Bui Quynh Duy, Luu Chinh, Mai Sy Hung, Ha Hang Thi, Ta Huong Thu, Pham Binh Thai
Faculty of Bridges and Roads, Hanoi University of Civil Engineering, Hanoi, Vietnam.
Faculty of Hydraulic Engineering, Hanoi University of Civil Engineering, Hanoi, Vietnam.
Risk Anal. 2023 Jul;43(7):1478-1495. doi: 10.1111/risa.14018. Epub 2022 Sep 11.
In this study, a new approach of machine learning (ML) models integrated with the analytic hierarchy process (AHP) method was proposed to develop a holistic flood risk assessment map. Flood susceptibility maps were created using ML techniques. AHP was utilized to combine flood vulnerability and exposure criteria. We selected Quang Binh province of Vietnam as a case study and collected available data, including 696 flooding locations of historical flooding events in 2007, 2010, 2016, and 2020; and flood influencing factors of elevation, slope, curvature, flow direction, flow accumulation, distance from river, river density, land cover, geology, and rainfall. These data were used to construct training and testing datasets. The susceptibility models were validated and compared using statistical techniques. An integrated flood risk assessment framework was proposed to incorporate flood hazard (flood susceptibility), flood exposure (distance from river, land use, population density, and rainfall), and flood vulnerability (poverty rate, number of freshwater stations, road density, number of schools, and healthcare facilities). Model validation suggested that deep learning has the best performance of AUC = 0.984 compared with other ensemble models of MultiBoostAB Ensemble (0.958), Random SubSpace Ensemble (0.962), and credal decision tree (AUC = 0.918). The final flood risk map shows 5075 ha (0.63%) in extremely high risk, 47,955 ha (5.95%) in high-risk, 40,460 ha (5.02%) in medium risk, 431,908 ha (53.55%) in low risk areas, and 281,127 ha (34.86%) in very low risk. The present study highlights that the integration of ML models and AHP is a promising framework for mapping flood risks in flood-prone areas.
在本研究中，提出了一种将机器学习（ML）模型与层次分析法（AHP）相结合的新方法，以绘制整体洪水风险评估图。利用ML技术创建洪水易发性地图。运用AHP来综合洪水脆弱性和暴露标准。我们选择越南广平省作为案例研究，并收集了可用数据，包括2007年、2010年、2016年和2020年历史洪水事件的696个洪水发生地点；以及海拔、坡度、曲率、流向、流量累积、距河流距离、河流密度、土地覆盖、地质和降雨等洪水影响因素。这些数据用于构建训练和测试数据集。使用统计技术对易发性模型进行验证和比较。提出了一个综合洪水风险评估框架，纳入洪水危险（洪水易发性）、洪水暴露（距河流距离、土地利用、人口密度和降雨）和洪水脆弱性（贫困率、淡水站数量、道路密度、学校数量和医疗设施）。模型验证表明，与MultiBoostAB集成模型（0.958）、随机子空间集成模型（0.962）和信念决策树（AUC = 0.918）等其他集成模型相比，深度学习具有最佳性能，AUC = 0.984。最终的洪水风险地图显示，极高风险区域为5075公顷（0.63%），高风险区域为47955公顷（5.95%），中风险区域为40460公顷（5.02%），低风险区域为431908公顷（53.55%），极低风险区域为281127公顷（34.86%）。本研究强调，ML模型与AHP的集成是绘制洪水易发地区洪水风险图的一个有前景的框架。
