| Author: | Deng, Tianan |
| Title: | Modelling and forecasting algal blooms growth in Tolo Harbour by using neural network model and support vector machine |
| Advisors: | Chau, K. W. (CEE) |
| Degree: | M.Sc. |
| Year: | 2020 |
| Subject: | Algal blooms -- Environmental aspects -- China -- Hong Kong Algal blooms -- Monitoring -- China -- Hong Kong Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Civil and Environmental Engineering |
| Pages: | ix, 108 pages : color illustrations |
| Language: | English |
| Abstract: | In recent years, with the rapid development of urbanization and industrialization, the water bodies around cities have deteriorated seriously due to the discharge of pollutants. Since two waterfront towns of Tai Po and Shatin were developed, water eutrophication caused frequent harmful algal blooms (HAB) event due to domestic and industrial wastes discharge. In order to forewarn HAB events, we attempted to model the trend of algal growth in Tolo Harbour by using data collected over 30 years of environmental variables sampled at Tolo Harbour and successfully developed three different models namely ANN, GA-ANN and SVM. In general, the predictions results of all three models are highly consistent with observed data. In terms of the performance parameters, the accuracy of SVM model is much better than that of ANN and GA-ANN. It was surprised that GA-ANN model did not improve the performance of ANN to a great extent. This may be that the basic ANN model without optimization has been trained well enough by feeding with a large amount of data hence the optimization effect of genetic algorithm is not very obvious. Before modelling begins, the significant variables were analyzed, which shows the controlling factors of algal growth in Tolo Harbour are TIN, PO4, pH, BOD5 and ChlÂa concentration of past seven days. The different input combinations of variables are tested in trimming process, eventually it was found that there is no any benefit to establish a network with more environmental variables since the simplest network with only Chl-a concentration as inputs is good enough in predicting algal blooms dynamics in Tolo Harbour. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5358.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 5.39 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10905