UPM Institutional Repository

Flood modelling using an integrated Artificial Neural Network and Neuro-Fuzzy technique for Johor River Basin, Malaysia


Kia, Masoud Bakhtyari (2013) Flood modelling using an integrated Artificial Neural Network and Neuro-Fuzzy technique for Johor River Basin, Malaysia. PhD thesis, Universiti Putra Malaysia.


Flooding is one of the most destructive natural hazards that cause damage to both life and property every year, and therefore the development of flood model to determine inundation area in watersheds is important for decision makers. In recent years, data mining approaches such as artificial neural network (ANN) and Neuro-Fuzzy techniques are being increasingly used for flood modeling. Previously, these methods were frequently used for hydrological and flood modeling by taking rainfall as input and runoff data as output, usually without taking into consideration of other flood causative factors. The specific objective of this study is to develop a flood model using various flood causative factors by Multilayer Perceptron neural network MLP) and Local Linear Model Tree (LOLIMOT) techniques, and geographic information system (GIS) to modeling and simulate flood-prone areas in the southern part of Peninsular Malaysia. The ANN and Neuro-Fuzzy models for this study were developed in MATLAB using seven flood causative factors. Relevant thematic layers (including rainfall, slope, elevation, flow accumulation, soil, land use, and geology) are generated using GIS, and field surveys. In the context of objective weight assignments, the ANN is used to directly produce water levels and then the flood map is constructed in GIS. Comparison between the forecasted and observed river flow indicate that the accuracy of models are quite good especially in ANN model. The flood inundation area is derived based on this model by using DEM map. To measure the performance of the model, four criteria performances, including coefficient of determination (R2), the sum squared error, the mean square error, and the root mean square error are used. The verification results showed satisfactory agreement between the predicted and the real hydrological records. The sensitivity analysis performed shows that with the exception of the rainfall factor as the main reason of floods, the elevation is the most important factor and geology has the least influence on river flow. The study is first attempt to use these integration methods in the flood modeling that used different causative factors. The results of this study could be used to help local and national government plan for the future and develop appropriate (to the local environmental conditions) new infrastructure to protect the lives and property of the people of Johor.

Download File

FK 2013 113RR.pdf

Download (1MB) | Preview

Additional Metadata

Item Type: Thesis (PhD)
Subject: Flow visualization
Subject: Detectors
Subject: Water resources development - Malaysia
Call Number: FK 2013 113
Chairman Supervisor: Saied Pirasteh, PhD
Divisions: Faculty of Engineering
Depositing User: Haridan Mohd Jais
Date Deposited: 20 Jul 2017 11:31
Last Modified: 20 Jul 2017 11:31
URI: http://psasir.upm.edu.my/id/eprint/56170
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item