More Like this

1. Ground-Based Corroboration of GOES-17 Fire Detection Capabilities During Ignition of the Kincade Fire

   https://doi.org/10.15191/nwajom.2020.0808  

   Lindley, T. Todd; Zwink, Alexander B.; Gravelle, Chad M.; Schmidt, Christopher C.; Palmer, Cynthia K.; Rowe, Scott T.; Heffernan, Robyn; Driscoll, Neal; Kent, Graham M. (July 2020, Journal of Operational Meteorology)

   null (Ed.)

   Corroboration of Geostationary Operational Environmental Satellite-17 (GOES-17) wildland fire detection capabilities occurred during the 24 October 2019 (evening of 23 October LST) ignition of the Kincade Fire in northern California. Post-analysis of remote sensing data compared to observations by the ALERTWildfire fire surveillance video system suggests that the emerging Kincade Fire hotspot was visually evident in GOES17 shortwave infrared imagery 52 s after the initial near-infrared heat source detected by the ground-based camera network. GOES-17 Advanced Baseline Imager Fire Detection Characteristic algorithms registered the fire 5 min after ignition. These observations represent the first documented comparative dataset between fire initiation and satellite detection, and thus provide context for GOES-16/17 wildland fire detections. 

   more » « less
2. Data-Driven Analysis of Wildfire Post-Event Reports: Patterns, Causes, and Mitigation Strategies

   https://doi.org/10.1109/SmartGridComm65349.2025.11204589  

   Khan, Sarah Sami; Mohsenian-Rad, Hamed; Parvania, Masood (September 2025, IEEE)

   Public Safety Power Shutoffs (PSPS) are a critical yet disruptive wildfire mitigation strategy used by electric utilities to reduce ignition risk during periods of elevated fire danger. However, current PSPS decisions often lack transparency and consistency, prompting the need for data-driven tools to better understand utility behavior. This paper presents a Support Vector Machine (SVM) framework to model and interpret PSPS decision-making using post-event wildfire reports. Forecast-based weather and fire behavior features are used as model inputs to represent decision-relevant variables reported by utilities. The model is calibrated using Platt scaling for probabilistic interpretability and adapted across utilities using importance- weighted domain adaptation to address feature distribution shifts. A post-hoc clustering segments PSPS events into wildfire risk zones based on ignition risk metrics excluded from model train- ing. Results demonstrate that the proposed framework supports interpretable, transferable analysis of PSPS decisions, offering insight into utility practices and informing more transparent de- energization planning. 

   more » « less
3. FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection

   https://doi.org/10.3390/rs14041007  

   Dewangan, Anshuman; Pande, Yash; Braun, Hans-Werner; Vernon, Frank; Perez, Ismael; Altintas, Ilkay; Cottrell, Garrison W.; Nguyen, Mai H. (February 2022, Remote Sensing)

   The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage. Past deep learning approaches for wildfire smoke detection have suffered from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly available dataset of nearly 25,000 labeled wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatiotemporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines and rivals human performance. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading to automated notification systems that reduce the time to wildfire response. 

   more » « less
4. The FireFlux II experiment: a model-guided field experiment to improve understanding of fire–atmosphere interactions and fire spread

   https://doi.org/10.1071/WF18089  

   Clements, Craig B.; Kochanski, Adam K.; Seto, Daisuke; Davis, Braniff; Camacho, Christopher; Lareau, Neil P.; Contezac, Jonathan; Restaino, Joseph; Heilman, Warren E.; Krueger, Steven K.; et al (January 2019, International Journal of Wildland Fire)

   The FireFlux II experiment was conducted in a tall grass prairie located in south-east Texas on 30 January 2013 under a regional burn ban and high fire danger conditions. The goal of the experiment was to better understand micrometeorological aspects of fire spread. The experimental design was guided by the use of a coupled fire–atmosphere model that predicted the fire spread in advance. Preliminary results show that after ignition, a surface pressure perturbation formed and strengthened as the fire front and plume developed, causing an increase in wind velocity at the fire front. The fire-induced winds advected hot combustion gases forward and downwind of the fire front that resulted in acceleration of air through the flame front. Overall, the experiment collected a large set of micrometeorological, air chemistry and fire behaviour data that may provide a comprehensive dataset for evaluating and testing coupled fire–atmosphere model systems. 

   more » « less
5. Wildfire Risk in the Complex Terrain of the Santa Barbara Wildland–Urban Interface during Extreme Winds

   https://doi.org/10.3390/fire5050138  

   Zigner, Katelyn; Carvalho, Leila M.; Jones, Charles; Benoit, John; Duine, Gert-Jan; Roberts, Dar; Fujioka, Francis; Moritz, Max; Elmquist, Nic; Hazard, Rob (October 2022, Fire)

   Each year, wildfires ravage the western U.S. and change the lives of millions of inhabitants. Situated in southern California, coastal Santa Barbara has witnessed devastating wildfires in the past decade, with nearly all ignitions started by humans. Therefore, estimating the risk imposed by unplanned ignitions in this fire-prone region will further increase resilience toward wildfires. Currently, a fire-risk map does not exist in this region. The main objective of this study is to provide a spatial analysis of regions at high risk of fast wildfire spread, particularly in the first two hours, considering varying scenarios of ignition locations and atmospheric conditions. To achieve this goal, multiple wildfire simulations were conducted using the FARSITE fire spread model with three ignition modeling methods and three wind scenarios. The first ignition method considers ignitions randomly distributed in 500 m buffers around previously observed ignition sites. Since these ignitions are mainly clustered around roads and trails, the second method considers a 50 m buffer around this built infrastructure, with ignition points randomly sampled from within this buffer. The third method assumes a Euclidean distance decay of ignition probability around roads and trails up to 1000 m, where the probability of selection linearly decreases further from the transportation paths. The ignition modeling methods were then employed in wildfire simulations with varying wind scenarios representing the climatological wind pattern and strong, downslope wind events. A large number of modeled ignitions were located near the major-exit highway running north–south (HWY 154), resulting in more simulated wildfires burning in that region. This could impact evacuation route planning and resource allocation under climatological wind conditions. The simulated fire areas were smaller, and the wildfires did not spread far from the ignition locations. In contrast, wildfires ignited during strong, northerly winds quickly spread into the wildland–urban interface (WUI) toward suburban and urban areas. 

   more » « less