PMID- 33552026
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20210210
IS  - 1664-302X (Print)
IS  - 1664-302X (Electronic)
IS  - 1664-302X (Linking)
VI  - 11
DP  - 2020
TI  - Tracking Major Sources of Water Contamination Using Machine Learning.
PG  - 616692
LID - 10.3389/fmicb.2020.616692 [doi]
LID - 616692
AB  - Current microbial source tracking techniques that rely on grab samples analyzed 
      by individual endpoint assays are inadequate to explain microbial sources across 
      space and time. Modeling and predicting host sources of microbial contamination 
      could add a useful tool for watershed management. In this study, we tested and 
      evaluated machine learning models to predict the major sources of microbial 
      contamination in a watershed. We examined the relationship between microbial 
      sources, land cover, weather, and hydrologic variables in a watershed in Northern 
      California, United States. Six models, including K-nearest neighbors (KNN), Naive 
      Bayes, Support vector machine (SVM), simple neural network (NN), Random Forest, 
      and XGBoost, were built to predict major microbial sources using land cover, 
      weather and hydrologic variables. The results showed that these models 
      successfully predicted microbial sources classified into two categories (human 
      and non-human), with the average accuracy ranging from 69% (Naive Bayes) to 88% 
      (XGBoost). The area under curve (AUC) of the receiver operating characteristic 
      (ROC) illustrated XGBoost had the best performance (average AUC = 0.88), followed 
      by Random Forest (average AUC = 0.84), and KNN (average AUC = 0.74). The 
      importance index obtained from Random Forest indicated that precipitation and 
      temperature were the two most important factors to predict the dominant microbial 
      source. These results suggest that machine learning models, particularly XGBoost, 
      can predict the dominant sources of microbial contamination based on the 
      relationship of microbial contaminants with daily weather and land cover, 
      providing a powerful tool to understand microbial sources in water.
CI  - Copyright (c) 2021 Wu, Song, Dubinsky and Stewart.
FAU - Wu, Jianyong
AU  - Wu J
AD  - Department of Environmental Sciences and Engineering, Gillings School of Global 
      Public Health, University of North Carolina, Chapel Hill, Chapel Hill, NC, United 
      States.
FAU - Song, Conghe
AU  - Song C
AD  - Department of Geography, University of North Carolina, Chapel Hill, Chapel Hill, 
      NC, United States.
FAU - Dubinsky, Eric A
AU  - Dubinsky EA
AD  - Environmental Genomics and Systems Biology Division, Lawrence Berkeley National 
      Laboratory, Berkeley, CA, United States.
FAU - Stewart, Jill R
AU  - Stewart JR
AD  - Department of Environmental Sciences and Engineering, Gillings School of Global 
      Public Health, University of North Carolina, Chapel Hill, Chapel Hill, NC, United 
      States.
LA  - eng
PT  - Journal Article
DEP - 20210120
PL  - Switzerland
TA  - Front Microbiol
JT  - Frontiers in microbiology
JID - 101548977
PMC - PMC7854693
OTO - NOTNLM
OT  - XGBoost
OT  - fecal contamination
OT  - land use
OT  - machine learning
OT  - microbial source tracking
OT  - rainfall
COIS- The authors declare that the research was conducted in the absence of any 
      commercial or financial relationships that could be construed as a potential 
      conflict of interest.
EDAT- 2021/02/09 06:00
MHDA- 2021/02/09 06:01
PMCR- 2021/01/20
CRDT- 2021/02/08 05:36
PHST- 2020/10/13 00:00 [received]
PHST- 2020/12/29 00:00 [accepted]
PHST- 2021/02/08 05:36 [entrez]
PHST- 2021/02/09 06:00 [pubmed]
PHST- 2021/02/09 06:01 [medline]
PHST- 2021/01/20 00:00 [pmc-release]
AID - 10.3389/fmicb.2020.616692 [doi]
PST - epublish
SO  - Front Microbiol. 2021 Jan 20;11:616692. doi: 10.3389/fmicb.2020.616692. 
      eCollection 2020.