Onsite Analysis of Water Quality using Smartphones

Abstract

Water treatment techniques require free chlorine as an essential component to prevent contamination and maintain water quality. However, conventional methods of free chlorine analysis rely on chemical reagents and laboratory equipment, which are expensive and time consumption. In this thesis paper, we propose using machine learning methods to develop an on-site system to analyze free chlorine in the water. This paper demonstrates the feasibility of this approach by training different machine learning models on a dataset of water samples with known free chlorine concentrations and evaluating its accuracy. Without laboratory equipment, the machine learning system can predict free chlorine concentration in real-time; therefore, by implementing this system, we aim to improve the efficiency and cost-effectiveness of water treatment processes.

Date of Award	Apr 2023
Original language	American English
Supervisor	Andrei Sleptchenko (Supervisor)