Uncertainty Estimation in Flood Inundation Mapping: An Application of Non‐parametric Bootstrapping

Two types of flooding, namely fluvial flood (FF) and pluvial flash flood (PFF), exist in tropical cities located close to permanent rivers, where extreme precipitation intensity occurs. Although several methods are available for assessment of FF, however, PFF has received minimal attention from the researchers. Studies rarely presented joint FF and PFF hazards. Therefore, the current study not only aims to evaluate probability and hazards for FF and PFF independently but also implements combined FF with PFF probabilistic inundation analysis. First, an integrated model was developed to analyze probability using fully distributed geographic information system (GIS)-based algorithms. These methods were performed on Damansara River Catchment in Kuala Lumpur, because yearly monsoon triggers FFs and simultaneously coincides with heavy local rainfalls. A hydraulic 2D high-resolution sub-grid model of Hydrologic Engineering Center River Analysis System was performed to simulate FF probability and hazard. Nine significant contributing parameters were trained with PFF inventory by GIS-based random forest (RF) model and each RF parameter was optimized by particle swarm optimization algorithm (PSO) to model the PFF probabilistic hazard. Finally, PFF was combined with FF probabilities to discover the impact and contribution of each type of urban flood hazard. This study is the first attempt to model PFF hazard using GIS and physical-based PSO-RF model and combined FF and PFF probabilistic map. The results provide detailed flood information for urban managers to smartly equip infrastructures, such as highways, roads, and sewage network.

show abstract

“…(17), inundation depth of PFF probability was quantified. Hazard was high when PFF inundation depth reached more than 20 cm [50].…”

Section: Hazard Analysis Of Ff and Pff Inundationmentioning

confidence: 98%

An integrated fluvial and flash pluvial model using 2D high-resolution sub-grid and particle swarm optimization-based random forest approaches in GIS

Rizeei

Pradhan

Saharkhiz

2018

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…The first approach is developing hydraulic or hydrologic models for mapping flooded areas, and the second approach is applying classification algorithms for mapping flooded areas. Flood inundation modelling is a complex hydrodynamic process that may contain large uncertainties [3,8]; for this reason, many researchers in their studies have proposed methods to improve over the flooding inundation modelling, as for example, in [3], where the authors proposed an integrated methods of geomatics and fluvial hydraulics to improve the information about flood behaviour.…”

Section: Introductionmentioning

confidence: 99%

Flood Mapping with Convolutional Neural Networks Using Spatio-Contextual Pixel Information

et al. 2019

View full text Add to dashboard Cite

Remote sensing technology in recent years has been regarded the most important source to provide substantial information for delineating the flooding extent to the disaster management authority. There have been numerous studies proposing mathematical or statistical classification models for flood mapping. However, conventional pixel-wise classifications methods rely on the exact match of the spectral signature to label the target pixel. In this study, we propose a fully convolutional neural networks (F-CNNs) classification model to map the flooding extent from Landsat satellite images. We utilised the spatial information from the neighbouring area of target pixel in classification. A total of 64 different models were generated and trained with a variable neighbourhood size of training samples and number of learnable filters. The training results revealed that the model trained with 3 × 3 neighbourhood sized training samples and with 32 convolutional filters achieved the best performance out of the experiments. A new set of different Landsat images covering flooded areas across Australia were used to evaluate the classification performance of the model. A comparison of our proposed classification model to the conventional support vector machines (SVM) classification model shows that the F-CNNs model was able to detect flooded areas more efficiently than the SVM classification model. For example, the F-CNNs model achieved a maximum precision rate (true positives) of 76.7% compared to 45.27% for SVM classification.

show abstract

“…Patel et al [9] carried out a simulation work under the 1D/2D couple hydrodynamic modeling in low-lying areas. Faghih et al [10] applied nonparametric bootstrap sampling to simulate inundation with different flow rates, which provided a reference for the uncertainty analysis of inundation.…”

Section: Hydrodynamic Methodmentioning

confidence: 99%

Estimation Method of Inundation Extent Based on Mathematical Morphology

Lai

Safonov

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Estimation of inundation extent is critical for the flood control system. It helps decision-maker determine the scope of damage to save residents' lives and property. In this paper, we analyzed the drawbacks of two kinds of methods of inundation estimation, hydrodynamic method and space-filling method, and divided inundation extent into water-body extent and water-invasion extent for the purpose of enhancing estimation accuracy. Based on Mathematical Morphology, an inundation estimation method suitable for flood mapping around natural and artificial lakes was put forward by integrating remote sensing (RS) data and digital elevation model (DEM) data. is method consists of three aspects, including the subdivision of water-body extent, the deduction of water-invasion extent which is viewed as the expansion of water-body extent, and the smoothing the boundaries of waterinvasion extent. With subdividing DEM data horizontally into cross sections to build equiangular subsets, the expansion operation was implemented by structuring elements which were established based on set operations and scalar flexibilities. us, water-invasion extent was easily described by the structuring elements under given water volume, so that inundation extent was conveniently estimated by spatial data. e experiment results show that the method has the advantages of high accuracy and expressiveness and low time consumption. It had been used to analyze the inundation caused by the water conservancy project named Hanjiang-to-Weihe River Water Transfer Project in China. e method served as decision support for building an efficient emergency response mechanism and helped implement flood disaster forecast and simulation.

show abstract

Uncertainty Estimation in Flood Inundation Mapping: An Application of Non‐parametric Bootstrapping

Cited by 29 publications

References 58 publications

An integrated fluvial and flash pluvial model using 2D high-resolution sub-grid and particle swarm optimization-based random forest approaches in GIS

An integrated fluvial and flash pluvial model using 2D high-resolution sub-grid and particle swarm optimization-based random forest approaches in GIS

Flood Mapping with Convolutional Neural Networks Using Spatio-Contextual Pixel Information

Estimation Method of Inundation Extent Based on Mathematical Morphology

Contact Info

Product

Resources

About