Wildfires are natural or man‐made disasters that continuously threaten portions of the transmission and distribution grid, and thus the stability of the electric grid. This paper presents a two‐stage framework for assessing power system‐wildfire risk using a data‐driven wildfire prediction model. The first stage of the framework estimates the spatio‐temporal probability of potential wildfire ignition and propagation using a deep neural network in combination with the wildfire physical spread model. Analysis reveals similar spatial and temporal patterns between the model‐predicted wildfire ignition potential and actual wildfire ignition. Motivated by these observations, the second stage assesses the wildfire risk in the power grid operation in terms of potential loss of load by de‐energisation, through combining geospatial information system data of the power grid topology and the stochastic spatio‐temporal wildfire model developed in the first stage. The electric power utility applications introduced by the proposed framework are twofold: 1) a spatio‐temporal risk model for proactive de‐energisation against potential power system failure‐induced wildfire, and 2) a spatio‐temporal spreading model for optimal grid operations against exogenous wildfire. The proposed model, based on real‐world dataset, is demonstrated on the IEEE 24‐bus test system mapped to a study area in Northern California, while the results illustrate the proposed model can achieve the best performance in potential wildfire ignition detection (AUC of 0.995) compared to other baselines, as well as demonstrates the risk‐aware operation of the power system enabled by the proposed framework.

Residents near the Great Salt Lake in northern Utah, USA have been exposed to ozone levels during recent summers exceeding the current United States National Ambient Air Quality Standard. Accurately forecasting those exceedances has been difficult as a result of the complex meteorological and photochemical processes fostering them. To help improve such forecasts, a low‐cost field study was conducted during summer 2015 to provide comprehensive observations of boundary‐layer ozone concentrations in the context of the prevailing meteorological conditions. A network of surface ozone sensors was supplemented by sensors mounted on vehicles, a public transit light‐rail car, news helicopter, tethered sonde, and unmanned aerial vehicle. The temporal and spatial evolution of boundary‐layer ozone concentrations were compared with the prevailing regional and local meteorological conditions on the basis of gridded operational analyses, surface weather stations, and additional sensors deployed for the field study. High ozone concentrations during June 2015 resulted primarily from local processes while smoke transported from distant wildfires contributed to elevated ozone concentrations during August. The Great Salt Lake influenced ozone concentrations along the Wasatch Front through several mechanisms, most importantly its impact on local wind circulations. The highest ozone concentrations were often found in a narrow zone between the Great Salt Lake and the urban regions to its south and east. Observations from multiple fixed site and mobile platforms during 18–19 August illustrate the complex variations in ozone concentrations as a function of elevation at the surface as well as vertically through the deep boundary layer.

Observing air quality from sensors onboard light rail cars in Salt Lake County, Utah began as a pilot study in 2014 and has now evolved into a five-year, state-funded program. This metropolitan region suffers from both elevated ozone levels during summer and high PM_2.5 events during winter. Pollution episodes result predominantly from local anthropogenic emissions but are also impacted by regional transport of dust, chemical precursors to ozone, and wildfire smoke, as well as being exacerbated by the topographical features surrounding the city. Two electric light-rail train cars from the Utah Transit Authority light-rail Transit Express (“TRAX”) system were outfitted with PM_2.5 and ozone sensors to measure air quality at high spatial and temporal resolutions in this region. Pollutant concentration data underwent quality control procedures to determine whether the train motion affected the readings and how the sensors compared against regulatory sensors. Quality assurance results from data obtained over the past year show that TRAX Observation Project sensors are reliable, which corroborates earlier preliminary validation work. Three case studies from summer 2019 are presented to illustrate the strength of the finely-resolved air quality observations: (1) an elevated ozone event, (2) elevated particulate pollution resulting from 4th of July fireworks, and (3) elevated particle pollution during a winter time inversion event. The mobile observations were able to capture spatial gradients, as well as pollutant hotspots, during both of these episodes. Sensors have been recently added to a third light rail train car, which travels on a north–south oriented rail line, where air quality was unable to be monitored previously. The TRAX Observation Project is currently being used to provide reliable pollutant data for health studies and inform urban planning efforts. Links to real-time data displays and updated information on the quality-controlled data from this study are available on the webpage for the Department of Atmospheric Sciences at the University of Utah.