Multiscale modeling of backward erosion piping in flood protection system infrastructure

Fascetti, Alessandro; Oskay, Caglar

doi:10.1111/mice.12489

Cited by 20 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, generative adversarial networks (GANs) are successfully adopted for detecting the road damages (Maeda, Kashiyama, Sekimoto, Seto, & Omata, 2020). A multilayer ML technique has been used to simulate failure in flood protection systems (Fascetti & Oskay, 2019). ML techniques are also used to develop early warning systems that inform infrastructure protection during disaster events.…”

Section: Literature Reviewmentioning

confidence: 99%

A hybrid deep learning model for predictive flood warning and situation awareness using channel network sensors data

Dong

Farahmand

et al. 2020

Computer aided Civil Eng

View full text Add to dashboard Cite

The objective of this study is to create and test a hybrid deep learning (DL) model, FastGRNN‐FCN (fast, accurate, stable and tiny gated recurrent neural network‐fully convolutional network), for urban flood prediction and situation awareness using channel network sensors data. The study used Harris County, Texas, as the testbed, and obtained channel sensor data from three historical flood events (e.g., 2016 Tax Day Flood, 2016 Memorial Day Flood, and 2017 Hurricane Harvey Flood) for training and validating the hybrid DL model. The flood data are divided into a multivariate time series and used as the model input. Each input comprises nine variables, including information of the studied channel sensor and its predecessor and successor sensors in the channel network. Precision‐recall curve and F‐measure are used to identify the optimal set of model parameters. The optimal model with a weight of 1 and a critical threshold of 0.59 are obtained through 100 iterations based on examining different weights and thresholds. The test accuracy and F‐measure eventually reach 97.8% and 0.792, respectively. The model is then tested in predicting the 2019 Imelda Flood in Houston and the results show an excellent match with the empirical flood. The results show that the model enables accurate prediction of the spatial–temporal flood propagation and recession and provides emergency response officials with a predictive flood warning tool for prioritizing the flood response and resource allocation strategies.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A hybrid deep learning model for predictive flood warning and situation awareness using channel network sensors data

Dong

Farahmand

et al. 2020

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…Dong et al, 2020S. Dong et al, , 2021Fascetti & Oskay, 2019). Unlike refueling liquid fuels for conventional gasoline vehicles, recharging the battery on an EV needs a much longer time.…”

Section: Problem Settingsmentioning

confidence: 99%

“…Instead of fully avoiding high‐risk areas, an optimized placement considering the magnitude of flood inundations can minimize the impact of flood hazards and simultaneously maximize the socio‐economic benefit of charging station networks. With the risk awareness in advance, the minimized but inevitable impacts can be alleviated and compensated by precautionary actions, such as elevating critical utilities and installing water alarms (Cheng et al., 2021; S. Dong et al., 2020, 2021; Fascetti & Oskay, 2019).…”

Section: Problem Settingsmentioning

confidence: 99%

Optimal planning of flood‐resilient electric vehicle charging stations

Zhang

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

This study is the first attempt to integrate flood resilience into the electric vehicle (EV) charging station planning process. Instead of fully avoiding flood-prone areas, an optimized placement considering the magnitude of flood inundations can minimize the impact of flood hazards and simultaneously maximize the socio-economic benefit of EV charging station networks. In this study, an integrated framework of the non-dominated sorting genetic algorithm-III (NSGA-III) and the technique for order of preference by similarity to ideal solution (TOPSIS) is proposed to optimize the charging station locations by maximizing the charging convenience, minimizing the impact of flood hazards, and minimizing the impact of existing charging stations. The NSGA-III is applied to solve the multi-objective location optimization of charging stations.TOPSIS is subsequently used to determine the best solution from the feasible candidates generated by the NSGA-III. A case study conducted in the Waikiki area demonstrates that the proposed optimization framework can effectively deal with the trade-off between the impact of flood hazards and the charging service of a charging station network. This study provides new insights into best practices for dealing with multiple conflicting objectives in EV charging station planning under climate change.

show abstract

“…For example, generative adversarial networks (GAN) is successfully adopted for detecting the road damages [31]. A multilayer ML technique has been used to simulate failure in flood protection systems [32]. ML techniques are also used to develop early warning systems that inform infrastructure protection during disaster events.…”

Section: Machine Learning In Infrastructure Risk Managementmentioning

confidence: 99%

A Hybrid Deep Learning Model for Predictive Flood Warning and Situation Awareness using Channel Network Sensors Data

Dong

Farahmand

et al. 2020

Preprint

View full text Add to dashboard Cite

The objective of this study is to create and test a hybrid deep learning model, FastGRNN-FCN (Fast, Accurate, Stable and Tiny Gated Recurrent Neural Network-Fully Convolutional Neural Network), for urban flood prediction and situation awareness using channel network sensors data. The study used Harris County, Texas as the testbed, and obtained channel sensor data from three historical flood events (e.g., 2016 Tax Day Flood, 2016 Memorial Day flood, and 2017 Hurricane Harvey Flood) for training and validating the hybrid deep learning model. The flood data are divided into a multivariate time series and used as the model input. Each input comprises nine variables, including information of the studied channel sensor and its predecessor and successor sensors in the channel network. Precision-recall curve and F-measure are used to identify the optimal set of model parameters. The optimal model with a weight of 1 and a critical threshold of 0.63 are obtained through one hundred iterations based on examining different weights and thresholds. The test accuracy and F-measure eventually reach 97.8% and 0.8, respectively. The model is then tested in predicting the 2019 Imelda flood in Houston and the results show an excellent match with the empirical flood. The results show that the model enables accurate prediction of the spatial-temporal flood propagation and recession

show abstract

Multiscale modeling of backward erosion piping in flood protection system infrastructure

Cited by 20 publications

References 44 publications

A hybrid deep learning model for predictive flood warning and situation awareness using channel network sensors data

A hybrid deep learning model for predictive flood warning and situation awareness using channel network sensors data

Optimal planning of flood‐resilient electric vehicle charging stations

A Hybrid Deep Learning Model for Predictive Flood Warning and Situation Awareness using Channel Network Sensors Data

Contact Info

Product

Resources

About