Intelligent systems for water level prediction

Carl Steidley, Alex Sadovski, Phillipe Tissot, Rafic A. Bachnak, Zack Bowles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Tide tables are the method of choice for water level predictions in most coastal regions. In the United States, the National Ocean Service (NOS) uses harmonic analysis and time series of previous water levels to compute tide tables. This method is adequate for most locations along the US coast. However, for many locations along the coast of the Gulf of Mexico, tide tables do not meet NOS criteria. Wind forcing has been recognized as the main variable not included in harmonic analysis. The performance of the tide charts is particularly poor in shallow embayments along the coast of Texas. Recent research at Texas A&M University-Corpus Christi has shown that Artificial Neural Network (ANN) models including input variables such as previous water levels, tidal forecasts, wind speed, wind direction, wind forecasts and barometric pressure can greatly improve water level predictions at several coastal locations including open coast and deep embayment stations. In this paper, the ANN modeling technique was applied for the first time to a shallow embayment, the station of Rockport located near Corpus Christi, Texas. The ANN performance was compared to the NOS tide charts and the persistence model for the years 1997 to 2001. This site was ideal because it is located in a shallow embayment along the Texas coast and there is an 11-year historical record of water levels and meteorological data in the Texas Coastal Ocean Observation Network (TCOON) database. The performance of the ANN model was measured using NOS criteria such as Central Frequency (CF), Maximum Duration of Positive Outliers (MDPO), and Maximum Duration of Negative Outliers (MDNO). The ANN model compared favorably to existing models using these criteria and is the best predictor of future water levels tested.

Original languageEnglish (US)
Title of host publication18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005
Pages181-185
Number of pages5
StatePublished - Dec 1 2005
Event18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005 - Honolulu, HI, United States
Duration: Nov 9 2005Nov 11 2005

Publication series

Name18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005

Other

Other18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005
CountryUnited States
CityHonolulu, HI
Period11/9/0511/11/05

Fingerprint

Intelligent systems
Water levels
Tides
Coastal zones
Neural networks
Harmonic analysis
Network performance
Time series

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

Steidley, C., Sadovski, A., Tissot, P., Bachnak, R. A., & Bowles, Z. (2005). Intelligent systems for water level prediction. In 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005 (pp. 181-185). (18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005).
Steidley, Carl ; Sadovski, Alex ; Tissot, Phillipe ; Bachnak, Rafic A. ; Bowles, Zack. / Intelligent systems for water level prediction. 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005. 2005. pp. 181-185 (18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005).
@inproceedings{ec67f02016da41c59aafa5b6ff081568,
title = "Intelligent systems for water level prediction",
abstract = "Tide tables are the method of choice for water level predictions in most coastal regions. In the United States, the National Ocean Service (NOS) uses harmonic analysis and time series of previous water levels to compute tide tables. This method is adequate for most locations along the US coast. However, for many locations along the coast of the Gulf of Mexico, tide tables do not meet NOS criteria. Wind forcing has been recognized as the main variable not included in harmonic analysis. The performance of the tide charts is particularly poor in shallow embayments along the coast of Texas. Recent research at Texas A&M University-Corpus Christi has shown that Artificial Neural Network (ANN) models including input variables such as previous water levels, tidal forecasts, wind speed, wind direction, wind forecasts and barometric pressure can greatly improve water level predictions at several coastal locations including open coast and deep embayment stations. In this paper, the ANN modeling technique was applied for the first time to a shallow embayment, the station of Rockport located near Corpus Christi, Texas. The ANN performance was compared to the NOS tide charts and the persistence model for the years 1997 to 2001. This site was ideal because it is located in a shallow embayment along the Texas coast and there is an 11-year historical record of water levels and meteorological data in the Texas Coastal Ocean Observation Network (TCOON) database. The performance of the ANN model was measured using NOS criteria such as Central Frequency (CF), Maximum Duration of Positive Outliers (MDPO), and Maximum Duration of Negative Outliers (MDNO). The ANN model compared favorably to existing models using these criteria and is the best predictor of future water levels tested.",
author = "Carl Steidley and Alex Sadovski and Phillipe Tissot and Bachnak, {Rafic A.} and Zack Bowles",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781604234817",
series = "18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005",
pages = "181--185",
booktitle = "18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005",

}

Steidley, C, Sadovski, A, Tissot, P, Bachnak, RA & Bowles, Z 2005, Intelligent systems for water level prediction. in 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005. 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005, pp. 181-185, 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005, Honolulu, HI, United States, 11/9/05.

Intelligent systems for water level prediction. / Steidley, Carl; Sadovski, Alex; Tissot, Phillipe; Bachnak, Rafic A.; Bowles, Zack.

18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005. 2005. p. 181-185 (18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Intelligent systems for water level prediction

AU - Steidley, Carl

AU - Sadovski, Alex

AU - Tissot, Phillipe

AU - Bachnak, Rafic A.

AU - Bowles, Zack

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Tide tables are the method of choice for water level predictions in most coastal regions. In the United States, the National Ocean Service (NOS) uses harmonic analysis and time series of previous water levels to compute tide tables. This method is adequate for most locations along the US coast. However, for many locations along the coast of the Gulf of Mexico, tide tables do not meet NOS criteria. Wind forcing has been recognized as the main variable not included in harmonic analysis. The performance of the tide charts is particularly poor in shallow embayments along the coast of Texas. Recent research at Texas A&M University-Corpus Christi has shown that Artificial Neural Network (ANN) models including input variables such as previous water levels, tidal forecasts, wind speed, wind direction, wind forecasts and barometric pressure can greatly improve water level predictions at several coastal locations including open coast and deep embayment stations. In this paper, the ANN modeling technique was applied for the first time to a shallow embayment, the station of Rockport located near Corpus Christi, Texas. The ANN performance was compared to the NOS tide charts and the persistence model for the years 1997 to 2001. This site was ideal because it is located in a shallow embayment along the Texas coast and there is an 11-year historical record of water levels and meteorological data in the Texas Coastal Ocean Observation Network (TCOON) database. The performance of the ANN model was measured using NOS criteria such as Central Frequency (CF), Maximum Duration of Positive Outliers (MDPO), and Maximum Duration of Negative Outliers (MDNO). The ANN model compared favorably to existing models using these criteria and is the best predictor of future water levels tested.

AB - Tide tables are the method of choice for water level predictions in most coastal regions. In the United States, the National Ocean Service (NOS) uses harmonic analysis and time series of previous water levels to compute tide tables. This method is adequate for most locations along the US coast. However, for many locations along the coast of the Gulf of Mexico, tide tables do not meet NOS criteria. Wind forcing has been recognized as the main variable not included in harmonic analysis. The performance of the tide charts is particularly poor in shallow embayments along the coast of Texas. Recent research at Texas A&M University-Corpus Christi has shown that Artificial Neural Network (ANN) models including input variables such as previous water levels, tidal forecasts, wind speed, wind direction, wind forecasts and barometric pressure can greatly improve water level predictions at several coastal locations including open coast and deep embayment stations. In this paper, the ANN modeling technique was applied for the first time to a shallow embayment, the station of Rockport located near Corpus Christi, Texas. The ANN performance was compared to the NOS tide charts and the persistence model for the years 1997 to 2001. This site was ideal because it is located in a shallow embayment along the Texas coast and there is an 11-year historical record of water levels and meteorological data in the Texas Coastal Ocean Observation Network (TCOON) database. The performance of the ANN model was measured using NOS criteria such as Central Frequency (CF), Maximum Duration of Positive Outliers (MDPO), and Maximum Duration of Negative Outliers (MDNO). The ANN model compared favorably to existing models using these criteria and is the best predictor of future water levels tested.

UR - http://www.scopus.com/inward/record.url?scp=84883286820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883286820&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781604234817

T3 - 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005

SP - 181

EP - 185

BT - 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005

ER -

Steidley C, Sadovski A, Tissot P, Bachnak RA, Bowles Z. Intelligent systems for water level prediction. In 18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005. 2005. p. 181-185. (18th International Conference on Computer Applications in Industry and Engineering 2005, CAINE 2005).