A5008350048- Power System Reliability and Maintenance
- Transportation Planning and Optimization
- Lightning and Electromagnetic Phenomena
- Economic and Environmental Valuation
- Fire effects on ecosystems
- Urban Transport and Accessibility
- Meteorological Phenomena and Simulations
- Tropical and Extratropical Cyclones Research
- Energy Load and Power Forecasting
- Pharmaceutical and Antibiotic Environmental Impacts
- Water Governance and Infrastructure
- Infrastructure Resilience and Vulnerability Analysis
- Transportation and Mobility Innovations
- Maritime Ports and Logistics
- Marine Biology and Environmental Chemistry
- Water Treatment and Disinfection
- Smart Parking Systems Research
- Analytical chemistry methods development
- Water resources management and optimization
- Hydrology and Drought Analysis
- Hydropower, Displacement, Environmental Impact
- Urban and Freight Transport Logistics
- Microplastics and Plastic Pollution
- Power Transformer Diagnostics and Insulation
- Power System Optimization and Stability
Los Alamos National Laboratory
2023-2025
University of Connecticut
2018-2023
World Bank
1975-1977
Northwestern University
1974
Power outages caused by extreme weather events cost the economy of United States billions dollars every year and endanger lives people affected them. These types could be better managed if accurate predictions storm impacts were available. While empirical power outage prediction models have been in development for many years, operational most impactful weather-related proven difficult to achieve several reasons. In this paper, we describe a data intensive modeling approach specifically...
Abstract Wastewater (WW) systems are vulnerable to extreme precipitation events; storm‐induced WW system failures pollute the environment and put public health at risk. Despite these vulnerabilities, we know very little about how managers responding current climate risks or future change. This study aims fill this critical gap in literature. Data from surveys interviews were used understand what doing adapt climate, facilitates those adaptations, if they adapting Findings show most (78%)...
The accuracy of machine learning-based power outage prediction models (OPMs) is sensitive to how well event severity represented in their training datasets. Unbalanced or overly dispersed can result random errors predictions and underestimation severe events overestimation weak ones. To improve the storm-caused outages, we introduce a novel method called “Conditioned OPM” that divides an OPM dataset into subsets representative predicted event's by calculating quantile weight distance (QWD)...
Thunderstorms are complex weather phenomena that cause substantial power outages in a short period. This makes thunderstorm outage prediction challenging using eventwise models (OPMs), which summarize the storm dynamics over entire course of into limited number parameters. We developed new, temporally sensitive framework designed for to learn hourly thunderstorm-caused directly from forecasts. Validation several built on this hour-by-hour and comparison with baseline model show abilities...
Thunderstorms are one of the most damaging weather phenomena in United States, but they also least predictable. This unpredictable nature can make it especially challenging for emergency responders, infrastructure managers, and power utilities to be able prepare react these types events when occur. Predictive analytical methods could used help adapt storms, there uncertainties inherent predictability convective storms that pose a challenge accurate prediction storm-related outages....
This paper develops a statistical framework to analyze the effectiveness of vegetation management at reducing power outages during storms varying severity levels. The was applied on Eversource Energy distribution grid in Connecticut, USA based 173 rain and wind events from 2005–2020, including Hurricane Irene, Sandy, Tropical Storm Isaias. data were binned by storm (high/low) levels, where maximum applicable length for each circuit determined, divided into four bins actual performed value...
The outage prediction model (OPM) is a weather-related machine learning-based power model, which has been developed at the University of Connecticut for many years and recently grown to cover three states five utility service territories. This large heterogeneous domain supported by dataset hundreds storm events. presents opportunity investigate effect spatial organisation training structure on performance, identify potential weaknesses in modelling approach, evaluate generalisability...