For more than a century, coastal wetlands have been recognized for their ability to stabilize shorelines and protect coastal communities. However, this paradigm has recently been called into question by small-scale experimental evidence. Here, we conduct a literature review and a small meta-analysis of wave attenuation data, and we find overwhelming evidence in support of established theory. Our review suggests that mangrove and salt marsh vegetation afford context-dependent protection from erosion, storm surge, and potentially small tsunami waves. In biophysical models, field tests, and natural experiments, the presence of wetlands reduces wave heights, property damage, and human deaths. Meta-analysis of wave attenuation by vegetated and unvegetated wetland sites highlights the critical role of vegetation in attenuating waves. Although we find coastal wetland vegetation to be an effective shoreline buffer, wetlands cannot protect shorelines in all locations or scenarios; indeed large-scale regional erosion, river meandering, and large tsunami waves and storm surges can overwhelm the attenuation effect of vegetation. However, due to a nonlinear relationship between wave attenuation and wetland size, even small wetlands afford substantial protection from waves. Combining man-made structures with wetlands in ways that mimic nature is likely to increase coastal protection. Oyster domes, for example, can be used in combination with natural wetlands to protect shorelines and restore critical fishery habitat. Finally, coastal wetland vegetation modifies shorelines in ways (e.g. peat accretion) that increase shoreline integrity over long timescales and thus provides a lasting coastal adaptation measure that can protect shorelines against accelerated sea level rise and more frequent storm inundation. We conclude that the shoreline protection paradigm still stands, but that gaps remain in our knowledge about the mechanistic and context-dependent aspects of shoreline protection.

The present and future role of coastal wetland vegetation in protecting shorelines: answering recent challenges to the paradigm

A metric and frameworks for resilience analysis of engineered and infrastructure systems

Natural disasters can cause large blackouts. Research into natural disaster impacts on electric power systems is emerging to understand the causes of the blackouts, explore ways to prepare and harden the grid, and increase the resilience of the power grid under such events. At the same time, new technologies such as smart grid, micro grid, and wide area monitoring applications could increase situational awareness as well as enable faster restoration of the system. This paper aims to consolidate and review the progress of the research field towards methods and tools of forecasting natural disaster related power system disturbances, hardening and pre-storm operations, and restoration models. Challenges and future research opportunities are also presented in the paper.

Research on Resilience of Power Systems Under Natural Disasters—A Review

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

Tackling Climate Change with Machine Learning

This paper focuses on the role of networked microgrids as distributed systems for enhancing the power system resilience against extreme events. Resilience is an intrinsically complex property which requires deep understanding of microgrid operation in order to respond effectively in emergency conditions. The paper first introduces the definition and offers a generic framework for analyzing the power system resilience. The notion that large power systems can achieve a higher level of resilience through the deployment of networked microgrids is discussed in detail. In particular, the management of networked microgrids for riding through extreme events is analyzed. In addition, the merits of advanced information and communication technologies (ICTs) in microgrid-based distributed systems that can support the power system resilience are presented. The paper also points out the challenges for expanding the role of distributed systems and concludes that networked microgrids in particular provide a universal solution for improving the resilience against extreme events in Smart Cities.

Networked Microgrids for Enhancing the Power System Resilience

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.

Comparison and validation of statistical methods for predicting power outage durations in the event of hurricanes.

Hurricanes regularly cause widespread and prolonged power outages along the U.S. coastline. These power outages have significant impacts on other infrastructure dependent on electric power and on the population living in the impacted area. Efficient and effective emergency response planning within power utilities, other utilities dependent on electric power, private companies, and local, state, and federal government agencies benefit from accurate estimates of the extent and spatial distribution of power outages in advance of an approaching hurricane. A number of models have been developed for predicting power outages in advance of a hurricane, but these have been specific to a given utility service area, limiting their use to support wider emergency response planning. In this paper, we describe the development of a hurricane power outage prediction model applicable along the full U.S. coastline using only publicly available data, we demonstrate the use of the model for Hurricane Sandy, and we use the model to estimate what the impacts of a number of historic storms, including Typhoon Haiyan, would be on current U.S. energy infrastructure.

Predicting Hurricane Power Outages to Support Storm Response Planning

A multi-hazard approach to assess severe weather-induced major power outage risks in the U.S.

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.

Power outage estimation for tropical cyclones: improved accuracy with simpler models.

Accurate estimates of the duration of power outages caused by hurricanes prior to landfall are valuable for utility companies and government agencies that wish to plan and optimize their restoration efforts. Accurate pre-storm estimates are also important information for customers and operators of other infrastructures systems, who rely heavily on electricity. Traditionally, utilities make restoration plans based on managerial judgment and experience. However, skillful outage forecast models are conducive to improved decision-making practices by utilities and can greatly enhance storm preparation and restoration management procedures of power companies and emergency managers. This paper presents a novel statistical approach for estimating power outage durations that is 87 % more accurate than existing models in the literature. The power outage duration models are developed and carefully validated for outages caused by Hurricanes Dennis, Katrina, and Ivan in a central Gulf Coast state. This paper identifies the key variables in predicting hurricane-induced outage durations and their degree of influence on predicting outage restoration for the utility company service area used as our case study.

Roshanak Nateghi

Papers

Comparison and validation of statistical methods for predicting power outage durations in the event of hurricanes.

Predicting Hurricane Power Outages to Support Storm Response Planning

A multi-hazard approach to assess severe weather-induced major power outage risks in the U.S.

Power outage estimation for tropical cyclones: improved accuracy with simpler models.

Forecasting hurricane-induced power outage durations