TY - GEN A1 - Kim, Dongeon A1 - Sun, Yabin A1 - Wendi, Dadiyorto A1 - Jiang, Ze A1 - Liong, Shie-Yui A1 - Gourbesville, Philippe T1 - Flood modelling framework for Kuching City, Malaysia BT - Overcoming the Lack of Data T2 - Advances in Hydroinformatics: SimHydro 2017 - Choosing The Right Model in Applied Hydraulics N2 - Several areas in Southeast Asia are very vulnerable to climate change and unable to take immediate/effective actions on countermeasures due to insufficient capabilities. Malaysia, in particular the east coast of peninsular Malaysia and Sarawak, is known as one of the vulnerable regions to flood disaster. Prolonged and intense rainfall, natural activities and increase in runoff are the main reasons to cause flooding in this area. In addition, topographic conditions also contribute to the occurrence of flood disaster. Kuching city is located in the northwest of Borneo Island and part of Sarawak river catchment. This area is a developing state in Malaysia experiencing rapid urbanization since 2000s, which has caused the insufficient data availability in topography and hydrology. To deal with these challenging issues, this study presents a flood modelling framework using the remote sensing technologies and machine learning techniques to acquire the digital elevation model (DEM) with improved accuracy for the non-surveyed areas. Intensity–duration–frequency (IDF) curves were derived from climate model for various scenario simulations. The developed flood framework will be beneficial for the planners, policymakers, stakeholders as well as researchers in the field of water resource management in the aspect of providing better ideas/tools in dealing with the flooding issues in the region. Y1 - 2018 SN - 978-981-10-7218-5 SN - 978-981-10-7217-8 U6 - https://doi.org/10.1007/978-981-10-7218-5_39 SN - 2364-6934 SN - 2364-8198 SP - 559 EP - 568 PB - Springer CY - Singapore ER - TY - JOUR A1 - Wendi, Dadiyorto A1 - Liong, Shie-Yui A1 - Sun, Yabin A1 - Doan, Chi Dung T1 - An innovative approach to improve SRTM DEM using multispectral imagery and artificial neural network JF - Journal of advances in modeling earth systems N2 - Although the Shuttle Radar Topography Mission [SRTM) data are a publicly accessible Digital Elevation Model [DEM) provided at no cost, its accuracy especially at forested area is known to be limited with root mean square error (RMSE) of approx. 14 m in Singapore's forested area. Such inaccuracy is attributed to the 5.6 cm wavelength used by SRTM that does not penetrate vegetation well. This paper considers forested areas of central catchment of Singapore as a proof of concept of an approach to improve the SRTM data set. The approach makes full use of (1) the introduction of multispectral imagery (Landsat 8), of 30 m resolution, into SRTM data; (2) the Artificial Neural Network (ANN) to flex its known strengths in pattern recognition and; (3) a reference DEM of high accuracy (1 m) derived through the integration of stereo imaging of worldview-1 and extensive ground survey points. The study shows a series of significant improvements of the SRTM when assessed with the reference DEM of 2 different areas, with RMSE reduction of ∼68% (from 13.9 m to 4.4 m) and ∼52% (from 14.2 m to 6.7 m). In addition, the assessment of the resulting DEM also includes comparisons with simple denoising methodology (Low Pass Filter) and commercially available product called NEXTMap® World 30™. KW - SRTM improvements KW - Landsat 8 KW - ANN Y1 - 2016 U6 - https://doi.org/10.1002/2015MS000536 SN - 1942-2466 VL - 8 SP - 691 EP - 702 PB - American Geophysical Union CY - Washington ER -