No abstract

No abstract

The application of different multivariate statistical techniques for the interpretation of a complex data matrix obtained during 2000-2007 from the watercourses in the Southwest New Territories and Kowloon, Hong Kong was presented in this study. The data set consisted of the analytical results of 23 parameters measured monthly at 16 different sampling sites. Hierarchical cluster analysis grouped the 12 months into two periods and the 16 sampling sites into three groups based on similarity in water quality characteristics. Discriminant analysis (DA) provided better results both temporally and spatially. DA also offered an important data reduction as it only used four parameters for temporal analysis, affording 84.2% correct assignations, and eight parameters for spatial analysis, affording 96.1% correct assignations. Principal component analysis/factor analysis identified four latent factors standing for organic pollution, industrial pollution, nonpoint pollution, and fecal pollution, respectively. KN1, KN4, KN5, and KN7 were greatly affected by organic pollution, industrial pollution, and nonpoint pollution. The main pollution sources of TN1 and TN2 were organic pollution and nonpoint pollution, respectively. Industrial pollution had high effect on TN3, TN4, TN5, and TN6.

[1] This paper proposes a neural network (NN)-embedded genetic algorithm (GA) approach for solving inverse water quality modeling problems to overcome the computational bottleneck of inverse modeling by replacing a water quality model with an efficient NN functional evaluator. An existing one-step, NN-embedded GA approach is found incapable of solving an inverse water quality modeling problem because it tends to fail in guiding the global search process to converge toward the near optima. As a remedy, an adaptive NN-GA approach is proposed to achieve a gradual convergence toward the near optima through an iterative network learning method. The proposed approach is applied to a full-scale, numerical example, and the result shows that the adaptive NN-GA approach is capable of obtaining near-optimal solutions for the inverse problem of a complicated water quality model.