Normal view MARC view ISBD view

Flood forecasting by using artificial neural network (ANN) in Kuala Krai, Kelantan / Noorfarhana Idayu Ibrahim

By:

Noorfarhana Idayu Ibrahim [author.]

Material type: Text

text

Media type:

unmediated
computer

Carrier type:

volume
computer disc

ISBN:

THE0008324(Local)

Subject(s):

Dissertation note: Project Paper (Bachelors of Civil Engineering) -- Universiti Malaysia Pahang – 2018 Abstract: Developing flood forecasting is necessity especially for east coast peninsular Malaysia that experienced flood every year due to northeast monsoon and when it coincides with monsoon that gave harm and damages to human life. A case study of flood is going to be conduct to analyze the pattern of water level and to determine other causes that contributes to the flood. A strong performance of forecasting model for water level could be a solution to minimize bad impact of flood. It is also used to develop high accuracy model utilizing Artificial Neural Network (ANN) in predicting flood. Furthermore, Artificial Neural Network (ANN) use historical data to find data pattern to make data forecasting. Historical data require generating the result by forecast a model. In the study area of station number is 5222452, Sungai Lebir at Kelantan River where hourly water level data for past 30 years dated from 1986 until 2016 that gained from Drainage and Irrigation Department, Ampang have been used to forecast hourly water level. In this study were using Multilayer Perceptron Neural Network (MLP) technique. MLP is known as a supervised feed forward back propagation learning ANN model. Besides that, three type of time interval 1, 3 and 6 hour and 6 types of data input which are 2, 3, 4, 5, 6 and 7 were analyzed. Result showed that all data input successfully achieve high accuracy forecasting result where 0.8 to 1 for NSC value were recorded as strong performance. Therefore, the best performance was occurred in one hour interval time with the architecture 2-2-1.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 2 )
Title notes ( 4 )

Holdings
Item type	Current library	Collection	Call number	Status	Date due	Barcode
Thesis	UMPLIB GAMBANG Reference	Reference	FKASA .I33 2018 r Bc. (Browse shelf(Opens below))	Not for loan		0000127222
Thesis	UMPLIB GAMBANG Reference	Reference	CD12106 (Browse shelf(Opens below))	Not for loan		0000127223

Faculty of Civil Engineering and Earth Resources

Project Paper (Bachelors of Civil Engineering) -- Universiti Malaysia Pahang – 2018

Includes bibliographical references

Developing flood forecasting is necessity especially for east coast peninsular Malaysia that experienced flood every year due to northeast monsoon and when it coincides with monsoon that gave harm and damages to human life. A case study of flood is going to be conduct to analyze the pattern of water level and to determine other causes that contributes to the flood. A strong performance of forecasting model for water level could be a solution to minimize bad impact of flood. It is also used to develop high accuracy model utilizing Artificial Neural Network (ANN) in predicting flood. Furthermore, Artificial Neural Network (ANN) use historical data to find data pattern to make data forecasting. Historical data require generating the result by forecast a model. In the study area of station number is 5222452, Sungai Lebir at Kelantan River where hourly water level data for past 30 years dated from 1986 until 2016 that gained from Drainage and Irrigation Department, Ampang have been used to forecast hourly water level. In this study were using Multilayer Perceptron Neural Network (MLP) technique. MLP is known as a supervised feed forward back propagation learning ANN model. Besides that, three type of time interval 1, 3 and 6 hour and 6 types of data input which are 2, 3, 4, 5, 6 and 7 were analyzed. Result showed that all data input successfully achieve high accuracy forecasting result where 0.8 to 1 for NSC value were recorded as strong performance. Therefore, the best performance was occurred in one hour interval time with the architecture 2-2-1.