Flooding and its relationship with land cover change, population growth, and road density

• DOI: 10.1016/j.gsf.2021.101224
• Publication Date: 2021-05-05T06:32:45Z
• Authors: Mahfuzur Rahman; Chen Ningsheng; Golam Iftekhar Ma...; Md Monirul Islam; Hamid Reza Pourgh...; Hilal Ahmad; Jules Maurice Hab...; Rana Muhammad Ali...; Mehtab Alam; Enlong Liu; Zheng Han; Huayong Ni; Tian Shufeng; Ashraf Dewan
• Keywords: Land Cover

Bangladesh experiences frequent hydro-climatic disasters such as flooding. These are believed to be associated with land use changes and climate variability. However, identifying the factors that lead flooding is challenging. This study mapped flood susceptibility in northeast region of using Bayesian regularization back propagation (BRBP) neural network, classification regression trees (CART), a statistical model (STM) evidence belief function (EBF), their ensemble models (EMs) for three time periods (2000, 2014, 2017). The accuracy machine learning algorithms (MLAs), STM, EMs were assessed by considering area under curve—receiver operating characteristic (AUC-ROC). Evaluation levels aforementioned revealed EM4 (BRBP-CART-EBF) outperformed (AUC > 90%) standalone other analyzed. Furthermore, this investigated relationships among cover change (LCC), population growth (PG), road density (RD), relative (RCF) areas period between 2000 2017. results showed very high increased 19.72% 2017, while PG rate 51.68% over same period. Pearson correlation coefficient RCF RD was calculated 0.496. findings highlight significant association floods causative factors. could valuable policymakers resource managers they can improvements management reduction damage risks.