1.375 height=22.8  /> = 150. Figure 5 shows the calculated values of optimal SVR model versus observed values for chlorophyll-a (= 0.8202). It can be concluded that the predicted results are in good agreement with the observation ones.

The optimal SVR model was compared with stepwise MLR and back propagation artificial neural network (BPANN). The parameters of BPANN model with three layers used were as follows: the number of hidden nodes was seven; the transformation function was sigmoid; the learning rate and momentum of each epoch were set to 0.30 and 0.20 respectively. External validation was used to compare the predictive capacity of models. The data set was randomly classified into training set (80% data) and test set (20% data) and the predictive () values were calculated according to the following equation:

(8)

Figure 2. versus and C with RBF kernel function (σ = 0.10).

Figure 3. versus and C with polynomial kernel function.

Figure 4. versus and C with linear kernel function.

Figure 5. Observed values versus calculated values for chlorophyll-a using optimal SVR model.

where and represent the predicted and observed chlorophyll-a values of the test set, respectively. is the mean chlorophyll-a value of the training set.

The values of MLR, BPANN and SVR models were 0.4127, 0.7644 and 0.7842 respectively. Figure 6 shows the predicted values of optimal SVR model versus observed values for chlorophyll-a. Based on the above results. The SVR method has been shown to perform well for regression and be a useful and powerful technique to construct the chlorophyll-a model during spring algal bloom.

4. Conclusion

The support vector regression model of chlorophyll-a during spring algal bloom in Xiangxi Bay of Three

Figure 6. Observed values versus predicted values for chlorophyll-a using optimal SVR model.

Gorges Reservoir was established. Using stepwise MLR method, the important environmental variables (DO, pH, Turb, PO4, NH4, NO3 and SiO4) were selected. The parameters in SVR such as the type of kernel function, the regularization parameter and -insensitive loss function were optimized by leave one out cross validation. and of the optimal SVR model are 0.8202 and 0.7301, respectively. Compared with MLR and BPANN models, the SVR model has been shown to perform well for regression with the value of 0.7842 for the test set.

5. Acknowledgements

This work was funded by National Natural Science Foundation of China (No. 50679038, 51009080), National Science and Technology Support Program of China (No. 2008BAB29B09), National Water Special Project of China (2008ZX07104-004) and Hubei Province Ministry of Environmental Protection, China (No. 2008HB08). We thank Daobin Ji, Zhengjian Yang, Zhongqiang Yi, Jun Ma, Yanmei Su, Xia Yang and Qiaoli Cao for their assistance in the field and lab.

REFERENCES

  1. S. R. Carpenter, D. Ludwig and W. A. Brock, “Management of Eutrophication for Lakes Subject to Potentially Irreversible Change,” Ecological Applications, Vol. 9, 1999, pp. 751-771. doi:10.1890/1051-0761(1999)009[0751:MOEFLS]2.0.CO;2
  2. D. W. Schindler, “Recent Advances in the Understanding and Management of Eutrophication,” Limnology and Oceanography, Vol. 51, 2006, pp. 356-363. doi:10.4319/lo.2006.51.1_part_2.0356
  3. I. Kagalou, E. Papastergiadou and I. Leonardos, “Long Term Changes in the Eutrophication Process in a Shallow Mediterranean Lake Ecosystem of W. Greece: Response after the Reduction of External Load,” Journal of Environmental Management, Vol. 87, No. 3, 2008, pp. 497- 506. doi:10.1016/j.jenvman.2007.01.039
  4. H. B. Glasgow Jr. and J. M. Burkholder, “Water Quality Trends and Management Implications from a Five-Year Study of a Eutrophic Estuary,” Ecological Applications, Vol. 10, 2000, pp. 1024-1046. doi:10.1890/1051-0761(2000)010[1024:WQTAMI]2.0.CO;2
  5. P. J. Dillon and F. H. Rigler, “The Phosphorus-Chlorophyll Relationship in Lakes,” Limnology and Oceanography, Vol. 19, No. 5, 1974, pp. 767-773. doi:10.4319/lo.1974.19.5.0767
  6. K. An and S. S. Park, “Indirect Influence of the Summer Monsoon on Chlorophyll-Total Phosphorus Models in Reservoirs: A Case Study,” Ecological Modelling, Vol. 152, No. 2-3, 2002, pp. 191-203. doi:10.1016/S0304-3800(02)00020-0
  7. G. Phillips, O. P. Pietilainen, L. Carvalho, A. Solimini, A. L. Solheim and A. Cardoso, “Chlorophyll-Nutrient Relationships of Different Lake Types Using a Large European Dataset,” Aquatic Ecology, Vol. 42, No. 2, 2008, pp. 213-226. doi:10.1007/s10452-008-9180-0
  8. L. Hakanson, J. M. Malmaeus, U. Bodemer and V. Gerhardt, “Coefficients of Variation for Chlorophyll, Green Algae, Diatoms, Cryptophytes And Blue-Greens in Rivers as a Basis For Predictive Modelling and Aquatic Management,” Ecological Modelling, Vol. 169, No. 1, 2003, pp. 179-196. doi:10.1016/S0304-3800(03)00269-2
  9. K. K. Balachandran, K. V. Jayalakshmy, C. M. Laluraj, M. Nair, T. Joseph and P. Sheeba, “Step-Up Multiple Regression Model to Compute Chlorophyll a in the Coastal Waters off Cochin, Southwest Coast of India,” Environmental Monitoring and Assessment, Vol. 139, No. 1-3, 2008, pp. 217-226. doi:10.1007/s10661-007-9829-5
  10. N. K. Sharma, D. Mohan and A. K. Rai, “Predicting Phytoplankton Growth and Dynamics in Relation to Physico-Chemical Characteristics of Water Body,” Water Air & Soil Pollution, Vol. 202, No. 1-4, 2009, pp. 325-333. doi:10.1007/s11270-009-9979-x
  11. K. H. Cho, J.-H. Kang, S. J. Ki, Y. Park, S. M. Cha and J. H. Kim, “Determination of the Optimal Parameters in Regression Models for the Prediction of Chlorophyll-a: A Case Study of the Yeongsan Reservoir, Korea,” Science of the Total Environment, Vol. 407, No. 8, 2009, pp. 2536- 2545. doi:10.1016/j.scitotenv.2009.01.017
  12. Y. Liu, H. Guo and P. Yang, “Exploring the Influence of Lake Water Chemistry on Chlorophyll-a: A Multivariate Statistical Model Analysis,” Ecological Modelling, Vol. 221, No. 4, 2010, pp. 681-688. doi:10.1016/j.ecolmodel.2009.03.010
  13. M. Xu, G. M. Zeng, X. Y. Xu and G. H. Huang, “Application of Bayesian Regularized BP Neural Network Model for Analysis of Aquatic Ecological Data—A Case Study of Chlorophyll a Prediction in Nanzui Water Area of Dongting Lake,” Journal of Environmental Science, Vol. 17, No. 6, 2005, pp. 946-952.
  14. K.-S. Jeong, D.-K. Kim and G.-J. Joo, “River Phytoplankton Prediction Model by Artificial Neural Network: Model Performance and Selection of Input Variables to Predict Time-Series Phytoplankton Proliferations in a Regulated River System,” Ecological Informatics, Vol. 1, No. 3, 2006, pp. 235-245. doi:10.1016/j.ecoinf.2006.04.001
  15. V. Vapnik, “Statistical Learning Theory,” Wiley, New York, 1998.
  16. V. Vapnik, “An Overview of Statistical Learning Theory,” IEEE Transactions on Neural Networks, Vol. 10, No. 5, 1999, pp. 988-999. doi:10.1109/72.788640
  17. U. Thissen, R. van Brakel, A. P. de Weijer, W. J. Melssen and L. M. C. Buydens, “Using Support Vector Machines for Time Series Prediction,” Chemometrics and Intelligent Laboratory Systems, Vol. 69, No. 1-2, 2003, pp. 35- 49. doi:10.1016/S0169-7439(03)00111-4
  18. J. G. Wu, J. H. Huang, X. G. Han, Z. Q. Xie and X. M. Gao, “Three-Gorge Dam—Experiment in Habitat Fragmentation?” Science, Vol. 300, No. 5623, 2003, pp. 1239- 1240. doi:10.1126/science.1083312
  19. L. Ye, D. F. Li, T. Tang, X. D. Qu and Q. H. Cai, “Spatial Distribution of Water Quality in Xiangxi River, China,” China Journal of Applied Ecology, Vol. 14, No. 11, 2003, pp. 1959-1962.
  20. T. Tang, D. F. Li, W. B. Pan, X. D. Qu and Q. H. Cai, “River Continuum Characteristics of Xiangxi River,” China Journal of Applied Ecology, Vol. 15, No. 1, 2004, pp. 141-144.
  21. H. Y. Wang, “Effects of the Three Gorges Reservoir on the Water Environment of the Xiangxi River with the Proposal of Countermeasures,” Resource and Environment of Yangtze Basin, Vol. 14, No. 2, 2005, pp. 233-237.
  22. X. C. Jin and Q. Y. Tu, “Criterion of Eutrophication Survey on Lakes,” 2nd Edition, Environmental Science Press, Beijing, 1990.
  23. A. J. Lewitus, E. T. Koepfler and J. T. Morris, “Seasonal Variation in the Regulation of Phytoplankton by Nitrogen and Grazing in a Salt Marsh Estuary,” Limnology and Oceanography, Vol. 43, No. 4, 1998, pp. 636-646. doi:10.4319/lo.1998.43.4.0636
  24. S. R. Gunn, “Support Vector Machines for Classification and Regression,” Technical Report, Image Speech and Intelligent Systems Research Group, University of Southampton, Southampton, 1997. http://www.isis.ecs.soton.ac.uk/isystems/kernel/

Journal Menu >>