Multi-hazard could exacerbate in coastal Bangladesh in the context of climate change

Abstract

Floods and landslides have cascading effects on coastal areas of Bangladesh. This study aims to develop multi-hazard maps (e.g., floods and landslides) for the coastal region, by integrating a genetic algorithm optimizer with Long Short-Term Memory deep learning algorithm (GA-LSTM-DLA), global climate model, and geospatial data. It assesses vulnerabilities to multiple hazards and projects future risks considering the Australian Community Climate and Earth System Simulator Earth System Model 1.5 (ACCESS-ESM1-5) under three climate scenarios, i.e., Shared Socioeconomic Pathways1-2.6, 2–4.5, and 5–8.5 (SSP1-2.6, SSP2-4.5, and SSP5-8.5). The Receiver Operating Characteristic (ROC) curve is used to assess the performance of GA-LSTM-DLA model. According to important feature obtained by random forest (RF) algorithm, most important features for flash, riverine, tidal floods, and landslides are drainage density, rainfall, and geology, respectively. The baseline susceptibility maps for flash, riverine, tidal floods, and landslides are initially recorded as 0.11%, 7.99%, 3.46%, and 0.03%. Projections for the year 2100, under different SSPs, show significant increase, i.e., SSP1-2.6—flash 1.31%, riverine 23.74%, tidal 26.97%, landslides 2.05%; SSP2-4.5—flash 0.12%, riverine 30.97%, tidal 10.23%, landslides 0.18%; SSP5-8.5—flash 0.02%, riverine 17.42%, tidal 6.19%, landslides 0.14%. These projections highlight urgent need for mitigation and adaptation measures against hazards susceptibility, particularly under more extreme socioeconomic scenarios. Overall, the findings of this work are critical for policymakers to develop informed strategies for climate resilience, sustainable development, and disaster risk reduction in the coastal region of Bangladesh.