Full metadata record
DC FieldValueLanguage
dc.contributorFaculty of Construction and Environmenten_US
dc.contributor.advisorChau, Kwok-wing (CEE)-
dc.creatorWang, Quan-
dc.identifier.urihttps://theses.lib.polyu.edu.hk/handle/200/9063-
dc.languageEnglishen_US
dc.publisherHong Kong Polytechnic University-
dc.rightsAll rights reserveden_US
dc.titleNeural network and genetic programming for modeling coastal algal blooms in Tolo Harbour, Hong Kongen_US
dcterms.abstractWater is a special resource on the earth, which cannot be replaced by any other material. Water is a unique physical and chemical properties. In a word, nobody can live without water. However, the living condition are facing with the problem of water resource shortage and deterioration of water quality. Especially, harmful algal bloom (HAB) is regarded as a serious environmental problem in Tolo Harbour, Hong Kong. In recent years, forecasting of water quality has become one of the hottest point of most scholar. Based on the non-determinacy and highly non-linearity characteristic of the water environment pollution processing, machine learning (ML) techniques have been more and more used to model the progress of algal dynamics. One of the ML method, artificial neural network (ANN), is used to predict the algal blooms of the coastal waters of Tolo Harbour. And the model we set up is based on a biweekly water quality data of two monitors TM3 and TM4 at Tolo Harbour (2004-2014). Analysis of different combination of input scenarios shows that the smaller variables input, the better agreement with observations is obtained. And the finding is in contrast to previous study which suggested that more complicated neural networks is goodness for algal blooms predation in freshwater systems. Then, the study of the various scenarios weights of trained neural network and genetic programming shows that well prediction of long time period of algal dynamics will be got when the input is only chlorophyll-a. What is more, the consequence of the study also suggest that the prediction of algal biomass based on the biweekly record data have good performance on long-term trends, but the prediction on short-term trends is still need more frequency record data.en_US
dcterms.extentx, 88 pages : color illustrationsen_US
dcterms.isPartOfPolyU Electronic Thesesen_US
dcterms.issued2016en_US
dcterms.educationalLevelM.Sc.en_US
dcterms.educationalLevelAll Masteren_US
dcterms.LCSHHong Kong Polytechnic University -- Dissertationsen_US
dcterms.LCSHAlgal blooms -- Monitoring -- China -- Hong Kongen_US
dcterms.LCSHWater quality -- China -- Hong Kongen_US
dcterms.accessRightsrestricted accessen_US

Files in This Item:
File Description SizeFormat 
991021952829903411.pdfFor All Users (off-campus access for PolyU Staff & Students only)2.32 MBAdobe PDFView/Open


Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. 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.
  3. 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.

Show simple item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/9063