Predicting water quality variables
| dc.contributor.advisor | Brink, Willie | en_ZA |
| dc.contributor.advisor | Wilms, Josefine M. | en_ZA |
| dc.contributor.author | Elmahdi, Reem | en_ZA |
| dc.contributor.other | Stellenbosch University. Faculty of Science. Department of Mathematical Sciences (Applied Mathematics). | en_ZA |
| dc.date.accessioned | 2020-02-23T18:08:52Z | |
| dc.date.accessioned | 2020-04-28T12:17:38Z | |
| dc.date.available | 2020-02-23T18:08:52Z | |
| dc.date.available | 2020-04-28T12:17:38Z | |
| dc.date.issued | 2020-03 | |
| dc.description | Thesis (MSc)--Stellenbosch University, 2020. | en_ZA |
| dc.description.abstract | ENGLISH ABSTRACT: Water is an important substance for all of life, and can be used in domestic, agricultural and industrial activities. Water quality determines the usefulness of water for particular purposes, and can be defined in terms of time-varying water quality variables such as dissolved oxygen, turbidity, temperature, pH, specific conductance, chlorophylls, nitrate and salinity. Different mathematical and statistical models have been used for the prediction of time-series data. Machine learning can also be used when enough data is available. In particular, artificial neural networks (ANNs) have demonstrated success in solving such problems. They are conceptually simple and easily implemented. In this thesis,an overview of two ANN s tructures is presented for solving the problem of predicting water quality variables. Specifically, multilayer perceptrons (MLPs) and long short-term memory (LSTM) networks are presented. Experiments are conducted on Hog Island water quality variables and the results of the models are compared using various accuracy metrics like root mean squared error. It is found that LSTM performs better than MLP across most of the accuracy metrics. | en_ZA |
| dc.description.abstract | AFRIKAANSE OPSOMMING: Water is belangrik vir alle vorme van lewe, en kan in huishoudelike, landbou-en nywerheidsaktiwiteite gebruik word. Waterkwaliteit bepaal die bruikbaarheid van water vir spesifieke doeleindes, en kan gedefinieer word in terme van tydafhanklike waterkwaliteitsveranderlikes soos opgeloste suurstof, troebelheid, temperatuur, pH, spesifieke geleiding, chlorofille, nitraat en soutge-halte. Verskillende wiskundige en statistiese modelle is al gebruik vir die voorspelling van tydreeksdata. Masjienleer kan ook g ebruik word as daar genoegdata beskikbaar is. In die besonder het kunsmatige neurale netwerke sukses behaal met die oplos van sulke probleme. Sulke netwerke is konseptueel eenvoudig en maklik om te implementeer. In hierdie tesis word ’n oorsig van twee neurale netwerkstrukture aangebied vir die voorspelling van waterkwaliteitsveranderlikes. In die besonder word meerlaag-perseptrone (MLP’s) en lang-korttermyngeheue (long short-term memory, LSTM) netwerke aangebied. Eksperimente is uitgevoer op Hog Eiland waterkwaliteitsveranderlikes en die resul-tate van die modelle word met behulp van verskillende akkuraatheidsmetrieke vergelyk, soos wortelgemiddelde kwadraatfout. Daar word gevind dat LSTM beter presteer as MLP volgens meeste van die akkuraatheidsmetrieke. | af_ZA |
| dc.description.version | Masters | en_ZA |
| dc.format.extent | v, 78 pages : illustrations | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/10019.1/108072 | |
| dc.language.iso | en_ZA | en_ZA |
| dc.publisher | Stellenbosch : Stellenbosch University. | en_ZA |
| dc.rights.holder | Stellenbosch University. | en_ZA |
| dc.subject | Water quality -- Management | en_ZA |
| dc.subject | Machine learning | en_ZA |
| dc.subject | Neural networks (Computer science) | en_ZA |
| dc.subject | Prediction of water quality | en_ZA |
| dc.subject | Time-series analysis -- Computer programs | en_ZA |
| dc.subject | Variables (Mathematics) | en_ZA |
| dc.subject | UCTD | |
| dc.title | Predicting water quality variables | en_ZA |
| dc.type | Thesis | en_ZA |