Flood prediction of Sungai Bedup, Serian, Sarawak, Malaysia using deep learning

This study aims to evaluate the performance of the Long Short Term Memory (LSTM) model for flood forecasting. Seven water level data sets provided by the Department of Irrigation and Drainage (DID) for Sungai Bedup, Serian, Kuching, Sarawak, Malaysia are used for evaluating the performances of this...

Full description

Saved in:
Bibliographic Details
Main Author: Roselind, Tei
Format: Final Year Project Report
Language:English
English
Published: Universiti Malaysia Sarawak (UNIMAS) 2018
Subjects:
Online Access:http://ir.unimas.my/id/eprint/29088/1/Flood%20prediction%20of%20Sungai%20Bedup%2C%20Serian%2C%20Sarawak%2C%20Malaysia%20using%20deep%20learning%20%2824%20pgs%29.pdf
http://ir.unimas.my/id/eprint/29088/4/Roselind%20Tei%20ft.pdf
http://ir.unimas.my/id/eprint/29088/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study aims to evaluate the performance of the Long Short Term Memory (LSTM) model for flood forecasting. Seven water level data sets provided by the Department of Irrigation and Drainage (DID) for Sungai Bedup, Serian, Kuching, Sarawak, Malaysia are used for evaluating the performances of this algorithm. Distinctive network was trained and tested using daily data obtained from the DID Department in Kuching with the year range from 2014 to 2017. The performances of the algorithm were evaluated based on (Training Error, Testing Error, Loss, Accuracy, Validate Loss and Validate Accuracy, respectively) and compared with the Backpropagation neural network (BP). Among the seven data sets, Sungai Bedup showed a small testing rate which is (0.08), followed by Bukit Matuh (0.11), Sungai Teb (0.14), Sungai Merang (0.15), Sungai Meringgu (0.12), Semuja Nonok (0.14) and lastly is Sungai Busit (0.13). The performance of the developed model is evaluated by comparing them with BP model. Results from this study evidently proved that LSTM models is reliable to forecasting flood with the lowest testing error rate which is (0.08) and highest validate accuracy (92.61% ) compared to Bp with the testing error rate (0.711) and validate accuracy (85.00%). Discussion is provided to prove the effectiveness of the model in forecasting flood problems.