Integrating Entropy‐Based Naïve Bayes and GIS for Spatial Evaluation of Flood Hazard

• Published in: Risk analysis 2017-04, Vol.37 (4), p.756-773
• Main Authors: Liu, Rui, Chen, Yun, Wu, Jianping, Gao, Lei, Barrett, Damian, Xu, Tingbao, Li, Xiaojuan, Li, Linyi, Huang, Chang, Yu, Jia
• Format: Article
• Language: English
• Subjects: Climatic conditions; Density; Disaster management; Entropy; Environmental hazards; Environmental risk; Evaluation; Evapotranspiration; Extreme weather; Flood hazards; Flood mapping; Flooding; Floods; Geographic information systems; Hazard assessment; Hydrology; Imagery; Inundation; likelihood; Mapping; MODIS; Moisture content; Proximity; Rainfall; Regional analysis; Remote sensing; risk; Risk assessment; River basins; Soil formation; Soil water; Spatial data; Spectroradiometers; Topography; uncertainty; Vegetation; Water
• ISSN: 0272-4332; 1539-6924
• DOI: 10.1111/risa.12698

Regional flood risk caused by intensive rainfall under extreme climate conditions has increasingly attracted global attention. Mapping and evaluation of flood hazard are vital parts in flood risk assessment. This study develops an integrated framework for estimating spatial likelihood of flood hazard by coupling weighted naïve Bayes (WNB), geographic information system, and remote sensing. The north part of Fitzroy River Basin in Queensland, Australia, was selected as a case study site. The environmental indices, including extreme rainfall, evapotranspiration, net‐water index, soil water retention, elevation, slope, drainage proximity, and density, were generated from spatial data representing climate, soil, vegetation, hydrology, and topography. These indices were weighted using the statistics‐based entropy method. The weighted indices were input into the WNB‐based model to delineate a regional flood risk map that indicates the likelihood of flood occurrence. The resultant map was validated by the maximum inundation extent extracted from moderate resolution imaging spectroradiometer (MODIS) imagery. The evaluation results, including mapping and evaluation of the distribution of flood hazard, are helpful in guiding flood inundation disaster responses for the region. The novel approach presented consists of weighted grid data, image‐based sampling and validation, cell‐by‐cell probability inferring and spatial mapping. It is superior to an existing spatial naive Bayes (NB) method for regional flood hazard assessment. It can also be extended to other likelihood‐related environmental hazard studies.