Rainfall-based river flow prediction using NARX in Malaysia

Hassanuddin Mohamed Noor; David Ndzi; Guangguang Yang

doi:10.1109/CSPA.2017.8064926

Rainfall-based river flow prediction using NARX in Malaysia

Hassanuddin Mohamed Noor, David Ndzi, Guangguang Yang

Faculty of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Flood forecasting is one of the most important and demanding operational responsibilities carried out by meteorological services all over the world. This task is complicated in the field of meteorology because all decisions have to consider in the visage of physiographical uncertainty factors such as the land coverage and vegetation, type of soil and topology of the catchment area [1][2]. This paper shows that the Nonlinear Autoregressive Exogenous (NARX) model can successfully to model a flow of the rivers 24 hours in advance based on current rainfall rates.

Original language	English
Title of host publication	2017 IEEE 13th International Colloquium on Signal Processing & its Applications
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	67-72
ISBN (Electronic)	978-1509011841
ISBN (Print)	978-1509011858
DOIs	https://doi.org/10.1109/CSPA.2017.8064926
Publication status	Published - 12 Oct 2017
Event	2017 IEEE 13th International Colloquium on Signal Processing & its Applications - Batu Ferringhi, Malaysia Duration: 10 Mar 2017 → 12 Mar 2017

Conference

Conference	2017 IEEE 13th International Colloquium on Signal Processing & its Applications
Abbreviated title	CSPA
Country/Territory	Malaysia
City	Batu Ferringhi
Period	10/03/17 → 12/03/17

Keywords

rivers
floods
predictive models
artifical neural networks
training
reservoirs
neurons
artificial neural network (ANN)
flow rate prediction

Access to Document

10.1109/CSPA.2017.8064926

Cite this

@inproceedings{eeb4807913094930a67c6979cca5fd12,

title = "Rainfall-based river flow prediction using NARX in Malaysia",

abstract = "Flood forecasting is one of the most important and demanding operational responsibilities carried out by meteorological services all over the world. This task is complicated in the field of meteorology because all decisions have to consider in the visage of physiographical uncertainty factors such as the land coverage and vegetation, type of soil and topology of the catchment area [1][2]. This paper shows that the Nonlinear Autoregressive Exogenous (NARX) model can successfully to model a flow of the rivers 24 hours in advance based on current rainfall rates.",

keywords = "rivers, floods, predictive models, artifical neural networks, training, reservoirs, neurons, artificial neural network (ANN), flow rate prediction",

author = "Noor, {Hassanuddin Mohamed} and David Ndzi and Guangguang Yang",

note = "Academic has left, so post-print is unavailable.; 2017 IEEE 13th International Colloquium on Signal Processing & its Applications, CSPA ; Conference date: 10-03-2017 Through 12-03-2017",

year = "2017",

month = oct,

day = "12",

doi = "10.1109/CSPA.2017.8064926",

language = "English",

isbn = "978-1509011858",

pages = "67--72",

booktitle = "2017 IEEE 13th International Colloquium on Signal Processing & its Applications",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Noor, HM, Ndzi, D & Yang, G 2017, Rainfall-based river flow prediction using NARX in Malaysia. in 2017 IEEE 13th International Colloquium on Signal Processing & its Applications. Institute of Electrical and Electronics Engineers Inc., pp. 67-72, 2017 IEEE 13th International Colloquium on Signal Processing & its Applications, Batu Ferringhi, Malaysia, 10/03/17. https://doi.org/10.1109/CSPA.2017.8064926

TY - GEN

T1 - Rainfall-based river flow prediction using NARX in Malaysia

AU - Noor, Hassanuddin Mohamed

AU - Ndzi, David

AU - Yang, Guangguang

N1 - Academic has left, so post-print is unavailable.

PY - 2017/10/12

Y1 - 2017/10/12

N2 - Flood forecasting is one of the most important and demanding operational responsibilities carried out by meteorological services all over the world. This task is complicated in the field of meteorology because all decisions have to consider in the visage of physiographical uncertainty factors such as the land coverage and vegetation, type of soil and topology of the catchment area [1][2]. This paper shows that the Nonlinear Autoregressive Exogenous (NARX) model can successfully to model a flow of the rivers 24 hours in advance based on current rainfall rates.

AB - Flood forecasting is one of the most important and demanding operational responsibilities carried out by meteorological services all over the world. This task is complicated in the field of meteorology because all decisions have to consider in the visage of physiographical uncertainty factors such as the land coverage and vegetation, type of soil and topology of the catchment area [1][2]. This paper shows that the Nonlinear Autoregressive Exogenous (NARX) model can successfully to model a flow of the rivers 24 hours in advance based on current rainfall rates.

KW - rivers

KW - floods

KW - predictive models

KW - artifical neural networks

KW - training

KW - reservoirs

KW - neurons

KW - artificial neural network (ANN)

KW - flow rate prediction

U2 - 10.1109/CSPA.2017.8064926

DO - 10.1109/CSPA.2017.8064926

M3 - Conference contribution

SN - 978-1509011858

SP - 67

EP - 72

BT - 2017 IEEE 13th International Colloquium on Signal Processing & its Applications

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE 13th International Colloquium on Signal Processing & its Applications

Y2 - 10 March 2017 through 12 March 2017

ER -

Rainfall-based river flow prediction using NARX in Malaysia

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this