Deep Learning for Accelerated Seismic Reliability Analysis of Transportation Networks

@article{Nabian2018DeepLF,
  title={Deep Learning for Accelerated Seismic Reliability Analysis of Transportation Networks},
  author={Mohammad Amin Nabian and Hadi Meidani},
  journal={Comput. Aided Civ. Infrastructure Eng.},
  year={2018},
  volume={33},
  pages={443-458}
}
  • M. Nabian, H. Meidani
  • Published 2018
  • Computer Science, Mathematics
  • Comput. Aided Civ. Infrastructure Eng.
Natural disasters can have catastrophic impacts on the functionality of infrastructure systems and cause severe physical and socio-economic losses. Given budget constraints, it is crucial to optimize decisions regarding mitigation, preparedness, response, and recovery practices for these systems. This requires accurate and efficient means to evaluate the infrastructure system reliability. While numerous research efforts have addressed and quantified the impact of natural disasters on… Expand
Post-Earthquake Assessment of Buildings Using Deep Learning
TLDR
This study has proposed a CNN based autonomous damage detection model that has real-time application in the event of an earthquake. Expand
Identify seismically vulnerable unreinforced masonry buildings using deep learning
  • Salman Khan, Anna Lang, C. Salvaggio
  • Computer Science, Engineering
  • Optical Engineering + Applications
  • 2021
TLDR
This work achieves the best overall accuracy reported to date, at 83.6%, in identifying unfinished U RM, finished URM, and non-URM buildings and performs extensive empirical analysis to establish synergistic parameters on the deep neural network, namely ResNeXt-101-FixRes. Expand
Adaptive network reliability analysis: Methodology and applications to power grid
TLDR
This study presents the first adaptive surrogate-based Network Reliability Analysis using Bayesian Additive Regression Trees (ANR-BART), which is robust and yields accurate estimates of network failure probability, while significantly reducing the computational cost of reliability analysis. Expand
Artificial intelligence in seismology: Advent, performance and future trends
TLDR
An overview of the recent AI studies in seismology is provided and the future direction of the AI methods in earthquake engineering is envisioned which will involve deep learning-enhanced seismology in an internet-of-things (IoT) platform. Expand
Multiscale Modeling of Backward Erosion Piping in Flood Protection Infrastructure
This manuscript presents a novel multiscale modeling approach to simulate the evolution of the Backward Erosion Piping (BEP) process in Flood Protection Systems (FPSs). Amultiphase description of theExpand
Applications of artificial intelligence for disaster management
Natural hazards have the potential to cause catastrophic damage and significant socioeconomic loss. The actual damage and loss observed in the recent decades has shown an increasing trend. As aExpand
Vulnerability and resilience of transportation systems: A recent literature review
  • Shouzheng Pan, Hai Yan, Jia He, Zhengbing He
  • Computer Science
  • 2021
TLDR
The recent progress in the study of vulnerability and resilience is reviewed and related metrics and research methods are carefully analyzed and summarized from qualitative and quantitative perspectives. Expand
Developing Machine-Learning Models to Predict Airfield Pavement Responses
TLDR
Machine-learning based ML models can predict pavement responses with a high accuracy and low computation time and in the case of feeding more data from various airports, ML models have proven to be a promising technique for pavement analysis engine for future airport pavement design frameworks. Expand
A graph deep learning method for short-term traffic forecasting on large road networks
TLDR
A graph deep learning framework to predict large‐scale network traffic flow with high accuracy and efficiency and model the dynamics of the traffic flow on a road network as an irreducible and aperiodic Markov chain on a directed graph. Expand
Modeling Hot-Mix asphalt dynamic modulus using deep residual neural Networks: Parametric and sensitivity analysis study
TLDR
This study applies a deep residual neural networks (DRNNs) technique for the first time to the problem to enhance the E* prediction capabilities by utilizing residual connections that bypass some layers in the deep network structure in order to alleviate the problem of training with high accuracy. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 81 REFERENCES
Deep Learning for Accelerated Reliability Analysis of Infrastructure Networks
TLDR
A deep learning framework for accelerating infrastructure system reliability analysis is presented and two distinct deep neural network surrogates are constructed and studied and highlight the effectiveness of the proposed approach in accelerating the transportation system two-terminal reliability analysis with extremely high prediction accuracy. Expand
Transportation system modeling and applications in earthquake engineering
Abstract : Transportation networks constitute one class of major civil infrastructure systems that is a critical backbone of modern society. Physical damage and functional loss to transportationExpand
Accelerated Monte Carlo system reliability analysis through machine-learning-based surrogate models of network connectivity
TLDR
An approximate framework in which the connectivity check of each sample is estimated using a machine-learning-based classifier is proposed, which is able to predict network connectivity with accuracies of 99% for both methods and are 1–2 orders of magnitude faster than using a Monte Carlo method with an exact connectivity check. Expand
Serviceability Assessment of a Municipal Water System Under Spatially Correlated Seismic Intensities
TLDR
In this article, the serviceability of an infrastructure network system is evaluated with a model that considers spatial correlation in seismic intensity and demand and their usefulness for engineering decision making is evaluated. Expand
A stochastic computational framework for the joint transportation network fragility analysis and traffic flow distribution under extreme events
Abstract This paper deals with a novel technique that jointly uses structural fragility analysis, network flow analysis, and random field theory to assess the correlation among the damage levels ofExpand
Measuring the performance of transportation infrastructure systems in disasters: a comprehensive review
This paper provides a comprehensive overview of the literature on transportation infrastructure system performance in disasters. Specifically, it reviews those articles appearing in refereedExpand
A two-stage stochastic programming model for transportation network protection
TLDR
This paper model the network retrofit problem as a two-stage stochastic programming problem that optimizes a mean-risk objective of the system loss and develops an efficient algorithm to efficiently handle the binary integer variables in the first stage and the nonlinear recourse in the second stage of the model formulation. Expand
Generalized bridge network performance analysis with correlation and time-variant reliability
Abstract A novel approach and framework for the analysis of bridge networks is presented. The goal of the analysis is to assess the life-cycle performance of the network and its time-variantExpand
Performance-based design and seismic reliability analysis using designed experiments and neural networks
Seismic design involves many uncertainties that arise from the earthquake motions, structural geometries, material properties, and analytical models. Taking into account all major uncertainties,Expand
NEEWS: A novel earthquake early warning model using neural dynamic classification and neural dynamic optimization
TLDR
A novel solution to the complex problem of earthquake prediction is provided through adroit integration of a machine learning classification algorithm and the robust neural dynamics optimization algorithm of Adeli and Park. Expand
...
1
2
3
4
5
...