A5053335194- Infrastructure Resilience and Vulnerability Analysis
- Disaster Management and Resilience
- Flood Risk Assessment and Management
- Evacuation and Crowd Dynamics
- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Traffic control and management
- Tropical and Extratropical Cyclones Research
- Complex Network Analysis Techniques
- Facility Location and Emergency Management
- Vehicle emissions and performance
- Occupational Health and Safety Research
- Human Mobility and Location-Based Analysis
- Korean Urban and Social Studies
- Supply Chain Resilience and Risk Management
- Disaster Response and Management
- Hydrological Forecasting Using AI
- Advanced MIMO Systems Optimization
- Fuzzy Systems and Optimization
- Trauma and Emergency Care Studies
- Insurance, Mortality, Demography, Risk Management
- Energy, Environment, and Transportation Policies
- Impact of Light on Environment and Health
- Multi-Criteria Decision Making
- Infrastructure Maintenance and Monitoring
University of Delaware
2020-2024
University of Virginia
2023
Texas A&M University
2019-2022
Oregon State University
2014-2022
ORCID
2020
University of Electronic Science and Technology of China
2013
AbstractThis paper presents a hybrid short-term traffic speed prediction framework through empirical mode decomposition (EMD) and autoregressive integrated moving average (ARIMA). The goals of this are to investigate (1) does the model provide better conditions (i.e. speeds) than traditional models? (2) how performance varies for varying scenarios such as mixed flow vehicle-type specific in work zone, on-ramp, off-ramp; (3) why models other single-staged models. Using data from zone on...
Abstract Smart resilience is the beneficial result of collision course fields data science and urban to flooding. The objective this study propose demonstrate a smart flood framework that leverages heterogeneous community-scale big infrastructure sensor enhance predictive risk monitoring situational awareness. focuses on four core capabilities could be augmented by use analytics techniques: (1) mapping; (2) automated rapid impact assessment; (3) failure prediction monitoring; (4) awareness...
Abstract Compound failures occur when urban flooding coincides with traffic congestion, and their impact on network connectivity is poorly understood. Firstly, either three-dimensional road networks or the roads has been considered, but not both. Secondly, we lack science frameworks to consider compound in infrastructure networks. Here present a network-theory-based framework that bridges this gap by considering structural, functional, topological failures. We analyze high-resolution data...
This paper presents a framework that integrates network theory methods into infrastructure assessment in order to investigate transportation robustness from topological perspective. The objectives of this are threefold: (1) develop can effectively measure performance under different stress levels (hazard scales); (2) determine the constraints networks' spatially embedded nature assessment; and (3) characterize percolation transition networks systematically evaluate cities' robustness, doing...
The objective of this paper is to integrate the post-disaster network access critical facilities into robustness assessment, considering geographical exposure infrastructure natural hazards. Conventional percolation modelling that uses generating function measure fails characterize spatial networks due degree correlation. In addition, giant component alone not sufficient represent performance transportation in setting, especially terms (i.e. emergency services). Furthermore, failure...
The objective of this article is to systematically assess and identify factors affecting risk disparity due infrastructure service disruptions in extreme weather events. We propose a household gap model that characterizes societal risks at the level by examining as threats, tolerance households susceptibility, experienced hardship an indicator for realized impacts risk. concept "zone tolerance" was encapsulated account different capabilities endure adverse impacts. tested validated context...
Abstract This paper presents a Bayesian network model to assess the vulnerability of flood control infrastructure and simulate failure cascade based on topological structure networks along with hydrological information gathered from sensors. Two measures are proposed characterize cascade: (a) node probability (NFP), which determines likelihood each component under scenario rainfall event, (b) susceptibility, captures susceptibility due other links. The was tested in both single watershed...
Abstract The objective of this study is to create and test a hybrid deep learning (DL) model, FastGRNN‐FCN (fast, accurate, stable tiny gated recurrent neural network‐fully convolutional network), for urban flood prediction situation awareness using channel network sensors data. used Harris County, Texas, as the testbed, obtained sensor data from three historical events (e.g., 2016 Tax Day Flood, Memorial 2017 Hurricane Harvey Flood) training validating DL model. are divided into...
This paper proposes and tests a multilayer framework for simulating the network dynamics of inter-organizational coordination among interdependent infrastructure systems (IISs) in resilience planning. Inter-organizational IISs (such as transportation, flood control, emergency management) would greatly affect effectiveness Hence, it is important to examine understand networks organizations within across various To capture dynamic nature frequency heterogeneity organizations, this simulation...
Housing and household characteristics are key determinants of social economic well-being, yet our understanding their interrelationships remains limited. This study addresses this knowledge gap by developing a deep contrastive learning (DCL) model to infer housing-household relationships using the American Community Survey (ACS) Public Use Microdata Sample (PUMS). More broadly, proposed is suitable for class problems where goal learn joint between two distinct entities without explicitly...