Caspian Sea level prediction using satellite altimetry by artificial neural networks

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

The demand for accurate predictions of sea level fluctuations in coastal management and ship navigation activities is increasing. To meet such demand, accessible high-quality data and proper modeling process are critically required. This study focuses on developing and validating a neural methodology applicable to the short-term forecast of the Caspian Sea level. The input and output data sets used contain two time series obtained from Topex/Poseidon and Jason-1 satellite altimetry missions from 1993 to 2008. The forecast is performed by multilayer perceptron network, radial basis function, and generalized regression neural networks. Several tests of different artificial neural network (ANN) architectures and learning algorithms are carried out as alternative methods to the conventional models to assess their applicability for estimating Caspian Sea level anomalies. The results derived from the ANN are compared with observed sea level values and with the forecasts calculated by a routine autoregressive moving average (ARMA) model. Different ANNs satisfactorily provide reliable results for the short-term prediction of Caspian Sea level anomalies. The root mean square errors of the differences between observations and predictions from artificial intelligence approaches can be significantly reduced by about 50 % compared with ARMA techniques.

Original languageEnglish
Pages (from-to)1035-1042
Number of pages8
JournalInternational Journal of Environmental Science and Technology
Volume11
Issue number4
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Spacecraft
Caspian Sea
satellite altimetry
Sea level
Oceans and Seas
artificial neural network
neural networks
sea level
Satellites
Neural networks
prediction
anomaly
Neural Networks (Computer)
Radial basis function networks
Ships
artificial intelligence
Artificial Intelligence
coastal zone management
Multilayer neural networks
ships

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Environmental Chemistry
  • Agricultural and Biological Sciences(all)

Cite this

@article{b98fa70d94f64bb59731c8ad755c2d02,
title = "Caspian Sea level prediction using satellite altimetry by artificial neural networks",
abstract = "The demand for accurate predictions of sea level fluctuations in coastal management and ship navigation activities is increasing. To meet such demand, accessible high-quality data and proper modeling process are critically required. This study focuses on developing and validating a neural methodology applicable to the short-term forecast of the Caspian Sea level. The input and output data sets used contain two time series obtained from Topex/Poseidon and Jason-1 satellite altimetry missions from 1993 to 2008. The forecast is performed by multilayer perceptron network, radial basis function, and generalized regression neural networks. Several tests of different artificial neural network (ANN) architectures and learning algorithms are carried out as alternative methods to the conventional models to assess their applicability for estimating Caspian Sea level anomalies. The results derived from the ANN are compared with observed sea level values and with the forecasts calculated by a routine autoregressive moving average (ARMA) model. Different ANNs satisfactorily provide reliable results for the short-term prediction of Caspian Sea level anomalies. The root mean square errors of the differences between observations and predictions from artificial intelligence approaches can be significantly reduced by about 50 {\%} compared with ARMA techniques.",
author = "M. Imani and Rey-Jer You and Chung-Yen Kuo",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s13762-013-0287-z",
language = "English",
volume = "11",
pages = "1035--1042",
journal = "International Journal of Environmental Science and Technology",
issn = "1735-1472",
publisher = "CEERS",
number = "4",

}

TY - JOUR

T1 - Caspian Sea level prediction using satellite altimetry by artificial neural networks

AU - Imani, M.

AU - You, Rey-Jer

AU - Kuo, Chung-Yen

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The demand for accurate predictions of sea level fluctuations in coastal management and ship navigation activities is increasing. To meet such demand, accessible high-quality data and proper modeling process are critically required. This study focuses on developing and validating a neural methodology applicable to the short-term forecast of the Caspian Sea level. The input and output data sets used contain two time series obtained from Topex/Poseidon and Jason-1 satellite altimetry missions from 1993 to 2008. The forecast is performed by multilayer perceptron network, radial basis function, and generalized regression neural networks. Several tests of different artificial neural network (ANN) architectures and learning algorithms are carried out as alternative methods to the conventional models to assess their applicability for estimating Caspian Sea level anomalies. The results derived from the ANN are compared with observed sea level values and with the forecasts calculated by a routine autoregressive moving average (ARMA) model. Different ANNs satisfactorily provide reliable results for the short-term prediction of Caspian Sea level anomalies. The root mean square errors of the differences between observations and predictions from artificial intelligence approaches can be significantly reduced by about 50 % compared with ARMA techniques.

AB - The demand for accurate predictions of sea level fluctuations in coastal management and ship navigation activities is increasing. To meet such demand, accessible high-quality data and proper modeling process are critically required. This study focuses on developing and validating a neural methodology applicable to the short-term forecast of the Caspian Sea level. The input and output data sets used contain two time series obtained from Topex/Poseidon and Jason-1 satellite altimetry missions from 1993 to 2008. The forecast is performed by multilayer perceptron network, radial basis function, and generalized regression neural networks. Several tests of different artificial neural network (ANN) architectures and learning algorithms are carried out as alternative methods to the conventional models to assess their applicability for estimating Caspian Sea level anomalies. The results derived from the ANN are compared with observed sea level values and with the forecasts calculated by a routine autoregressive moving average (ARMA) model. Different ANNs satisfactorily provide reliable results for the short-term prediction of Caspian Sea level anomalies. The root mean square errors of the differences between observations and predictions from artificial intelligence approaches can be significantly reduced by about 50 % compared with ARMA techniques.

UR - http://www.scopus.com/inward/record.url?scp=84897518786&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897518786&partnerID=8YFLogxK

U2 - 10.1007/s13762-013-0287-z

DO - 10.1007/s13762-013-0287-z

M3 - Article

VL - 11

SP - 1035

EP - 1042

JO - International Journal of Environmental Science and Technology

JF - International Journal of Environmental Science and Technology

SN - 1735-1472

IS - 4

ER -