Determination of flood-inducing rainfall and runoff for highly urbanized area based on high-resolution radar-gauge composite rainfall data and flooded area GIS data

Flood Susceptibility Mapping Using Image-Based 2D-CNN Deep Learning: Overview and Case Study Application Using Multiparametric Spatial Data in Data-Scarce Urban Environments

“…Based on the slope of the case study area, the residential areas with high population concentrations along the river are the most affected by both the river and urban fooding. Te susceptibility results are closely related to the urban patterns such that when fooding occurs, the inner city and the low-laying residential areas are the most susceptible [31,40]. Te susceptibility assessments demonstrate that food adaptations are required in the case study area.…”

“…Given the drawbacks of the 1D-CNN and 3D-CNN models and the fact that food conditioning factors comprise of 2D-spatial images, image-based 2D-CNN is proposed in this study for FSM as it can efciently capture the spatial relationship between the neighboring environmental parameters. Further to the positive results in 2-D image processing [40], the conventional 2D-CNN has demonstrated superior results as compared to 1D-CNN, LeNet-5, 3D-CNN, and other machine learning methods like SVM and Decision Tree [35]. Te other advantage is that 2D-CNN allows diferent outputs to be run to reach an optimum result and employs a linear or unbiased variable selection model.…”

A Monte Carlo simulation and sensitivity analysis framework demonstrating the advantages of probabilistic forecasting over deterministic forecasting in terms of flood warning reliability

“…Barbetta et al (2017) evaluated a deterministic and probabilistic hydrometric threshold-based warning decision strategy in terms of hits, missed events, and false alarms for the Tiber River, in central Italy. Dao et al (2020) used a deterministic rainfall threshold-based warning decision strategy to evaluate the flood warning reliability associated with an urban FEWS through hits, missed events, and false alarms in a more recent case study. There has been limited research that explores how deterministic and probabilistic warning strategies behave in the face of perturbations of factors controlling the forecast quality associated with peak water levels.…”

Estimation of rainfall threshold for flood warning for small urban watersheds based on the 1D–2D drainage model simulation

“…However, it is difficult to implement these methods for the urban flood analysis because of the challenges in detecting the urban flooding due to fast watershed response time (Emmanuel et al, 2012;Einfalt et al, 2004) and complex flooding mechanisms governed by drainage pipe network settings, terrain, and landcover (Chen et al, 2009, Zhang et al,2014. Dao et al (2020a) overcame this issue by using the flooded area data obtained from two massive field observation campaigns across the city of Seoul. A database containing every single flooded building during the two major flood events of 2010 and 2011 for 239 watersheds was used in the study.…”