Developing a real-time early warning system for potable water sources

点击翻译按钮获取中文摘要

Canada's freshwater ecosystem and drinking water quality has been negatively impacted by harmful algal blooms (HABs). HABs can produce high concentrations of cyanotoxins and natural organic matters which pose a severe threat to Canadian health. However, current water quality monitoring systems are laborious to characterize cyanotoxins or natural organic matters. By teaming up with academic, government and industry partners, we herein proposed to develop an early warning system to forecast the concentrations of cyanotoxins and natural organic matters in source drinking waters, by integrating a field-deployable multi-parameter sensor and machine learning algorithms. The machine learning algorithms will be benchmarked by characterizing grab samples with high-resolution mass spectrometry based nontargeted analysis. A total of 1,728 grab sample data points will be produced across 12 months. The dataset will be used to validate the machine-learning algorithms by matching to real-time UV-Vis absorbance spectra collected by remote sensors. The early warning system established in the current 1-year project will help to forecast source water quality and protect Canadian health from drinking water pollution.