Fault detection for salinity sensors in the Columbia estuary

Cynthia Archer, Antonio Baptista, Todd K. Leen

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Sensors deployed in the Columbia River estuary gather information on physical dynamics and changes in estuary habitat. Of these sensors, conductivity sensors are particularly susceptible to biofouling, which gradually degrades sensor response and corrupts critical data. Several weeks may pass before degradation is visibly detected. Since the onset time of biofouling is unknown, an indeterminate amount of measurement data is corrupted. To speed detection and minimize data loss, we develop automatic biofouling detectors based on machine learning approaches for these conductivity sensors. We demonstrate that our detectors identify biofouling at least as reliably as human experts. In addition, these detectors provide accurate estimates of biofouling onset time. Real-time detectors installed during the summer of 2001 produced no false alarms yet detected all episodes of sensor degradation before the field staff.

Original languageEnglish (US)
JournalWater Resources Research
Volume39
Issue number3
StatePublished - Mar 2003

Fingerprint

Biofouling
Estuaries
biofouling
Fault detection
sensors (equipment)
estuaries
estuary
salinity
sensor
detectors
Sensors
Detectors
conductivity
Degradation
degradation
Columbia River
artificial intelligence
Learning systems
detection
Rivers

Keywords

  • Biofouling
  • Fault detection
  • Novelty detection
  • Salinity measurement
  • Sensor degradation
  • Sensor failure

ASJC Scopus subject areas

  • Environmental Science(all)
  • Environmental Chemistry
  • Aquatic Science
  • Water Science and Technology

Cite this

Fault detection for salinity sensors in the Columbia estuary. / Archer, Cynthia; Baptista, Antonio; Leen, Todd K.

In: Water Resources Research, Vol. 39, No. 3, 03.2003.

Research output: Contribution to journalArticle

@article{7c7106c950a04d5e928394f43431e9a7,
title = "Fault detection for salinity sensors in the Columbia estuary",
abstract = "Sensors deployed in the Columbia River estuary gather information on physical dynamics and changes in estuary habitat. Of these sensors, conductivity sensors are particularly susceptible to biofouling, which gradually degrades sensor response and corrupts critical data. Several weeks may pass before degradation is visibly detected. Since the onset time of biofouling is unknown, an indeterminate amount of measurement data is corrupted. To speed detection and minimize data loss, we develop automatic biofouling detectors based on machine learning approaches for these conductivity sensors. We demonstrate that our detectors identify biofouling at least as reliably as human experts. In addition, these detectors provide accurate estimates of biofouling onset time. Real-time detectors installed during the summer of 2001 produced no false alarms yet detected all episodes of sensor degradation before the field staff.",
keywords = "Biofouling, Fault detection, Novelty detection, Salinity measurement, Sensor degradation, Sensor failure",
author = "Cynthia Archer and Antonio Baptista and Leen, {Todd K.}",
year = "2003",
month = "3",
language = "English (US)",
volume = "39",
journal = "Water Resources Research",
issn = "0043-1397",
publisher = "American Geophysical Union",
number = "3",

}

TY - JOUR

T1 - Fault detection for salinity sensors in the Columbia estuary

AU - Archer, Cynthia

AU - Baptista, Antonio

AU - Leen, Todd K.

PY - 2003/3

Y1 - 2003/3

N2 - Sensors deployed in the Columbia River estuary gather information on physical dynamics and changes in estuary habitat. Of these sensors, conductivity sensors are particularly susceptible to biofouling, which gradually degrades sensor response and corrupts critical data. Several weeks may pass before degradation is visibly detected. Since the onset time of biofouling is unknown, an indeterminate amount of measurement data is corrupted. To speed detection and minimize data loss, we develop automatic biofouling detectors based on machine learning approaches for these conductivity sensors. We demonstrate that our detectors identify biofouling at least as reliably as human experts. In addition, these detectors provide accurate estimates of biofouling onset time. Real-time detectors installed during the summer of 2001 produced no false alarms yet detected all episodes of sensor degradation before the field staff.

AB - Sensors deployed in the Columbia River estuary gather information on physical dynamics and changes in estuary habitat. Of these sensors, conductivity sensors are particularly susceptible to biofouling, which gradually degrades sensor response and corrupts critical data. Several weeks may pass before degradation is visibly detected. Since the onset time of biofouling is unknown, an indeterminate amount of measurement data is corrupted. To speed detection and minimize data loss, we develop automatic biofouling detectors based on machine learning approaches for these conductivity sensors. We demonstrate that our detectors identify biofouling at least as reliably as human experts. In addition, these detectors provide accurate estimates of biofouling onset time. Real-time detectors installed during the summer of 2001 produced no false alarms yet detected all episodes of sensor degradation before the field staff.

KW - Biofouling

KW - Fault detection

KW - Novelty detection

KW - Salinity measurement

KW - Sensor degradation

KW - Sensor failure

UR - http://www.scopus.com/inward/record.url?scp=1542546112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542546112&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1542546112

VL - 39

JO - Water Resources Research

JF - Water Resources Research

SN - 0043-1397

IS - 3

ER -