Development of a novel hybrid multi-boosting neural network model for spatial prediction of urban flood

Abstract

In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models.

Nordic contributions to stochastic methods in hydrology

“…The complicated interaction between different risk-related mechanisms in WRM cannot be easily modelled to characterize the system response under different risk control settings. Flood management is usually addressed from a risk viewpoint to quantify the hazard and depth of inundation and to consider the susceptibility to flooding (Oliver et al 2019;Andaryani et al 2021;Darabi et al 2021). Various stochastics techniques have been used to assess the risk in WRM and related concerns, particularly for extreme events during floods and droughts.…”

Toward an Integrated Disaster Management Approach: How Artificial Intelligence Can Boost Disaster Management

“…Such approaches enable flood notifications and verification in real-time, thus significantly reducing the time spent on investigations [39]. Darabi et al [83] applied ML algorithms to calculate the flood-related region in Amol city, Iran, using geospatial predictor variables. The distance to channel, land use, and run-off generation were identified as the primary causes of flood hazards [84].…”