Correlation of wave data from buoy networks

S. N. Londhe, Vijay Panchang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Missing oceanographic data resulting from an instrument that is damaged, malfunctioning, or otherwise non-operational can be an impediment to real-time applications of the data and also to statistical calculations pertaining to climatological studies. The problem of reconstructing lost information by correlating oceanographic data from multiple stations is explored through the use of artificial neural networks. A comprehensive simulation study was performed by developing six buoy networks (each containing several buoys) in locations with diverse geographical and wave properties: the northeastern part of the US, the Gulf of Mexico, and Prince William Sound (Alaska). The simulations demonstrate that the missing significant wave heights at the location of one buoy can, for the most part, be reliably reconstructed using artificial neural networks (ANNs) and data from other buoys. ANN model results in the northeastern part of the US tended to suffer from frequent under-prediction, while networks in the Gulf of Mexico and in Prince William Sound showed greater fidelity to measurements. The potential for redeploying some buoys to other locations and using the neural network model instead is examined.

Original languageEnglish
Pages (from-to)481-492
Number of pages12
JournalEstuarine, Coastal and Shelf Science
Volume74
Issue number3
DOIs
Publication statusPublished - 1 Sep 2007
Externally publishedYes

Fingerprint

neural networks
artificial neural network
Gulf of Mexico
wave property
significant wave height
simulation
prediction
gulf

Keywords

  • artificial neural network
  • buoy systems
  • correlation analysis
  • missing data
  • water waves

ASJC Scopus subject areas

  • Oceanography
  • Aquatic Science

Cite this

Correlation of wave data from buoy networks. / Londhe, S. N.; Panchang, Vijay.

In: Estuarine, Coastal and Shelf Science, Vol. 74, No. 3, 01.09.2007, p. 481-492.

Research output: Contribution to journalArticle

@article{9d493722739b4d1abf89cb043c1138a1,
title = "Correlation of wave data from buoy networks",
abstract = "Missing oceanographic data resulting from an instrument that is damaged, malfunctioning, or otherwise non-operational can be an impediment to real-time applications of the data and also to statistical calculations pertaining to climatological studies. The problem of reconstructing lost information by correlating oceanographic data from multiple stations is explored through the use of artificial neural networks. A comprehensive simulation study was performed by developing six buoy networks (each containing several buoys) in locations with diverse geographical and wave properties: the northeastern part of the US, the Gulf of Mexico, and Prince William Sound (Alaska). The simulations demonstrate that the missing significant wave heights at the location of one buoy can, for the most part, be reliably reconstructed using artificial neural networks (ANNs) and data from other buoys. ANN model results in the northeastern part of the US tended to suffer from frequent under-prediction, while networks in the Gulf of Mexico and in Prince William Sound showed greater fidelity to measurements. The potential for redeploying some buoys to other locations and using the neural network model instead is examined.",
keywords = "artificial neural network, buoy systems, correlation analysis, missing data, water waves",
author = "Londhe, {S. N.} and Vijay Panchang",
year = "2007",
month = "9",
day = "1",
doi = "10.1016/j.ecss.2007.05.003",
language = "English",
volume = "74",
pages = "481--492",
journal = "Estuarine, Coastal and Shelf Science",
issn = "0272-7714",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - Correlation of wave data from buoy networks

AU - Londhe, S. N.

AU - Panchang, Vijay

PY - 2007/9/1

Y1 - 2007/9/1

N2 - Missing oceanographic data resulting from an instrument that is damaged, malfunctioning, or otherwise non-operational can be an impediment to real-time applications of the data and also to statistical calculations pertaining to climatological studies. The problem of reconstructing lost information by correlating oceanographic data from multiple stations is explored through the use of artificial neural networks. A comprehensive simulation study was performed by developing six buoy networks (each containing several buoys) in locations with diverse geographical and wave properties: the northeastern part of the US, the Gulf of Mexico, and Prince William Sound (Alaska). The simulations demonstrate that the missing significant wave heights at the location of one buoy can, for the most part, be reliably reconstructed using artificial neural networks (ANNs) and data from other buoys. ANN model results in the northeastern part of the US tended to suffer from frequent under-prediction, while networks in the Gulf of Mexico and in Prince William Sound showed greater fidelity to measurements. The potential for redeploying some buoys to other locations and using the neural network model instead is examined.

AB - Missing oceanographic data resulting from an instrument that is damaged, malfunctioning, or otherwise non-operational can be an impediment to real-time applications of the data and also to statistical calculations pertaining to climatological studies. The problem of reconstructing lost information by correlating oceanographic data from multiple stations is explored through the use of artificial neural networks. A comprehensive simulation study was performed by developing six buoy networks (each containing several buoys) in locations with diverse geographical and wave properties: the northeastern part of the US, the Gulf of Mexico, and Prince William Sound (Alaska). The simulations demonstrate that the missing significant wave heights at the location of one buoy can, for the most part, be reliably reconstructed using artificial neural networks (ANNs) and data from other buoys. ANN model results in the northeastern part of the US tended to suffer from frequent under-prediction, while networks in the Gulf of Mexico and in Prince William Sound showed greater fidelity to measurements. The potential for redeploying some buoys to other locations and using the neural network model instead is examined.

KW - artificial neural network

KW - buoy systems

KW - correlation analysis

KW - missing data

KW - water waves

UR - http://www.scopus.com/inward/record.url?scp=34547499076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547499076&partnerID=8YFLogxK

U2 - 10.1016/j.ecss.2007.05.003

DO - 10.1016/j.ecss.2007.05.003

M3 - Article

VL - 74

SP - 481

EP - 492

JO - Estuarine, Coastal and Shelf Science

JF - Estuarine, Coastal and Shelf Science

SN - 0272-7714

IS - 3

ER -