Comparison and Validation of Statistical Methods for Predicting Power Outage Durations in the Event of Hurricanes

This article compares statistical methods for modeling power outage durations during hurricanes and examines the predictive accuracy of these methods. Being able to make accurate predictions of power outage durations is valuable because the information can be used by utility companies to plan their restoration efforts more efficiently. This information can also help inform customers and public agencies of the expected outage times, enabling better collective response planning, and coordination of restoration efforts for other critical infrastructures that depend on electricity. In the long run, outage duration estimates for future storm scenarios may help utilities and public agencies better allocate risk management resources to balance the disruption from hurricanes with the cost of hardening power systems. We compare the out‐of‐sample predictive accuracy of five distinct statistical models for estimating power outage duration times caused by Hurricane Ivan in 2004. The methods compared include both regression models (accelerated failure time (AFT) and Cox proportional hazard models (Cox PH)) and data mining techniques (regression trees, Bayesian additive regression trees (BART), and multivariate additive regression splines). We then validate our models against two other hurricanes. Our results indicate that BART yields the best prediction accuracy and that it is possible to predict outage durations with reasonable accuracy.     

Improving the Predictive Accuracy of Hurricane Power Outage Forecasts Using Generalized Additive Models

Electric power is a critical infrastructure service after hurricanes, and rapid restoration of electric power is important in order to minimize losses in the impacted areas. However, rapid restoration of electric power after a hurricane depends on obtaining the necessary resources, primarily repair crews and materials, before the hurricane makes landfall and then appropriately deploying these resources as soon as possible after the hurricane. This, in turn, depends on having sound estimates of both the overall severity of the storm and the relative risk of power outages in different areas. Past studies have developed statistical, regression-based approaches for estimating the number of power outages in advance of an approaching hurricane. However, these approaches have either not been applicable for future events or have had lower predictive accuracy than desired. This article shows that a different type of regression model, a generalized additive model (GAM), can outperform the types of models used previously. This is done by developing and validating a GAM based on power outage data during past hurricanes in the Gulf Coast region and comparing the results from this model to the previously used generalized linear models.     

An Integrated Scenario Ensemble-Based Framework for Hurricane Evacuation Modeling: Part 2—Hazard Modeling

Hurricane track and intensity can change rapidly in unexpected ways, thus making predictions of hurricanes and related hazards uncertain. This inherent uncertainty often translates into suboptimal decision-making outcomes, such as unnecessary evacuation. Representing this uncertainty is thus critical in evacuation planning and related activities. We describe a physics-based hazard modeling approach that (1) dynamically accounts for the physical interactions among hazard components and (2) captures hurricane evolution uncertainty using an ensemble method. This loosely coupled model system provides a framework for probabilistic water inundation and wind speed levels for a new, risk-based approach to evacuation modeling, described in a companion article in this issue. It combines the Weather Research and Forecasting (WRF) meteorological model, the Coupled Routing and Excess STorage (CREST) hydrologic model, and the ADvanced CIRCulation (ADCIRC) storm surge, tide, and wind-wave model to compute inundation levels and wind speeds for an ensemble of hurricane predictions. Perturbations to WRF's initial and boundary conditions and different model physics/parameterizations generate an ensemble of storm solutions, which are then used to drive the coupled hydrologic + hydrodynamic models. Hurricane Isabel (2003) is used as a case study to illustrate the ensemble-based approach. The inundation, river runoff, and wind hazard results are strongly dependent on the accuracy of the mesoscale meteorological simulations, which improves with decreasing lead time to hurricane landfall. The ensemble envelope brackets the observed behavior while providing “best-case” and “worst-case” scenarios for the subsequent risk-based evacuation model.     

Uncertainty Analysis for Computer Model Projections of Hurricane Losses

Projecting losses associated with hurricanes is a complex and difficult undertaking that is wrought with uncertainties. Hurricane Charley, which struck southwest Florida on August 13, 2004, illustrates the uncertainty of forecasting damages from these storms. Due to shifts in the track and the rapid intensification of the storm, real-time estimates grew from 2 to 3 billion dollars in losses late on August 12 to a peak of 50 billion dollars for a brief time as the storm appeared to be headed for the Tampa Bay area. The storm hit the resort areas of Charlotte Harbor near Punta Gorda and then went on to Orlando in the central part of the state, with early poststorm estimates converging on a damage estimate in the 28 to 31 billion dollars range. Comparable damage to central Florida had not been seen since Hurricane Donna in 1960. The Florida Commission on Hurricane Loss Projection Methodology (FCHLPM) has recognized the role of computer models in projecting losses from hurricanes. The FCHLPM established a professional team to perform onsite (confidential) audits of computer models developed by several different companies in the United States that seek to have their models approved for use in insurance rate filings in Florida. The team's members represent the fields of actuarial science, computer science, meteorology, statistics, and wind and structural engineering. An important part of the auditing process requires uncertainty and sensitivity analyses to be performed with the applicant's proprietary model. To influence future such analyses, an uncertainty and sensitivity analysis has been completed for loss projections arising from use of a Holland B parameter hurricane wind field model. Uncertainty analysis quantifies the expected percentage reduction in the uncertainty of wind speed and loss that is attributable to each of the input variables.     

Prestorm Estimation of Hurricane Damage to Electric Power Distribution Systems

Hurricanes frequently cause damage to electric power systems in the United States, leading to widespread and prolonged loss of electric service. Restoring service quickly requires the use of repair crews and materials that must be requested, at considerable cost, prior to the storm. U.S. utilities have struggled to strike a good balance between over‐ and underpreparation largely because of a lack of methods for rigorously estimating the impacts of an approaching hurricane on their systems. Previous work developed methods for estimating the risk of power outages and customer loss of power, with an outage defined as nontransitory activation of a protective device. In this article, we move beyond these previous approaches to directly estimate damage to the electric power system. Our approach is based on damage data from past storms together with regression and data mining techniques to estimate the number of utility poles that will need to be replaced. Because restoration times and resource needs are more closely tied to the number of poles and transformers that need to be replaced than to the number of outages, this pole‐based assessment provides a much stronger basis for prestorm planning by utilities. Our results show that damage to poles during hurricanes can be assessed accurately, provided that adequate past damage data are available. However, the availability of data can, and currently often is, the limiting factor in developing these types of models in practice. Opportunities for further enhancing the damage data recorded during hurricanes are also discussed.     

Sensitivity Analysis for Computer Model Projections of Hurricane Losses

Projecting losses associated with hurricanes is a complex and difficult undertaking that is fraught with uncertainties. Hurricane Charley, which struck southwest Florida on August 13, 2004, illustrates the uncertainty of forecasting damages from these storms. Due to shifts in the track and the rapid intensification of the storm, real-time estimates grew from 2 billion dollars to 3 billion dollars in losses late on the 12th to a peak of 50 billion dollars for a brief time as the storm appeared to be headed for the Tampa Bay area. The storm struck the resort areas of Charlotte Harbor and moved across the densely populated central part of the state, with early poststorm estimates in the 28 dollars to 31 billion dollars range, and final estimates converging at 15 billion dollars as the actual intensity at landfall became apparent. The Florida Commission on Hurricane Loss Projection Methodology (FCHLPM) has a great appreciation for the role of computer models in projecting losses from hurricanes. The FCHLPM contracts with a professional team to perform onsite (confidential) audits of computer models developed by several different companies in the United States that seek to have their models approved for use in insurance rate filings in Florida. The team's members represent the fields of actuarial science, computer science, meteorology, statistics, and wind and structural engineering. An important part of the auditing process requires uncertainty and sensitivity analyses to be performed with the applicant's proprietary model. To influence future such analyses, an uncertainty and sensitivity analysis has been completed for loss projections arising from use of a sophisticated computer model based on the Holland wind field. Sensitivity analyses presented in this article utilize standardized regression coefficients to quantify the contribution of the computer input variables to the magnitude of the wind speed.     

Low‐Probability Flood Risk Modeling for New York City

The devastating impact by Hurricane Sandy (2012) again showed New York City (NYC) is one of the most vulnerable cities to coastal flooding around the globe. The low‐lying areas in NYC can be flooded by nor'easter storms and North Atlantic hurricanes. The few studies that have estimated potential flood damage for NYC base their damage estimates on only a single, or a few, possible flood events. The objective of this study is to assess the full distribution of hurricane flood risk in NYC. This is done by calculating potential flood damage with a flood damage model that uses many possible storms and surge heights as input. These storms are representative for the low‐probability/high‐impact flood hazard faced by the city. Exceedance probability‐loss curves are constructed under different assumptions about the severity of flood damage. The estimated flood damage to buildings for NYC is between US$59 and 129 millions/year. The damage caused by a 1/100‐year storm surge is within a range of US$2 bn–5 bn, while this is between US$5 bn and 11 bn for a 1/500‐year storm surge. An analysis of flood risk in each of the five boroughs of NYC finds that Brooklyn and Queens are the most vulnerable to flooding. This study examines several uncertainties in the various steps of the risk analysis, which resulted in variations in flood damage estimations. These uncertainties include: the interpolation of flood depths; the use of different flood damage curves; and the influence of the spectra of characteristics of the simulated hurricanes.     

The Dynamics of Disaster Recovery: Resilience and Entropy in Hurricane Response Systems 2005–2008

The challenge for policy makers and disaster managers is to achieve a balance between two dynamics — resilience and entropy — in order to develop sustainable risk reduction. Achieving an appropriate balance between resilience and entropy in any given community requires a systematic exploration of both dynamics. The recent hurricanes that struck Louisiana, Hurricane Katrina on August 29, 2005 and Hurricane Gustav, on September 1, 2008, offer an unusual opportunity to assess the degree to which both dynamics operated following Hurricane Katrina.     

Nonparametric Tree‐Based Predictive Modeling of Storm Outages on an Electric Distribution Network

This article compares two nonparametric tree‐based models, quantile regression forests (QRF) and Bayesian additive regression trees (BART), for predicting storm outages on an electric distribution network in Connecticut, USA. We evaluated point estimates and prediction intervals of outage predictions for both models using high‐resolution weather, infrastructure, and land use data for 89 storm events (including hurricanes, blizzards, and thunderstorms). We found that spatially BART predicted more accurate point estimates than QRF. However, QRF produced better prediction intervals for high spatial resolutions (2‐km grid cells and towns), while BART predictions aggregated to coarser resolutions (divisions and service territory) more effectively. We also found that the predictive accuracy was dependent on the season (e.g., tree‐leaf condition, storm characteristics), and that the predictions were most accurate for winter storms. Given the merits of each individual model, we suggest that BART and QRF be implemented together to show the complete picture of a storm's potential impact on the electric distribution network, which would allow for a utility to make better decisions about allocating prestorm resources.     

Power Outage Estimation for Tropical Cyclones: Improved Accuracy with Simpler Models

In this article, we discuss an outage‐forecasting model that we have developed. This model uses very few input variables to estimate hurricane‐induced outages prior to landfall with great predictive accuracy. We also show the results for a series of simpler models that use only publicly available data and can still estimate outages with reasonable accuracy. The intended users of these models are emergency response planners within power utilities and related government agencies. We developed our models based on the method of random forest, using data from a power distribution system serving two states in the Gulf Coast region of the United States. We also show that estimates of system reliability based on wind speed alone are not sufficient for adequately capturing the reliability of system components. We demonstrate that a multivariate approach can produce more accurate power outage predictions.     

Petroleum and Hazardous Material Releases from Industrial Facilities Associated with Hurricane Katrina

Hurricane Katrina struck an area dense with industry, causing numerous releases of petroleum and hazardous materials. This study integrates information from a number of sources to describe the frequency, causes, and effects of these releases in order to inform analysis of risk from future hurricanes. Over 200 onshore releases of hazardous chemicals, petroleum, or natural gas were reported. Storm surge was responsible for the majority of petroleum releases and failure of storage tanks was the most common mechanism of release. Of the smaller number of hazardous chemical releases reported, many were associated with flaring from plant startup, shutdown, or process upset. In areas impacted by storm surge, 10% of the facilities within the Risk Management Plan (RMP) and Toxic Release Inventory (TRI) databases and 28% of SIC 1311 facilities experienced accidental releases. In areas subject only to hurricane strength winds, a lower fraction (1% of RMP and TRI and 10% of SIC 1311 facilities) experienced a release while 1% of all facility types reported a release in areas that experienced tropical storm strength winds. Of industrial facilities surveyed, more experienced indirect disruptions such as displacement of workers, loss of electricity and communication systems, and difficulty acquiring supplies and contractors for operations or reconstruction (55%), than experienced releases. To reduce the risk of hazardous material releases and speed the return to normal operations under these difficult conditions, greater attention should be devoted to risk‐based facility design and improved prevention and response planning.     

Leader–follower equilibria to examine investment decisions in grid resilience-enhancing measures

Large-area, long-duration power outages are increasingly common in the United States, and cost the economy billions of dollars each year. Building a strategy to enhance grid resilience requires an understanding of the optimal mix of preventive and corrective actions, the inefficiencies that arise when self-interested parties make resilience investment decisions, and the conditions under which regulators may facilitate the realization of efficient market outcomes. We develop a bi-level model to examine the mix of preventive and corrective measures that enhances grid resilience to a severe storm. The model represents a Stackelberg game between a regulated utility (leader) that may harden distribution feeders before a long-duration outage and/or deploy restoration crews after the disruption, and utility customers with varying preferences for reliable power (followers) who may invest in backup generators. We show that the regulator's denial of cost recovery for the utility's preventive expenditures, coupled with the misalignment between private objectives and social welfare maximization, yields significant inefficiencies in the resilience investment mix. Allowing cost recovery for a higher share of the utility's capital expenditures in preventive measures, extending the time horizon associated with damage cost recovery, and adopting a storm restoration compensation mechanism shift the realized market outcome toward the efficient solution. If about one-fifth of preventive resilience investments is approved by regulators, requiring utilities to pay a compensation of $365 per customer for a 3-day outage (about seven times the level of compensation currently offered by US utilities) provides significant incentives toward more efficient preventive resilience investments.     

Integrating Models and Data to Estimate the Structural Reliability of Utility Poles During Hurricanes

Utility systems such as power and communication systems regularly experience significant damage and loss of service during hurricanes. A primary damage mode for these systems is failure of wooden utility poles that support conductors and communication lines. In this article, we present an approach for combining structural reliability models for utility poles with observed data on pole performance during past hurricanes. This approach, based on Bayesian updating, starts from an imperfect but informative prior and updates this prior with observed performance data. We consider flexural and foundation failure mechanisms in the prior, acknowledging that these are an incomplete, but still informative, subset of the possible failure mechanisms for utility poles during hurricanes. We show how a model‐based prior can be updated with observed failure data, using pole failure data from Hurricane Katrina as a case study. The results of this integration of model‐based estimates and observed performance data then offer a more informative starting point for power system performance estimation for hurricane conditions.     

Explainable deep learning powered building risk assessment model for proactive hurricane response

Climate change and rapid urban development have intensified the impact of hurricanes, especially on the Southeastern Coasts of the United States. Localized and timely risk assessments can facilitate coastal communities’ preparedness and response to imminent hurricanes. Existing assessment methods focused on hurricane risks at large spatial scales, which were not specific or could not provide actionable knowledge for residents or property owners. Fragility functions and other widely utilized assessment methods cannot model the complex relationships between building features and hurricane risk levels effectively. Therefore, we develop and test a building-level hurricane risk assessment with deep feedforward neural network (DFNN) models. The input features of DFNN models cover the meta building characteristics, fine-grained meteorological, and hydrological environmental parameters. The assessment outcomes, that is, risk levels, include the probability and intensity of building/property damages induced by wind and surge hazards. We interpret the DFNN models with local interpretable model-agnostic explanations (LIME). We apply the DFNN models to a case building in Cameron County, Louisiana in response to a hypothetical imminent hurricane to illustrate how the building's risk levels can be timely assessed with the updating weather forecast. This research shows the potential of deep-learning models in integrating multi-sourced features and accurately predicting buildings’ risks of weather extremes for property owners and households. The AI-powered risk assessment model can help coastal populations form appropriate and updating perceptions of imminent hurricanes and inform actionable knowledge for proactive risk mitigation and long-term climate adaptation.     

Impact of Water Level Rise on Urban Infrastructures: Washington,DC, and Shanghai as Case Studies

The observed global sea level rise owing to climate change, coupled with the potential increase in extreme storms, requires a reexamination of existing infrastructural planning, construction, and management practices. Storm surge shows the effects of rising sea levels. The recent super storms that hit the United States (e.g., Hurricane Katrina in 2005, Sandy in 2012, Harvey and Maria in 2017) and China (e.g., Typhoon Haiyan in 2010) inflicted serious loss of life and property. Water level rise (WLR) of local coastal areas is a combination of sea level rise, storm surge, precipitation, and local land subsidence. Quantitative assessments of the impact of WLR include scenario identification, consequence assessment, vulnerability and flooding assessment, and risk management using inventory of assets from coastal areas, particularly population centers, to manage flooding risk and to enhance infrastructure resilience of coastal cities. This article discusses the impact of WLR on urban infrastructures with case studies of Washington, DC, and Shanghai. Based on the flooding risk analysis under possible scenarios, the property loss for Washington, DC, was evaluated, and the impact on the metro system of Shanghai was examined.     

Improved Methods for Estimating Flood Depth Exceedances Within Storm Surge Protection Systems

Contemporary studies conducted by the U.S. Army Corps of Engineers estimate probability distributions of flooding on the interior of ring levee systems by estimating surge exceedances at points along levee system boundaries, calculating overtopping volumes generated by this surface, then passing the resulting volumes of water through a drainage model to calculate interior flood depths. This approach may not accurately represent the exceedance probability of flood depths within the system interior; a storm producing 100‐year surge at one point is unlikely to simultaneously produce 100‐year surge levels everywhere around the system exterior. A conceptually preferred approach estimates surge and waves associated with a large set of storms. Each storm is run through the interior model separately, and the resulting flood depths are weighted by a parameterized likelihood of each synthetic storm. This results in an empirical distribution of flood depths accounting for geospatial variation in any individual storm's characteristics. This method can also better account for the probability of levee breaches or other system failures. The two methods can produce different estimates of flood depth exceedances and damage when applied to storm surge flooding in coastal Louisiana. Even differences in flood depth exceedances of less than 0.2 m can still produce large differences in projected damage. This article identifies and discusses differences in estimated flood depths and damage produced by each method within multiple Louisiana protection systems. The novel coupled dynamics approach represents a step toward enabling risk‐based design standards.     

Analysis of the Effects of Communication and Surveillance Facility Service Outages on Traffic Separations

This study examines air traffic separations in the service volumes of communication and surveillance facilities that experienced service outages. The data sample consists of 338 unscheduled service outages that happened in 2010 and 2011 at facilities located in the vicinity of 15 major traffic hubs. For each outage, radar track data were collected and used to calculate traffic separations during the period of 30 minutes before to 30 minutes after an outage. Then, the separation index, which indicates the percentage of horizontal separation retained between two aircraft at the same altitude, was estimated. The separation index and loss of separation events were analyzed using lognormal and negative binomial regression models. The results suggest that the count of separation events peaks during the 15 minutes after an outage. In addition, traffic collision avoidance system resolution advisory (TCAS RA) encounters and Category A separation events are 1.31 times more likely during the 30 minutes following the beginning of a service outage, as compared to the 30 minutes before the outage, for both types of facilities. Also, the separation index values are 19% lower following a surveillance facility outage and 4% lower following a communication facility service loss. This study provides evidence that unscheduled service outages of air traffic management facilities are associated with lost or reduced traffic separations and thus can be considered precursors to hazardous loss of separation events.     

Risk-Management and Risk-Analysis-Based Decision Tools for Attacks on Electric Power

Incident data about disruptions to the electric power grid provide useful information that can be used as inputs into risk management policies in the energy sector for disruptions from a variety of origins, including terrorist attacks. This article uses data from the Disturbance Analysis Working Group (DAWG) database, which is maintained by the North American Electric Reliability Council (NERC), to look at incidents over time in the United States and Canada for the period 1990-2004. Negative binomial regression, logistic regression, and weighted least squares regression are used to gain a better understanding of how these disturbances varied over time and by season during this period, and to analyze how characteristics such as number of customers lost and outage duration are related to different characteristics of the outages. The results of the models can be used as inputs to construct various scenarios to estimate potential outcomes of electric power outages, encompassing the risks, consequences, and costs of such outages.     

Application of a Regional Hurricane Wind Risk Forecasting Model for Wood-Frame Houses

Hurricane wind risk in a region changes over time due to changes in the number, type, locations, vulnerability, and value of buildings. A model was developed to quantitatively estimate changes over time in hurricane wind risk to wood-frame houses (defined in terms of potential for direct economic loss), and to estimate how different factors, such as building code changes and population growth, contribute to that change. The model, which is implemented in a simulation, produces a probability distribution of direct economic losses for each census tract in the study region at each time step in the specified time horizon. By changing parameter values and rerunning the analysis, the effects of different changes in the built environment on the hurricane risk trends can be estimated and the relative effectiveness of hypothetical mitigation strategies can be evaluated. Using a case study application for wood-frame houses in selected counties in North Carolina from 2000 to 2020, this article demonstrates how the hurricane wind risk forecasting model can be used: (1) to provide insight into the dynamics of regional hurricane wind risk-the total change in risk over time and the relative contribution of different factors to that change, and (2) to support mitigation planning. Insights from the case study include, for example, that the many factors contributing to hurricane wind risk for wood-frame houses interact in a way that is difficult to predict a priori, and that in the case study, the reduction in hurricane losses due to vulnerability changes (e.g., building code changes) is approximately equal to the increase in losses due to building inventory growth. The potential for the model to support risk communication is also discussed.     

Quantifying the Hurricane Catastrophe Risk to Offshore Wind Power

The U.S. Department of Energy has estimated that over 50 GW of offshore wind power will be required for the United States to generate 20% of its electricity from wind. Developers are actively planning offshore wind farms along the U.S. Atlantic and Gulf coasts and several leases have been signed for offshore sites. These planned projects are in areas that are sometimes struck by hurricanes. We present a method to estimate the catastrophe risk to offshore wind power using simulated hurricanes. Using this method, we estimate the fraction of offshore wind power simultaneously offline and the cumulative damage in a region. In Texas, the most vulnerable region we studied, 10% of offshore wind power could be offline simultaneously because of hurricane damage with a 100‐year return period and 6% could be destroyed in any 10‐year period. We also estimate the risks to single wind farms in four representative locations; we find the risks are significant but lower than those estimated in previously published results. Much of the hurricane risk to offshore wind turbines can be mitigated by designing turbines for higher maximum wind speeds, ensuring that turbine nacelles can turn quickly to track the wind direction even when grid power is lost, and building in areas with lower risk.