Assessment of physically-based and data-driven models to predict microbial water quality in open channels

Minyoung Kim, Charles P Gerba, Christopher Y. Choi

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In the present study, a physically-based hydraulic modeling tool and a data-driven approach using artificial neural networks (ANNs) were evaluated for their ability to simulate the fate and transport of microorganisms in a water system. To produce reliable data, a pipe network was constructed and a series of experiments using a fecal coliform indicator (Escherichia coli 15597) was conducted. For the physically-based model, morphological (pipe size, link length, slope, etc.) and hydraulic (flow rate) conditions were used as input variables, and for ANNs, water quality parameters (conductivity, pH, and turbidity) were used. Both approaches accurately described the fate and transport of microorganisms (physically-based model: correlation coeffcient (R) in the range of 0.914 - 0.977 and ANNs: R in the range of 0.949 - 0.980), with the exception of one case at a low flow rate (q = 31.56 cm3/sec). This study also indicated that these approaches could be complementarily utilized to assess the vulnerability of water facilities and to establish emergency plans based on hypothetical scenarios.

Original languageEnglish (US)
Pages (from-to)851-857
Number of pages7
JournalJournal of Environmental Sciences
Volume22
Issue number6
DOIs
StatePublished - 2010

Fingerprint

Water Quality
artificial neural network
Water quality
Neural networks
water quality
Microorganisms
Water
pipe
microorganism
Pipe
Flow rate
Hydraulics
hydraulics
Emergencies
Turbidity
fecal coliform
Escherichia coli
low flow
turbidity
vulnerability

Keywords

  • Artificial neural networks
  • Escherichia coli
  • Open channel
  • Transport

ASJC Scopus subject areas

  • Environmental Engineering
  • Environmental Science(all)
  • Environmental Chemistry
  • Medicine(all)

Cite this

Assessment of physically-based and data-driven models to predict microbial water quality in open channels. / Kim, Minyoung; Gerba, Charles P; Choi, Christopher Y.

In: Journal of Environmental Sciences, Vol. 22, No. 6, 2010, p. 851-857.

Research output: Contribution to journalArticle

@article{fcce80b0e33e4f1d8573cbd54c8540e3,
title = "Assessment of physically-based and data-driven models to predict microbial water quality in open channels",
abstract = "In the present study, a physically-based hydraulic modeling tool and a data-driven approach using artificial neural networks (ANNs) were evaluated for their ability to simulate the fate and transport of microorganisms in a water system. To produce reliable data, a pipe network was constructed and a series of experiments using a fecal coliform indicator (Escherichia coli 15597) was conducted. For the physically-based model, morphological (pipe size, link length, slope, etc.) and hydraulic (flow rate) conditions were used as input variables, and for ANNs, water quality parameters (conductivity, pH, and turbidity) were used. Both approaches accurately described the fate and transport of microorganisms (physically-based model: correlation coeffcient (R) in the range of 0.914 - 0.977 and ANNs: R in the range of 0.949 - 0.980), with the exception of one case at a low flow rate (q = 31.56 cm3/sec). This study also indicated that these approaches could be complementarily utilized to assess the vulnerability of water facilities and to establish emergency plans based on hypothetical scenarios.",
keywords = "Artificial neural networks, Escherichia coli, Open channel, Transport",
author = "Minyoung Kim and Gerba, {Charles P} and Choi, {Christopher Y.}",
year = "2010",
doi = "10.1016/S1001-0742(09)60188-1",
language = "English (US)",
volume = "22",
pages = "851--857",
journal = "Journal of Environmental Sciences",
issn = "1001-0742",
publisher = "Chinese Academy of Sciences",
number = "6",

}

TY - JOUR

T1 - Assessment of physically-based and data-driven models to predict microbial water quality in open channels

AU - Kim, Minyoung

AU - Gerba, Charles P

AU - Choi, Christopher Y.

PY - 2010

Y1 - 2010

N2 - In the present study, a physically-based hydraulic modeling tool and a data-driven approach using artificial neural networks (ANNs) were evaluated for their ability to simulate the fate and transport of microorganisms in a water system. To produce reliable data, a pipe network was constructed and a series of experiments using a fecal coliform indicator (Escherichia coli 15597) was conducted. For the physically-based model, morphological (pipe size, link length, slope, etc.) and hydraulic (flow rate) conditions were used as input variables, and for ANNs, water quality parameters (conductivity, pH, and turbidity) were used. Both approaches accurately described the fate and transport of microorganisms (physically-based model: correlation coeffcient (R) in the range of 0.914 - 0.977 and ANNs: R in the range of 0.949 - 0.980), with the exception of one case at a low flow rate (q = 31.56 cm3/sec). This study also indicated that these approaches could be complementarily utilized to assess the vulnerability of water facilities and to establish emergency plans based on hypothetical scenarios.

AB - In the present study, a physically-based hydraulic modeling tool and a data-driven approach using artificial neural networks (ANNs) were evaluated for their ability to simulate the fate and transport of microorganisms in a water system. To produce reliable data, a pipe network was constructed and a series of experiments using a fecal coliform indicator (Escherichia coli 15597) was conducted. For the physically-based model, morphological (pipe size, link length, slope, etc.) and hydraulic (flow rate) conditions were used as input variables, and for ANNs, water quality parameters (conductivity, pH, and turbidity) were used. Both approaches accurately described the fate and transport of microorganisms (physically-based model: correlation coeffcient (R) in the range of 0.914 - 0.977 and ANNs: R in the range of 0.949 - 0.980), with the exception of one case at a low flow rate (q = 31.56 cm3/sec). This study also indicated that these approaches could be complementarily utilized to assess the vulnerability of water facilities and to establish emergency plans based on hypothetical scenarios.

KW - Artificial neural networks

KW - Escherichia coli

KW - Open channel

KW - Transport

UR - http://www.scopus.com/inward/record.url?scp=77953701603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953701603&partnerID=8YFLogxK

U2 - 10.1016/S1001-0742(09)60188-1

DO - 10.1016/S1001-0742(09)60188-1

M3 - Article

C2 - 20923096

AN - SCOPUS:77953701603

VL - 22

SP - 851

EP - 857

JO - Journal of Environmental Sciences

JF - Journal of Environmental Sciences

SN - 1001-0742

IS - 6

ER -