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

开发饮用水源实时预警系统

• 批准号: 567513-2021
• 负责人: Peng, Hui
• 金额: $ 3.28万
• 依托单位: University of Toronto
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=723507
• 关键词: Developing; real; time; early; warning

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.

加拿大的淡水生态系统和饮用水质量受到有害藻华（HAB）的负面影响。 HAB可以产生高浓度的氰毒素和自然有机物，这对加拿大健康构成了严重威胁。但是，当前的水质监测系统努力地表征氰毒素或天然有机物。通过与学术，政府和行业合作伙伴合作，我们在这里提议开发一种预警系统，以预测源饮用水中的氰毒素和自然有机物的浓度，通过整合可实地可剥削的多参数传感器和机器学习算法。机器学习算法将通过表征基于高分辨率质谱分析的Grab样品来基准测试。在12个月中，总共将产生1,728个获取样本数据点。该数据集将通过与遥控传感器收集的实时UV-VIS吸光度光谱匹配来验证机器学习算法。当前一年项目中建立的预警系统将有助于预测水质并保护加拿大健康免受饮用水污染。