and artificial neural network to predict chlorophyll-a concentration of Yuqiao Reservoir’s outflow

Abstract

In order to investigate the eutrophication degree of Yuqiao Reservoir, a hybrid method, combining principal component regression (PCR) and artificial neural network (ANN), was adopted to predict chlorophyll-a concentration of Yuqiao Reservoir’s outflow. The data were obtained from two sampling sites, site 1 in the reservoir, and site 2 near the dam. Seven water variables, namely chlorophyll-a concentration of site 2 at time t and that of both sites 10 days before t, total phosphorus(TP), total nitrogen(TN), dissolved oxygen(DO), and temperature from January 2000 to September 2002, were utilized to develop models. To remove the collinearity between the variables, principal components extracted by principal component analysis were employed as predictors for models. The performance of models was assessed by the square of correlation coefficient, mean absolute error (MAE), root mean square error (RMSE) and average absolute relative error (AARE). Results show that the hybrid method has achieved more accurate prediction than PCR or ANN model. Finally, the three models were applied to predicting the chlorophyll-a concentration in 2003. The predictions of the hybrid method were found to be consistent with the observed values all year round, while the results of PCR and ANN models did not fit quite well from July to October.

Keywords

principal component regression / artificial neural network / hybrid method / chlorophyll-a / eutrophica-tion

References

[1] Selman Z. S., Greenhalgh S., Diaz R. Eutrophication and Hypoxia in Coastal Areas: A Global Assessment of the State of Knowledge[M]. 2008, Washington DC: World Resources Institute.

[2] Li X. Y., Xu F. L., Zhan W., et al. Current situation and development trend in lake eutrophication models[J]. Advances in Water Science, 2003, 14(6): 792-798.

[3] Hakanson L., Malmaeus J. M., Bodemer U., et al. Coefficients of variation for chlorophyll, green algae, diatoms, cryptophytes and blue-greens in rivers as a basis for predictive modelling and aquatic management[J]. Ecological Modelling, 2003, 169(1/2): 179-196.

[4] Mac Nally R. Multiple regression and inference in ecology and conservation biology: Further comments on identifying important predictor variables[J]. Biodiversity and Conservation, 2002, 11(8): 1397-1401.

[5] He L. M., He Z. L. Water quality prediction of marine recreational beaches receiving watershed baseflow and stormwater runoff in southern California, USA[J]. Water Research, 2008, 42(10/11): 2563-2573.

[6] Emrah D., Bülent S., Rabia K. Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique[J]. Journal of Environmental Management, 2009, 90(2): 1229-1235.

[7] Kuo J. T., Hsieh M. H., Lung W. S., et al. Using artificial neural network for reservoir eutrophication prediction[J]. Ecological Modelling, 2007, 200(1/2): 171-177.

[8] Kunwar P. S., Ankita B., Amrita M., et al. Artificial neural network modeling of the river water quality: A case study[J]. Ecological Modelling, 2009, 220(6): 888-895.

[9] Bates J. M., Granger C. W. J. The combination of forecasts[J]. Operations Research Quarterly, 1969, 20 448-451.

[10] Abdul-Wahab S. A., Bakheit C. S., Al-Alawi S. M. Principal component and multiple regression analysis in modeling of ground-level ozone and factors affecting its concentrations[ J] Environmental Modelling & Software, 2005, 20(10): 1263-1271.

[11] Li Y., Cheng W., Liu Jianting. The forecast of water quality based on artificial neural networks and regression analysis[J]. Journal of Zhengzhou University (Engineering Science), 2008, 29(1): 106 109

[12] Kowalkowski T., Zbytniewski R., Szpejna J., et al. Application chemometrics in river water classification[J]. Water Research, 2006, 40(4): 744-752.

[13] Fletcher D., Goss E. Forecasting with neural networks: An application using bankruptcy data[J]. Information & Management, 1993, 24(3): 159-167.

[14] Al-Alawi S. M., Abdul-Wahab S. A., Bakheit C. S. Combining principal component regression and artificial neural networks for more accurate predictions of groundlevel ozone[J]. Environmental Modelling & Software, 2008, 23(4): 396-403.

[15] Chaloulakou A., Saisana M., Spyrellis N. Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens[J]. Science of the Total Environment, 2003, 313(1/3): 1-13.