Machine learning for anomaly detection in cyanobacterial fluorescence signals

WATER RESEARCH

卷:197

Article

Almuhtaram, Husein¹  Zamyadi, Arash^2,3,4  Hofmann, Ron¹ 

[1] Univ Toronto, Dept Civil & Mineral Engn, Toronto, ON M5S 1A4, Canada

[2] Water RA Melbourne, 990 La Trobe St, Docklands, Vic 3008, Australia

[3] Univ New South Wales UNSW, BGA Innovat Hub, Sch Civil & Environm Engn, Sydney, NSW 2052, Australia

[4] Univ New South Wales UNSW, Water Res Ctr, Sch Civil & Environm Engn, Sydney, NSW 2052, Australia

关键词: Phycocyanin;    Drinking water treatment;    Cyanobacteria;    Monitoring;    Artificial intelligence;    Chlorophyll a;    CCchHlo C;   

DOI  :  10.1016/j.watres.2021.117073

来源: Elsevier

【 摘 要 】

Many drinking water utilities drawing from waters susceptible to harmful algal blooms (HABs) are imple-menting monitoring tools that can alert them to the onset of blooms. Some have invested in fluorescence-based online monitoring probes to measure phycocyanin, a pigment found in cyanobacteria, but it is not clear how to best use the data generated. Previous studies have focused on correlating phycocyanin flu-orescence and cyanobacteria cell counts. However, not all utilities collect cell count data, making this method impossible to apply in some cases. Instead, this paper proposes a novel approach to determine when a utility needs to respond to a HAB based on machine learning by identifying anomalies in phyco-cyanin fluorescence data without the need for corresponding cell counts or biovolume. Four widespread and open source algorithms are evaluated on data collected at four buoys in Lake Erie from 2014 to 2019: local outlier factor (LOF), One-Class Support Vector Machine (SVM), elliptic envelope, and Isolation Forest (iForest). When trained on standardized historical data from 2014 to 2018 and tested on labelled 2019 data collected at each buoy, the One-Class SVM and elliptic envelope models both achieve a maximum average F1 score of 0.86 among the four datasets. Therefore, One-Class SVM and elliptic envelope are promising algorithms for detecting potential HABs using fluorescence data only. (c) 2021 Elsevier Ltd. All rights reserved.

【 授权许可】

Free