Development of novel hybridized models for urban flood susceptibility mapping

Abstract

Floods in urban environments often result in loss of life and destruction of property, with many negative socio-economic effects. However, the application of most flood prediction models still remains challenging due to data scarcity. This creates a need to develop novel hybridized models based on historical urban flood events, using, e.g., metaheuristic optimization algorithms and wavelet analysis. The hybridized models examined in this study (Wavelet-SVR-Bat and Wavelet-SVR-GWO), designed as intelligent systems, consist of a support vector regression (SVR), integrated with a combination of wavelet transform and metaheuristic optimization algorithms, including the grey wolf optimizer (GWO), and the bat optimizer (Bat). The efficiency of the novel hybridized and standalone SVR models for spatial modeling of urban flood inundation was evaluated using different cutoff-dependent and cutoff-independent evaluation criteria, including area under the receiver operating characteristic curve (AUC), Accuracy (A), Matthews Correlation Coefficient (MCC), Misclassification Rate (MR), and F-score. The results demonstrated that both hybridized models had very high performance (Wavelet-SVR-GWO: AUC = 0.981, A = 0.92, MCC = 0.86, MR = 0.07; Wavelet-SVR-Bat: AUC = 0.972, A = 0.88, MCC = 0.76, MR = 0.11) compared with the standalone SVR (AUC = 0.917, A = 0.85, MCC = 0.7, MR = 0.15). Therefore, these hybridized models are a promising, cost-effective method for spatial modeling of urban flood susceptibility and for providing in-depth insights to guide flood preparedness and emergency response services.

Evaluasi Kualitas Infrastruktur Fasilitas Pendidikan Dasar Di Provinsi Jawa Barat Indonesia Menggunakan Pendekatan Berbasis Model Multi-Hazard Dan Aksesibilitas

“…Selain itu terdapatnya zona subduksi di Selatan Jawa dapat menimbulkan ancaman gempa bumi yang lebih besar (Widiyantoro et al, 2020). Berbagai macam bentuk bumi dan urbanisasi Provinsi Jawa Barat juga menimbulkan peningkatan resiko bencana alam lain seperti banjir dan longsor (Rahmati et al, 2020;Reichenbach et al, 2014). Bencana-bencana yang mungkin terjadi dapat mengancam keselamatan dan keamanan dari sarana pendidikan di Jawa Barat apabila tidak dipersiapkan dengan baik.…”

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

“…Urban planning and policy can reduce the adverse impacts of floods (Brody et al 2007(Brody et al , 2017. High-accuracy flood susceptibility maps that identify areas susceptible to flooding can help in this effort to mitigate losses (B€ uchele et al 2006;Ahmadisharaf and Kalyanapu 2019;Darabi et al 2019;Rahmati et al 2020).…”

“…Flood susceptibility mapping has also been conducted using machine learning, statistical and data-mining models like support vector machine ( Zhao et al 2019), random forest (Feng et al 2015;Lee et al 2017), logistic regression (Pradhan 2010;Lee et al 2018;Tehrany et al 2019), rule-based decision tree (Tehrany et al 2013), weights-of-evidence (Tehrany et al 2014;, frequency ratio (Youssef et al 2016), adaptive neuro-fuzzy inference system Termeh et al 2018;Costache 2019), kmeans cluster algorithm (Xu et al 2018), Shannon's entropy (Haghizadeh et al 2017), maximum entropy (Siahkamari et al 2018), genetic algorithm rule set production (Darabi et al 2020), boosted regression trees (Lee et al 2017), evidential belief function (Tehrany and Kumar 2018), classification and regression trees (Choubin et al 2019), alternating decision tree (Rahmati et al 2020), reduced-error pruning trees (Chen et al 2019) and naïve Bayes (Chen et al 2020). Recently, Bui et al (2020) developed a new deep-learning neural network algorithm for spatial modelling of flood susceptibility in Vietnam.…”

A New Hybrid Firefly–PSO Optimized Random Subspace Tree Intelligence for Torrential Rainfall-Induced Flash Flood Susceptible Mapping

“…In recent years, the rapid development of innovative technologies involved earth observations (EO), geographic information system (GIS)-based approaches, and machine learning techniques, which have been proven as promising tools to account for the complexity of spatial flood modeling [12]. Importantly, the integration of satellite remotely sensed imagery and GIS data had been proven as an effective way to map and evaluate flash flood damages [13,14]. For instance, Klemas [14] reported the use of satellite imagery and modeling techniques to predict flood vulnerability, whereas Lee et al [15] reported the usability of the random forest methods for mapping flood vulnerability in the metropolis.…”

“…Importantly, the integration of satellite remotely sensed imagery and GIS data had been proven as an effective way to map and evaluate flash flood damages [13,14]. For instance, Klemas [14] reported the use of satellite imagery and modeling techniques to predict flood vulnerability, whereas Lee et al [15] reported the usability of the random forest methods for mapping flood vulnerability in the metropolis. Recently, Khosravi, et al [16] used GIS-based frequency and weight ratio statistical bivariate statistical models for mapping flash flooding susceptibility.…”