Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean
A study implementing Nonlinear Autoregressive with Exogenous Input (NARX) neural network has been undertaken to predict monthly and seasonal SST anomalies in the western Indian Ocean. The study involves a coastal site located along the eastern African seashore, and an oceanic site that lies precisel...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
SAGE Publishing
2013-06-01
|
Series: | International Journal of Ocean and Climate Systems |
Online Access: | https://doi.org/10.1260/1759-3131.4.2.133 |
id |
doaj-f38e9f22b1f94d6bac0a1093b9dbd25e |
---|---|
record_format |
Article |
spelling |
doaj-f38e9f22b1f94d6bac0a1093b9dbd25e2020-11-25T02:11:09ZengSAGE PublishingInternational Journal of Ocean and Climate Systems1759-31311759-314X2013-06-01410.1260/1759-3131.4.2.13310.1260_1759-3131.4.2.133Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian OceanS. B. Mahongo0M. C. Deo1 Senior Researcher, Tanzania Fisheries Research Institute (TAFIRI), Institute Headquarters, P.O. Box 9750, Dar es Salaam, Tanzania Professor, Department of Civil Engineering, Indian Institute of Technology Bombay, Powai, Mumbai - 400 076, IndiaA study implementing Nonlinear Autoregressive with Exogenous Input (NARX) neural network has been undertaken to predict monthly and seasonal SST anomalies in the western Indian Ocean. The study involves a coastal site located along the eastern African seashore, and an oceanic site that lies precisely within the western pole of the Indian Ocean Dipole. Performance of the network is measured by a series of statistical indicators during testing phase (1981–2010), and results are compared with outputs from three other neural networks and a linear system, the Autoregressive Integrated Moving Average with Exogenous Input (ARIMAX) model. The NARX network has provided the best overall performance, but the other four models have also given sufficiently good predictions. The monthly predictions are on average within an error of ±0.09°C for the first 50% and 90% within ±0.22°C. The corresponding errors for the seasonal predictions are ±0.04°C and ±0.09°C, respectively. The RMSE between observations and predictions is about 0.13°C and 0.06°C for the monthly and seasonal SST anomalies, while the average correlation coefficient is about 0.88 and 0.98, respectively.https://doi.org/10.1260/1759-3131.4.2.133 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
S. B. Mahongo M. C. Deo |
spellingShingle |
S. B. Mahongo M. C. Deo Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean International Journal of Ocean and Climate Systems |
author_facet |
S. B. Mahongo M. C. Deo |
author_sort |
S. B. Mahongo |
title |
Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean |
title_short |
Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean |
title_full |
Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean |
title_fullStr |
Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean |
title_full_unstemmed |
Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean |
title_sort |
using artificial neural networks to forecast monthly and seasonal sea surface temperature anomalies in the western indian ocean |
publisher |
SAGE Publishing |
series |
International Journal of Ocean and Climate Systems |
issn |
1759-3131 1759-314X |
publishDate |
2013-06-01 |
description |
A study implementing Nonlinear Autoregressive with Exogenous Input (NARX) neural network has been undertaken to predict monthly and seasonal SST anomalies in the western Indian Ocean. The study involves a coastal site located along the eastern African seashore, and an oceanic site that lies precisely within the western pole of the Indian Ocean Dipole. Performance of the network is measured by a series of statistical indicators during testing phase (1981–2010), and results are compared with outputs from three other neural networks and a linear system, the Autoregressive Integrated Moving Average with Exogenous Input (ARIMAX) model. The NARX network has provided the best overall performance, but the other four models have also given sufficiently good predictions. The monthly predictions are on average within an error of ±0.09°C for the first 50% and 90% within ±0.22°C. The corresponding errors for the seasonal predictions are ±0.04°C and ±0.09°C, respectively. The RMSE between observations and predictions is about 0.13°C and 0.06°C for the monthly and seasonal SST anomalies, while the average correlation coefficient is about 0.88 and 0.98, respectively. |
url |
https://doi.org/10.1260/1759-3131.4.2.133 |
work_keys_str_mv |
AT sbmahongo usingartificialneuralnetworkstoforecastmonthlyandseasonalseasurfacetemperatureanomaliesinthewesternindianocean AT mcdeo usingartificialneuralnetworkstoforecastmonthlyandseasonalseasurfacetemperatureanomaliesinthewesternindianocean |
_version_ |
1724915951404580864 |