Investigating the impact of wind on sea level rise using multilayer perceptron neural network (MLP-NN) at coastal area, Sabah

T. Olivia Muslim, A. Najah Ahmed, Marlinda Abdul Malek, A. El-Shafie, Amr EL-Shafie

Research output: Contribution to journalArticle

Abstract

This study investigating the impact of wind on sea level rise (SLR) using Multilayer Perceptron Neural Network (MLP-NN) at Coastal Area, Sabah. The mean sea level (MSL) and four meteorology parameters namely; wind direction (WD), wind speed (WS), rainfall and mean cloud cover. These meteorological parameter and MSL were monitored regularly each month over a period from January 2007 to December 2016 at three different locations which is Kudat, Kota Kinabalu and Sandakan. Due to small amount of data set, both method the input data were divided into 80 % for training and 20% for testing data respectively.In this study, two scenarios were introduced; the scenario 1 (with wind) WD and WS as input parameter while scenario 2 (without wind)rainfall and mean cloud cover to predict sea level at each stations. Then by using previous monthly sea water level records the model was performed by predicting SLR for1 year, 5 years, 10 years, 30 years, and 50 years ahead in the future. The performance of the models was evaluated according to three statistical indices in terms of the correlation coefficient (R), root mean square error (RMSE) and scatter index (SI). Investigation results indicate that, when compared to measurements, for 50 years prediction, all three models in scenario 2 perform well (with average values of R = 0.6, RMSE = 0.2 cm and SI = 0.4).

Original languageEnglish
Pages (from-to)646-656
Number of pages11
JournalInternational Journal of Civil Engineering and Technology
Volume9
Issue number12
Publication statusPublished - 01 Dec 2018

Fingerprint

Sea level
Multilayer neural networks
Neural networks
Mean square error
Rain
Meteorology
Water levels
Testing

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Civil and Structural Engineering
  • Building and Construction
  • Computer Networks and Communications

Cite this

@article{ba21155cbc874784b279aab8a5fdc398,
title = "Investigating the impact of wind on sea level rise using multilayer perceptron neural network (MLP-NN) at coastal area, Sabah",
abstract = "This study investigating the impact of wind on sea level rise (SLR) using Multilayer Perceptron Neural Network (MLP-NN) at Coastal Area, Sabah. The mean sea level (MSL) and four meteorology parameters namely; wind direction (WD), wind speed (WS), rainfall and mean cloud cover. These meteorological parameter and MSL were monitored regularly each month over a period from January 2007 to December 2016 at three different locations which is Kudat, Kota Kinabalu and Sandakan. Due to small amount of data set, both method the input data were divided into 80 {\%} for training and 20{\%} for testing data respectively.In this study, two scenarios were introduced; the scenario 1 (with wind) WD and WS as input parameter while scenario 2 (without wind)rainfall and mean cloud cover to predict sea level at each stations. Then by using previous monthly sea water level records the model was performed by predicting SLR for1 year, 5 years, 10 years, 30 years, and 50 years ahead in the future. The performance of the models was evaluated according to three statistical indices in terms of the correlation coefficient (R), root mean square error (RMSE) and scatter index (SI). Investigation results indicate that, when compared to measurements, for 50 years prediction, all three models in scenario 2 perform well (with average values of R = 0.6, RMSE = 0.2 cm and SI = 0.4).",
author = "{Olivia Muslim}, T. and {Najah Ahmed}, A. and {Abdul Malek}, Marlinda and A. El-Shafie and Amr EL-Shafie",
year = "2018",
month = "12",
day = "1",
language = "English",
volume = "9",
pages = "646--656",
journal = "International Journal of Civil Engineering and Technology",
issn = "0976-6308",
publisher = "IAEME Publication",
number = "12",

}

Investigating the impact of wind on sea level rise using multilayer perceptron neural network (MLP-NN) at coastal area, Sabah. / Olivia Muslim, T.; Najah Ahmed, A.; Abdul Malek, Marlinda; El-Shafie, A.; EL-Shafie, Amr.

In: International Journal of Civil Engineering and Technology, Vol. 9, No. 12, 01.12.2018, p. 646-656.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Investigating the impact of wind on sea level rise using multilayer perceptron neural network (MLP-NN) at coastal area, Sabah

AU - Olivia Muslim, T.

AU - Najah Ahmed, A.

AU - Abdul Malek, Marlinda

AU - El-Shafie, A.

AU - EL-Shafie, Amr

PY - 2018/12/1

Y1 - 2018/12/1

N2 - This study investigating the impact of wind on sea level rise (SLR) using Multilayer Perceptron Neural Network (MLP-NN) at Coastal Area, Sabah. The mean sea level (MSL) and four meteorology parameters namely; wind direction (WD), wind speed (WS), rainfall and mean cloud cover. These meteorological parameter and MSL were monitored regularly each month over a period from January 2007 to December 2016 at three different locations which is Kudat, Kota Kinabalu and Sandakan. Due to small amount of data set, both method the input data were divided into 80 % for training and 20% for testing data respectively.In this study, two scenarios were introduced; the scenario 1 (with wind) WD and WS as input parameter while scenario 2 (without wind)rainfall and mean cloud cover to predict sea level at each stations. Then by using previous monthly sea water level records the model was performed by predicting SLR for1 year, 5 years, 10 years, 30 years, and 50 years ahead in the future. The performance of the models was evaluated according to three statistical indices in terms of the correlation coefficient (R), root mean square error (RMSE) and scatter index (SI). Investigation results indicate that, when compared to measurements, for 50 years prediction, all three models in scenario 2 perform well (with average values of R = 0.6, RMSE = 0.2 cm and SI = 0.4).

AB - This study investigating the impact of wind on sea level rise (SLR) using Multilayer Perceptron Neural Network (MLP-NN) at Coastal Area, Sabah. The mean sea level (MSL) and four meteorology parameters namely; wind direction (WD), wind speed (WS), rainfall and mean cloud cover. These meteorological parameter and MSL were monitored regularly each month over a period from January 2007 to December 2016 at three different locations which is Kudat, Kota Kinabalu and Sandakan. Due to small amount of data set, both method the input data were divided into 80 % for training and 20% for testing data respectively.In this study, two scenarios were introduced; the scenario 1 (with wind) WD and WS as input parameter while scenario 2 (without wind)rainfall and mean cloud cover to predict sea level at each stations. Then by using previous monthly sea water level records the model was performed by predicting SLR for1 year, 5 years, 10 years, 30 years, and 50 years ahead in the future. The performance of the models was evaluated according to three statistical indices in terms of the correlation coefficient (R), root mean square error (RMSE) and scatter index (SI). Investigation results indicate that, when compared to measurements, for 50 years prediction, all three models in scenario 2 perform well (with average values of R = 0.6, RMSE = 0.2 cm and SI = 0.4).

UR - http://www.scopus.com/inward/record.url?scp=85059245752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059245752&partnerID=8YFLogxK

M3 - Article

VL - 9

SP - 646

EP - 656

JO - International Journal of Civil Engineering and Technology

JF - International Journal of Civil Engineering and Technology

SN - 0976-6308

IS - 12

ER -