5 Hours ahead of time flood water level prediction modelling using NNARX technique: Case study terengganu

Qammarul Arieff Lukman, Fazlina Ahmat Ruslan, Ramli Adnan

Research output: ResearchConference contribution

Abstract

Flood is an overflowing of a large amount of water beyond its normal confines, especially over what is normally called dry land. Therefore, flood prediction system is crucial in order to notify the public about the incoming flood and an important task to achieve. The flood prediction may be very useful especially in the east cost of Malaysia. Artificial Neural Network (ANN) is well-known as an effective method to solve nonlinear problems and Nonlinear Auto Regression with Exogenous Input (NARX) is one of the classes of ANN. The case study of this research was at Terengganu originated from three upstream rivers which were Sungai Besut at Jambatan Jerteh, Sungai Besut at Kampung La, and Sungai Dungun at Kampung Pasir Raja while for the downstream was Sungai Besut at Jambatan Keruak. The model was developed by processing offline data obtained from JPS upon special request. 641 data collected from 9/1/2014 till 14/1/2014 were used for training, 641 data collected from 9/6/2014 till 13/6/2014 were used for validation which are to create the modeling part. As for testing data samples, 1351 data were collected starting from 16/11/2014 till 25/11/2014. Results showed that NNARX model successfully predicted flood water level 5 hours ahead of time.

LanguageEnglish
Title of host publication2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages104-108
Number of pages5
ISBN (Electronic)9781509011759
DOIs
StatePublished - Jan 10 2017
Event2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Shah Alam, Selangor, Malaysia
Duration: Aug 8 2016 → …

Other

Other2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016
CountryMalaysia
CityShah Alam, Selangor
Period8/8/16 → …

Fingerprint

Water
Prediction
Modeling
predictions
water
Water levels
flood predictions
Artificial Neural Network
Model
Neural networks
Malaysia
rivers
upstream
regression analysis
education
costs
Autoregression
Nonlinear Problem
Testing
Costs

All Science Journal Classification (ASJC) codes

  • Engineering (miscellaneous)
  • Control and Optimization
  • Modelling and Simulation
  • Instrumentation

Cite this

Lukman, Q. A., Ruslan, F. A., & Adnan, R. (2017). 5 Hours ahead of time flood water level prediction modelling using NNARX technique: Case study terengganu. In 2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding (pp. 104-108). [7813310] Institute of Electrical and Electronics Engineers Inc.. DOI: 10.1109/ICSGRC.2016.7813310

5 Hours ahead of time flood water level prediction modelling using NNARX technique : Case study terengganu. / Lukman, Qammarul Arieff; Ruslan, Fazlina Ahmat; Adnan, Ramli.

2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2017. p. 104-108 7813310.

Research output: ResearchConference contribution

Lukman, QA, Ruslan, FA & Adnan, R 2017, 5 Hours ahead of time flood water level prediction modelling using NNARX technique: Case study terengganu. in 2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding., 7813310, Institute of Electrical and Electronics Engineers Inc., pp. 104-108, 2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016, Shah Alam, Selangor, Malaysia, 8/8/16. DOI: 10.1109/ICSGRC.2016.7813310
Lukman QA, Ruslan FA, Adnan R. 5 Hours ahead of time flood water level prediction modelling using NNARX technique: Case study terengganu. In 2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding. Institute of Electrical and Electronics Engineers Inc.2017. p. 104-108. 7813310. Available from, DOI: 10.1109/ICSGRC.2016.7813310
Lukman, Qammarul Arieff ; Ruslan, Fazlina Ahmat ; Adnan, Ramli. / 5 Hours ahead of time flood water level prediction modelling using NNARX technique : Case study terengganu. 2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 104-108
@inbook{0f813091a7fd4e738a55fcdad200d7e2,
title = "5 Hours ahead of time flood water level prediction modelling using NNARX technique: Case study terengganu",
abstract = "Flood is an overflowing of a large amount of water beyond its normal confines, especially over what is normally called dry land. Therefore, flood prediction system is crucial in order to notify the public about the incoming flood and an important task to achieve. The flood prediction may be very useful especially in the east cost of Malaysia. Artificial Neural Network (ANN) is well-known as an effective method to solve nonlinear problems and Nonlinear Auto Regression with Exogenous Input (NARX) is one of the classes of ANN. The case study of this research was at Terengganu originated from three upstream rivers which were Sungai Besut at Jambatan Jerteh, Sungai Besut at Kampung La, and Sungai Dungun at Kampung Pasir Raja while for the downstream was Sungai Besut at Jambatan Keruak. The model was developed by processing offline data obtained from JPS upon special request. 641 data collected from 9/1/2014 till 14/1/2014 were used for training, 641 data collected from 9/6/2014 till 13/6/2014 were used for validation which are to create the modeling part. As for testing data samples, 1351 data were collected starting from 16/11/2014 till 25/11/2014. Results showed that NNARX model successfully predicted flood water level 5 hours ahead of time.",
author = "Lukman, {Qammarul Arieff} and Ruslan, {Fazlina Ahmat} and Ramli Adnan",
year = "2017",
month = "1",
doi = "10.1109/ICSGRC.2016.7813310",
pages = "104--108",
booktitle = "2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - CHAP

T1 - 5 Hours ahead of time flood water level prediction modelling using NNARX technique

T2 - Case study terengganu

AU - Lukman,Qammarul Arieff

AU - Ruslan,Fazlina Ahmat

AU - Adnan,Ramli

PY - 2017/1/10

Y1 - 2017/1/10

N2 - Flood is an overflowing of a large amount of water beyond its normal confines, especially over what is normally called dry land. Therefore, flood prediction system is crucial in order to notify the public about the incoming flood and an important task to achieve. The flood prediction may be very useful especially in the east cost of Malaysia. Artificial Neural Network (ANN) is well-known as an effective method to solve nonlinear problems and Nonlinear Auto Regression with Exogenous Input (NARX) is one of the classes of ANN. The case study of this research was at Terengganu originated from three upstream rivers which were Sungai Besut at Jambatan Jerteh, Sungai Besut at Kampung La, and Sungai Dungun at Kampung Pasir Raja while for the downstream was Sungai Besut at Jambatan Keruak. The model was developed by processing offline data obtained from JPS upon special request. 641 data collected from 9/1/2014 till 14/1/2014 were used for training, 641 data collected from 9/6/2014 till 13/6/2014 were used for validation which are to create the modeling part. As for testing data samples, 1351 data were collected starting from 16/11/2014 till 25/11/2014. Results showed that NNARX model successfully predicted flood water level 5 hours ahead of time.

AB - Flood is an overflowing of a large amount of water beyond its normal confines, especially over what is normally called dry land. Therefore, flood prediction system is crucial in order to notify the public about the incoming flood and an important task to achieve. The flood prediction may be very useful especially in the east cost of Malaysia. Artificial Neural Network (ANN) is well-known as an effective method to solve nonlinear problems and Nonlinear Auto Regression with Exogenous Input (NARX) is one of the classes of ANN. The case study of this research was at Terengganu originated from three upstream rivers which were Sungai Besut at Jambatan Jerteh, Sungai Besut at Kampung La, and Sungai Dungun at Kampung Pasir Raja while for the downstream was Sungai Besut at Jambatan Keruak. The model was developed by processing offline data obtained from JPS upon special request. 641 data collected from 9/1/2014 till 14/1/2014 were used for training, 641 data collected from 9/6/2014 till 13/6/2014 were used for validation which are to create the modeling part. As for testing data samples, 1351 data were collected starting from 16/11/2014 till 25/11/2014. Results showed that NNARX model successfully predicted flood water level 5 hours ahead of time.

UR - http://www.scopus.com/inward/record.url?scp=85012034456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012034456&partnerID=8YFLogxK

U2 - 10.1109/ICSGRC.2016.7813310

DO - 10.1109/ICSGRC.2016.7813310

M3 - Conference contribution

SP - 104

EP - 108

BT - 2016 7th IEEE Control and System Graduate Research Colloquium, ICSGRC 2016 - Proceeding

PB - Institute of Electrical and Electronics Engineers Inc.

ER -