Cover Image

Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia)

Predicted total sediment load is usually used to identify the intensity of a sedimentation process. Currently, the existing available models to predict total load are mostly developed based on data collected from flumes, channels and rivers located in western countries. These models may not be valid...

Full description

Saved in:
Bibliographic Details
Main Authors: Nadiatul Adilah, Ahmad Abdul Ghani, Junaidah, Ariffin
Format: Conference or Workshop Item
Language:English
Published: 2017
Subjects:
T Technology (General)
Online Access:http://umpir.ump.edu.my/id/eprint/18901/1/Improving%20Total%20Sediment%20Load%20Prediction%20using1.pdf
http://umpir.ump.edu.my/id/eprint/18901/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ump.umpir.18901
record_format eprints
spelling my.ump.umpir.189012018-07-30T07:05:35Z http://umpir.ump.edu.my/id/eprint/18901/ Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia) Nadiatul Adilah, Ahmad Abdul Ghani Junaidah, Ariffin T Technology (General) Predicted total sediment load is usually used to identify the intensity of a sedimentation process. Currently, the existing available models to predict total load are mostly developed based on data collected from flumes, channels and rivers located in western countries. These models may not be valid to predict sediment transport of rivers in the Tropics due to significant differences in the hydrological and sediment characteristics conditions. A new model using genetic programming (GE) technique is used to improve the prediction of sediment load for rivers in tropical Malaysia. Methods/StatisticalAnalysis: The model predictions are compared with those obtained from five available sediment transport models, including Engelund & Hansen (1967), Graf (1971), Ariffin (2004), Chan et al. (2005) and Sinnakaudan et al. (2006). Findings: The performance of the model in relation to the test set shows less scattering around the line of equality, between the measured and predicted total sediment loads. Statistical analyses of 68 data sets give the coefficient of correlation, r and the discrepancy ratio of 0.82 and 0.53 respectively. Application/Improvements: Hence, the GE Technique used in the prediction of Total Sediment Load is found to give better accuracy compared to other methods. 2017 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/18901/1/Improving%20Total%20Sediment%20Load%20Prediction%20using1.pdf Nadiatul Adilah, Ahmad Abdul Ghani and Junaidah, Ariffin (2017) Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia). In: Fluids and Chemical Engineering Conference (FluidsChE 2017), 4-6 April 2017 , Kota Kinabalu, Sabah, Malaysia. .
institution Universiti Malaysia Pahang
building UMP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Pahang
content_source UMP Institutional Repository
url_provider http://umpir.ump.edu.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Nadiatul Adilah, Ahmad Abdul Ghani
Junaidah, Ariffin
Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia)
description Predicted total sediment load is usually used to identify the intensity of a sedimentation process. Currently, the existing available models to predict total load are mostly developed based on data collected from flumes, channels and rivers located in western countries. These models may not be valid to predict sediment transport of rivers in the Tropics due to significant differences in the hydrological and sediment characteristics conditions. A new model using genetic programming (GE) technique is used to improve the prediction of sediment load for rivers in tropical Malaysia. Methods/StatisticalAnalysis: The model predictions are compared with those obtained from five available sediment transport models, including Engelund & Hansen (1967), Graf (1971), Ariffin (2004), Chan et al. (2005) and Sinnakaudan et al. (2006). Findings: The performance of the model in relation to the test set shows less scattering around the line of equality, between the measured and predicted total sediment loads. Statistical analyses of 68 data sets give the coefficient of correlation, r and the discrepancy ratio of 0.82 and 0.53 respectively. Application/Improvements: Hence, the GE Technique used in the prediction of Total Sediment Load is found to give better accuracy compared to other methods.
format Conference or Workshop Item
author Nadiatul Adilah, Ahmad Abdul Ghani
Junaidah, Ariffin
author_facet Nadiatul Adilah, Ahmad Abdul Ghani
Junaidah, Ariffin
author_sort Nadiatul Adilah, Ahmad Abdul Ghani
title Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia)
title_short Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia)
title_full Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia)
title_fullStr Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia)
title_full_unstemmed Improving Total Sediment Load Prediction using the GE Technique (Case Study: Malaysia)
title_sort improving total sediment load prediction using the ge technique (case study: malaysia)
publishDate 2017
url http://umpir.ump.edu.my/id/eprint/18901/1/Improving%20Total%20Sediment%20Load%20Prediction%20using1.pdf
http://umpir.ump.edu.my/id/eprint/18901/
_version_ 1643668558723416064
score 13.211869

Similar Items