Flood mapping of Northern Peninsular Malaysia using SAR images
Malaysia is one of the evident countries whose recurrence of floods proves that floods are getting worse. The northern peninsular of Malaysia has lost a lot of lives and property worth billions to the series of floods that have been occurring for many years. Many disaster management strategies have...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/51412/25/HafsatSalehDutsenwaiMFGHT2014.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Malaysia is one of the evident countries whose recurrence of floods proves that floods are getting worse. The northern peninsular of Malaysia has lost a lot of lives and property worth billions to the series of floods that have been occurring for many years. Many disaster management strategies have been adopted by the Malaysian government in handling these flood disasters but it is still a topic in the annual agenda. This research project aimed at using fusion techniques in mapping the flood extents in the northern peninsular Malaysia in order to contribute to the flood disaster eradication by extracting more and better information through the fusion of RadarSat 1 and TerraSAR-X images. The Principal Component Analysis was also used and compared with the fusion techniques which include the Hue Saturation and Value (HSV), the Brovey Transformation (BT), the Gram Schmidt (GS), and the Principal Component Spectral Sharpening (PCSS). The best principal component of the PCA, that is the PC2 which classified and compared with the classification of the other fusion techniques using Maximum likelihood (ML) and support Vector Machine (SVM). The results indicated BT technique has the highest overall accuracy of 70.9615% and kappa coefficient of 0.3418. This method showed relative improvement on the classification of the flooded and non-flooded area which was used to produce the flood extent Map that was further validated with the DEM data. The final results in this study showed that more information on the areas that are affected by the floods especially the extents, became more exposed after the classification of the fused images. |
|---|