William Hughes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
William Hughes has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Wei Zhang
Univ. of Connecticut
13 shared publications Zhixia Ding
Graduate Student, Dept. of Civil and Environmental Engineering, Univ. of Connecticut, Storrs, CT 06269
5 shared publications- Amvrossios C. Bagtzoglou
Professor, Dept. of Civil and Environmental Engineering, Univ. of Connecticut, Storrs, CT 06269. ORCID:
4 shared publications - Diego Cerrai
Department of Civil and Environmental Engineering, University of Connecticut, Storrs, CT, USA
4 shared publications Qin Lu
Department of Civil and Environmental Engineering, University of Connecticut, Storrs, CT, USA
3 shared publicationsAaron Spaulding
Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ, USA
2 shared publications
Latest Publications
- 1 September 2026
- Published by American Society of Civil Engineers (ASCE) in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
- Vol. 12 (3) , 04026038
Strengthening Resilience: An Agent-Based Model for Poststorm Restoration and Grid Hardening in Power Distribution Systems
Storm-related power outages cause substantial economic losses each year, affecting millions of customers for days or even weeks. To support effective preparation for extreme weather events,...
- 1 September 2026
- Published by American Society of Civil Engineers (ASCE) in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
- Vol. 12 (3) , 04026038
Strengthening Resilience: An Agent-Based Model for Poststorm Restoration and Grid Hardening in Power Distribution Systems
Storm-related power outages cause substantial economic losses each year, affecting millions of customers for days or even weeks. To support effective preparation for extreme weather events,...
- Open Access
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 42-55
Transmission Failure Prediction Using AI and Structural Modeling Informed by Distribution Outages
Understanding and quantifying the impact of severe weather events on the electric transmission and distribution system is crucial for ensuring its resiliency in the context of the increasing frequency and intensity of extreme weather events caused by climate change. While weather impact models for the distribution system have been widely developed during the past decade, transmission system impact models lagged behind because of the scarcity of data. This study demonstrates a weather impact model for predicting the probability of failure of transmission lines. It builds upon a recently developed model and focuses on reducing model bias, through multi-model integration, feature engineering, and the development of a storm index that leverages upon distribution system data to aid the prediction of transmission risk. We explored three methods for integrating machine learning with mechanistic models. They consist of: (a) creating a linear combination of the outputs of the two modeling approaches, (b) including fragility curves as additional inputs to machine learning models and (c) developing a new machine learning model that uses the outputs of the weather-based machine learning model, fragility curve estimates and wind data to make new predictions. Moreover, due to the limited number of historical outages in transmission networks, a storm index was developed leveraging a dataset of distribution outages to learn about storm behavior to improve model skills. In the current version of the model, we substantially reduced the overestimation in the sum of predicted values of transmission line probability of failure that was present in the previously published model by 10 times. This has led to a reduction of model bias from 3352% to 14.46-15.43%. The model with the integrated approach and storm index demonstrates substantial improvements in the estimation the probability of failure of transmission line and their ranking by risk level. The improved model is able to capture 60% of the outages within the top 22.5% of the ranked power lines, compared to a value of 34.9% for the previous model. With an estimate of the probability of failure of transmission lines ahead of storms, power system planning and maintenance engineers will have critical information to make informed decisions to create better mitigation plans and minimize power disruptions. Long term, this model can assist with resilience investments as it highlights areas of the system more susceptible to damage.
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 42-55
Open AccessTransmission Failure Prediction Using AI and Structural Modeling Informed by Distribution Outages
Understanding and quantifying the impact of severe weather events on the electric transmission and distribution system is crucial for ensuring its resiliency in the context of the increasing frequency and intensity of extreme weather events caused by climate change. While weather impact models for the distribution system have been widely developed during the past decade, transmission system impact models lagged behind because of the scarcity of data. This study demonstrates a weather impact model for predicting the probability of failure of transmission lines. It builds upon a recently developed model and focuses on reducing model bias, through multi-model integration, feature engineering, and the development of a storm index that leverages upon distribution system data to aid the prediction of transmission risk. We explored three methods for integrating machine learning with mechanistic models. They consist of: (a) creating a linear combination of the outputs of the two modeling approaches, (b) including fragility curves as additional inputs to machine learning models and (c) developing a new machine learning model that uses the outputs of the weather-based machine learning model, fragility curve estimates and wind data to make new predictions. Moreover, due to the limited number of historical outages in transmission networks, a storm index was developed leveraging a dataset of distribution outages to learn about storm behavior to improve model skills. In the current version of the model, we substantially reduced the overestimation in the sum of predicted values of transmission line probability of failure that was present in the previously published model by 10 times. This has led to a reduction of model bias from 3352% to 14.46-15.43%. The model with the integrated approach and storm index demonstrates substantial improvements in the estimation the probability of failure of transmission line and their ranking by risk level. The improved model is able to capture 60% of the outages within the top 22.5% of the ranked power lines, compared to a value of 34.9% for the previous model. With an estimate of the probability of failure of transmission lines ahead of storms, power system planning and maintenance engineers will have critical information to make informed decisions to create better mitigation plans and minimize power disruptions. Long term, this model can assist with resilience investments as it highlights areas of the system more susceptible to damage.
- Open Access
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 63568-63583
Integrating Structural Vulnerability Analysis and Data-Driven Machine Learning to Evaluate Storm Impacts on the Power Grid
The complex interactions between the weather, the environment, and electrical infrastructure that result in power outages are not fully understood, but because of the threat of climate change, the need for models that describe how these factors produce power grid failures is acute. Without them, it remains difficult to understand the amount of weather-related damage we may expect in the future, as well as how changes or upgrades to the infrastructure may mitigate it. To address this problem, a modeling framework is proposed in this article that integrates data derived from structural vulnerability analysis into a machine-learning based weather-related power outage prediction model to create a model that is sensitive both to the weather and the technical configuration of the infrastructure. This Physics Informed Machine Learning (PIML) approach is demonstrated using data from a major power utility operating in the US State of Connecticut, and is compared against a fragility curve modeling approach using some of the same data. The validation of the PIML model shows superior predictive ability, as well as variable sensitivities that follow expected patterns. These results suggest that the model would be able to evaluate the influence that different configurations of the infrastructure would have on the occurrence of power outages caused by severe storms, allowing for the anticipated effects of investments in infrastructural upgrades to be quantified and optimized.
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 63568-63583
Open AccessIntegrating Structural Vulnerability Analysis and Data-Driven Machine Learning to Evaluate Storm Impacts on the Power Grid
The complex interactions between the weather, the environment, and electrical infrastructure that result in power outages are not fully understood, but because of the threat of climate change, the need for models that describe how these factors produce power grid failures is acute. Without them, it remains difficult to understand the amount of weather-related damage we may expect in the future, as well as how changes or upgrades to the infrastructure may mitigate it. To address this problem, a modeling framework is proposed in this article that integrates data derived from structural vulnerability analysis into a machine-learning based weather-related power outage prediction model to create a model that is sensitive both to the weather and the technical configuration of the infrastructure. This Physics Informed Machine Learning (PIML) approach is demonstrated using data from a major power utility operating in the US State of Connecticut, and is compared against a fragility curve modeling approach using some of the same data. The validation of the PIML model shows superior predictive ability, as well as variable sensitivities that follow expected patterns. These results suggest that the model would be able to evaluate the influence that different configurations of the infrastructure would have on the occurrence of power outages caused by severe storms, allowing for the anticipated effects of investments in infrastructural upgrades to be quantified and optimized.
- 18 August 2023
- Published by Elsevier in International Journal of Disaster Risk Reduction
- Vol. 96
Evaluation of post-disaster home livability for coastal communities in a changing climate
- 18 August 2023
- Published by Elsevier in International Journal of Disaster Risk Reduction
- Vol. 96
Evaluation of post-disaster home livability for coastal communities in a changing climate
- 6 March 2023
- Published by Taylor & Francis in Structure and Infrastructure Engineering
- Vol. 20 (12) , 2035-2052
Probabilistic risk assessment framework for predicting large woody debris accumulations and scour near bridges
The accumulation of waterborne large woody debris is a critical issue facing bridges spanning active waterways. In addition to collision forces, drift buildup constricts flow, producing increased hydraulic pressures and exacerbating scour, the cause of nearly one-third of bridge failures. Accurate methods of predicting debris generation, transport, entrapment, and dimensions are consequently necessary to improve public safety, bridge designs, and informed decision-making. However, debris buildup characteristics are site-specific, varying with the regional vegetative, hydraulic, topographical, and geotechnical properties. As sufficient data on these properties is limited to create empirical predictive models, a probabilistic physics-based framework incorporating the risk assessment of local vegetation to estimate debris accumulation and scour is developed. Based on the upstream tree, soil, weather, and river conditions, fragility assessment of the riparian trees from landslides and windthrow is conducted to estimate the probability of debris generation and subsequent entrapment. The framework is demonstrated in a case study of a bridge in Vermont subject to Hurricane Irene. Sensitivity analysis is conducted to quantify the importance of various contributing factors, including slope, rainfall, wind gust, flow rate, and pier geometry. The experimental results highlight the importance of including the debris accumulation in the scour projections.
- 6 March 2023
- Published by Taylor & Francis in Structure and Infrastructure Engineering
- Vol. 20 (12) , 2035-2052
Probabilistic risk assessment framework for predicting large woody debris accumulations and scour near bridges
The accumulation of waterborne large woody debris is a critical issue facing bridges spanning active waterways. In addition to collision forces, drift buildup constricts flow, producing increased hydraulic pressures and exacerbating scour, the cause of nearly one-third of bridge failures. Accurate methods of predicting debris generation, transport, entrapment, and dimensions are consequently necessary to improve public safety, bridge designs, and informed decision-making. However, debris buildup characteristics are site-specific, varying with the regional vegetative, hydraulic, topographical, and geotechnical properties. As sufficient data on these properties is limited to create empirical predictive models, a probabilistic physics-based framework incorporating the risk assessment of local vegetation to estimate debris accumulation and scour is developed. Based on the upstream tree, soil, weather, and river conditions, fragility assessment of the riparian trees from landslides and windthrow is conducted to estimate the probability of debris generation and subsequent entrapment. The framework is demonstrated in a case study of a bridge in Vermont subject to Hurricane Irene. Sensitivity analysis is conducted to quantify the importance of various contributing factors, including slope, rainfall, wind gust, flow rate, and pier geometry. The experimental results highlight the importance of including the debris accumulation in the scour projections.
- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
- Vol. 9 (1) , 04022057
Modeling Tree Damages and Infrastructure Disruptions under Strong Winds for Community Resilience Assessment
Tree failures under extreme gusts could exacerbate storm damages to critical infrastructures, including the power delivery system, transportation network, or residential buildings. Nevertheless, the effects of tree damages have largely been excluded in existing community resilience assessment frameworks. To this end, presently, a model integrating tree failure consequences with community-level resilience evaluation is proposed for improved damage and recovery projections, considering the interconnected transportation, power delivery, and residential building systems. Tree failure probabilities are estimated based fragility analysis of the tree structural response under gusts. Proximity analysis is conducted to quantify the threat of trees striking critical infrastructures. The tree and wind risk assessments are integrated with fragility analysis of the power distribution system timber utility poles and the vulnerability analysis of low-rise wooden residential buildings. The methodology is carried out on a case study of a community in the northeastern US. The results indicate utility pole failures and roadway debris accumulations and blockages initiate when wind speeds reach around ( ). Although the inclusion of tree failures increase pole failure probability failure, tree-induced damages to residential buildings were found minimal due to the relatively lower heights of the sparser trees in the studied suburban region. Storm impacts are linked to the household level, including structural damages and their restoration times, increases in travel time to the main road, and probability of losing power. Vegetation management strategies are found to effectively reduce the building and powerline damages and debris buildup on roads.- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
- Vol. 9 (1) , 04022057
Modeling Tree Damages and Infrastructure Disruptions under Strong Winds for Community Resilience Assessment
Tree failures under extreme gusts could exacerbate storm damages to critical infrastructures, including the power delivery system, transportation network, or residential buildings. Nevertheless, the effects of tree damages have largely been excluded in existing community resilience assessment frameworks. To this end, presently, a model integrating tree failure consequences with community-level resilience evaluation is proposed for improved damage and recovery projections, considering the interconnected transportation, power delivery, and residential building systems. Tree failure probabilities are estimated based fragility analysis of the tree structural response under gusts. Proximity analysis is conducted to quantify the threat of trees striking critical infrastructures. The tree and wind risk assessments are integrated with fragility analysis of the power distribution system timber utility poles and the vulnerability analysis of low-rise wooden residential buildings. The methodology is carried out on a case study of a community in the northeastern US. The results indicate utility pole failures and roadway debris accumulations and blockages initiate when wind speeds reach around ( ). Although the inclusion of tree failures increase pole failure probability failure, tree-induced damages to residential buildings were found minimal due to the relatively lower heights of the sparser trees in the studied suburban region. Storm impacts are linked to the household level, including structural damages and their restoration times, increases in travel time to the main road, and probability of losing power. Vegetation management strategies are found to effectively reduce the building and powerline damages and debris buildup on roads.- 7 February 2023
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 34
Machine learning evaluation of storm-related transmission outage factors and risk
- 7 February 2023
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 34
Machine learning evaluation of storm-related transmission outage factors and risk