The Office of Graduate Administration is pleased to announce that Anqi Chen will be defending their thesis as a candidate for the degree Master of Science in  Natural Resources and Environmental Studies.

You are encouraged to attend the defence. The details of the defence and how to attend are included below:

DATE: 15 April, 2024

TIME: 2:30 PM

DEFENCE MODE: Remote via Zoom

Please contact the Office of Graduate Administration for information regarding remote/online attendance. 

To ensure the defence proceeds with no interruptions, please mute your audio and video on entry and do not inadvertently share your screen. The meeting will be locked to entry 5 minutes after it begins: ensure you are on time.

THESIS ENTITLED: ADVANCING WATER QUALITY PREDICTIONS THROUGH INTERGRATING MACHINE LEARNING WITH DATA AUGMENTATION: A CASE STUDY FOR FIRST NATIONS COMMUNITIES IN BRITISH COLUMBIA

ABSTRACT: Clean drinking water access is essential for public health and regarded as a scarce resource for Indigenous communities in rural and remote areas. In this research, a new iron and manganese prediction method based on Data Augmentation and Machine Learning Algorithms to be applied to drinking water in BC’s First Nation communities is reported. GAN based modelling and NI-BS-NI based modelling were developed to investigate the effects of different data augmentation methods and predictors for iron and manganese prediction results. Reliable synthetic data was obtained through both data augmentation methods, allowing 4 machine learning algorithms to predict iron and manganese utilizing 3 and 5 physical properties respectively. Compared with RF, XGB, and DT machine learning models, the GBR model showed the strongest fitting ability and accurate predictions for both NI-BS-NI based modelling and GAN based modelling in predicting iron and manganese, with the Train R² and Test R² of two models nearing 1, and all the RMSE scores are below 0.06. The decision-making tool developed using GAN technology is considered to have greater application potential due to its ability to provide accurate predictions while requiring only 3 input physical parameters.

COMMITTEE MEMBERSHIP:

Chair: Dr. Hossein Kazemian, University of Northern British Columbia

Examining Committee Members:

Supervisor: Dr. Jianbing Li, University of Northern British Columbia

Co-Supervisor: Dr. Min Zhao, University of Northern British Columbia

Committee Member: Dr. Oliver Lorhemen, University of Northern British Columbia

Committee Member: Dr. Dave Tamblyn, First Nations Health Authority

External Examiner: Dr. Wenbo Zheng, University of Northern British Columbia