Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/486918Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Ahmed H. El-Shafie, Prof. Dr. | - |
| dc.contributor.author | Mohammad Rostami Nia (P52302) | - |
| dc.date.accessioned | 2023-10-11T02:26:33Z | - |
| dc.date.available | 2023-10-11T02:26:33Z | - |
| dc.date.issued | 2017-12-12 | - |
| dc.identifier.other | ukmvital:108429 | - |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/486918 | - |
| dc.description | The ground slope is normally ignored in numerous infiltration models, especially in large scale regions. These models' survey infiltration carry the assumption that the slope of the ground is zero. Although, it is of importance to consider the surface slope effects while studying the infiltration process in any watershed, there are a few models which consider the slope in their calculations such as Green and Ampt models. In this context, the current study presents an integration of Artificial Neural Networks with Geographic Information System in a raster-based format. The efficiency of six different slope functions were examined and assessed in order to determine the best performance of slope function in the modified Green and Ampt models. In addition, three different artificial intelligence models with different transfer functions (Log-Sigmoid, PURELIN and Tan-Sigmoid) representing infiltration calculations have been obtained. Three different sub basins (Pengeli, Sayong and Linggiu) with different slopes based on existing runoff stations in the upstream region of the Johor River Basin in the south of Malaysia, were used to investigate the accuracy of the proposed model. The proposed models have been calibrated and validated utilizing the real data from the three study areas by six different efficiency functions (RMSE, 𝑅2, NASH, Spearman, Kendall and Gamma). It was finally concluded that the modified Green and Ampt models using the exponential form of the cosine for the slope in the formulation were more accurate (𝑅2 in Pengeli basin: 96.3%; Sayong basin: 91.5%; Linggiu basin: 94.6%) in comparison with original linear shape. In addition, it determines that the most suitable transfer function to simulate the infiltration is the log-sigmoid. It is also indicated that the presented model has an acceptable capability to simulate the runoff when the rate of the rainfall is very high or low (extreme data).,"Certification of Master's/Doctoral Thesis" is not available,Ph.D. | - |
| dc.language.iso | eng | - |
| dc.publisher | UKM, Bangi | - |
| dc.relation | Faculty of Engineering and Built Environment / Fakulti Kejuruteraan dan Alam Bina | - |
| dc.rights | UKM | - |
| dc.subject | Geographic information systems | - |
| dc.subject | Hydrologic models | - |
| dc.subject | Rivers -- Johor | - |
| dc.subject | Universiti Kebangsaan Malaysia -- Dissertations | - |
| dc.subject | Dissertations, Academic -- Malaysia | - |
| dc.title | An integrated GIS-ann-based model for infiltration estimation (case study: Johor River Basin) | - |
| dc.type | Theses | - |
| dc.format.pages | 116 | - |
| dc.identifier.callno | G70.212.N533 2017 3 tesis | - |
| dc.identifier.barcode | 003912(2019) | - |
| Appears in Collections: | Faculty of Engineering and Built Environment / Fakulti Kejuruteraan dan Alam Bina | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_108429+SOURCE1+SOURCE1.0.PDF Restricted Access | 1.6 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.