GIS-based spatial prediction of flood prone areas using standalone frequency ratio, logistic regression, weight of evidence and their ensemble techniques

Abstract

The aim of this research was to evaluate the predictive performances of frequency ratio (FR), logistic regression (LR) and weight of evidence (WoE), in flood susceptibility mapping in China. In addition, the ensemble WoE and LR and ensemble FR and LR techniques were applied and used in the evaluation. The flood inventory map, consisting of 196 flood locations, was extracted from a number of sources. The flood inventory data were randomly divided into a testing data-set, allocating 70% for training, and the remaining 30% for validation. The 15 flood conditioning factors included in the spatial database were altitude, slope, aspect, geology, distance from river, distance from road, distance from fault, soil type, land use/cover, rainfall, Normalized Difference Vegetation Index, Stream Power Index, Topographic Wetness Index, Sediment Transport Index and curvature. For validation, success and prediction rate curves were developed using area under the curve (AUC) method. The results indicated that the highest prediction rate of 90.36% was achieved using the ensemble technique of WoE and LR. The standalone WoE produced the highest prediction rate among the individual methods. It can be concluded that WoE offers a more advanced method of mapping prone areas, compared with the FR and LR methods.

Flood vulnerability mapping using frequency ratio (FR) model: a case study on Kulik river basin, Indo-Bangladesh Barind region

“…A high number of floods occur in lower slope area as the water cannot discharge swiftly. Slope between 0° and 10.59° supports the fact of flooding as the FR value is considerably more than one (Tehrany et al 2017). High slope indirectly enhances the flood probability as it fosters speedy water and the area with high slope has the less time to regulate and percolate water under the ground (Jaiswal et al 2003).…”

“…Slope and elevation maps ( Fig. 4a, b) of the study area have been prepared from DEM by using ArcGIS software (Khosravi et al 2016;Tehrany et al 2017). Slope and elevation are most important factors for flood vulnerability assessment.…”

“…Amount of flow accumulation at any point in the catchment area can be calculated by TWI technique, and it shows the flow of water under the influence of gravity (Moore et al 1991). TWI is a very effective technique for analysing flood potentiality (Rahmati et al 2016a, b, c, d;Haghizadeh et al 2017;Samanta et al 2018a, b;Khosravi et al 2016;Ali et al 2019;Tehrany et al 2015Tehrany et al , 2017. TWI map has been constructed from DEM by running flowing equation on Raster Calculator in ArcGIS environment (Regmi et al 2010;Moore et al 1991;Jaafari et al 2014;Nampak et al 2014;Ali et al 2019): where FLOWACC is the flow accumulation derived from DEM in ArcGIS environment and β is the slope (in °).…”

“…Across the globe in every year, different kinds of natural as well as man-induced hazards and disasters like floods, earthquakes and landslides are causing a large amount of life loss and property damage (Youssef et al 2011;Du et al 2013;WHO 2003;Tehrany et al 2017). Floods occur when there is an overflow of huge volume of water beyond its normal limits, causing inundation of river banks and water stagnation for temporary season.…”

“…Frequency ratio (FR) model (Lee et al 2012) is one of the highly acceptable techniques for hazards assessment with high accuracy rate. Frequency ratio (FR) is a one kind of bivariate statistical analysis (BSA), and this method gives value to every single class of each parameter and evaluates its impact on flood occurrence (Jebur et al 2014;Tehrany et al 2017). FR model is a simple process to run on GIS environment and can construct scientifically valid flood vulnerably map (Tehrany et al 2014a, b;Liao and Carin 2009;Samanta et al 2018a, b).…”