Currently, monitoring of water quality mostly reply on grab sampling, transporting sample to a laboratory and followed by laboratory analysis, which is unable to provide quick responses to water events as it often takes hours and even days to transport and analyse samples. For some analytes, such as disinfection by-products, they also require the use of more sophisticated analytical instruments which limited the turn-around time to even longer using the standard laboratory method and is not an effective approach for monitoring these potentially harmful contaminants to ensure water safety. On-line monitoring measures water quality continuously and allows quick responses by providing real-time data. Recently, UV-Vis and fluorescence spectroscopy have been reported as promising monitoring technologies. There are rarely studies on the development of surrogate parameters for emerging contaminants using spectral data. This project aims to apply machine learning to correlate event using the hidden analytical information from the spectra.
- Student type: International, Domestic
- Research degree type: PhD
- Signature research theme: Sustainable Green Transition
- Supervisor: Professor Christopher Chow
