In recent years, the increasing threat of devastating wildfires has underscored the need for effective prescribed fire management. Process-based computer simulations have traditionally been employed to plan prescribed fires for wildfire prevention. However, even simplified process models are too compute-intensive to be used for real-time decision-making. Traditional ML methods used for fire modeling offer computational speedup but struggle with physically inconsistent predictions, biased predictions due to class imbalance, biased estimates for fire spread metrics (e.g., burned area, rate of spread), and limited generalizability in out-of-distribution wind conditions. This paper introduces a novel machine learning (ML) framework that enables rapid emulation of prescribed fires while addressing these concerns. To overcome these challenges, the framework incorporates domain knowledge in the form of physical constraints, a hierarchical modeling structure to capture the interdependence among variables of interest, and also leverages pre-existing source domain data to augment training data and learn the spread of fire more effectively. Notably, improvement in fire metric (e.g., burned area) estimates offered by our framework makes it useful for fire managers, who often rely on these estimates to make decisions about prescribed burn management. Furthermore, our framework exhibits better generalization capabilities than the other ML-based fire modeling methods across diverse wind conditions and ignition patterns.
more »
« less
California wildfire spread derived using VIIRS satellite observations and an object-based tracking system
Abstract Changing wildfire regimes in the western US and other fire-prone regions pose considerable risks to human health and ecosystem function. However, our understanding of wildfire behavior is still limited by a lack of data products that systematically quantify fire spread, behavior and impacts. Here we develop a novel object-based system for tracking the progression of individual fires using 375 m Visible Infrared Imaging Radiometer Suite active fire detections. At each half-daily time step, fire pixels are clustered according to their spatial proximity, and are either appended to an existing active fire object or are assigned to a new object. This automatic system allows us to update the attributes of each fire event, delineate the fire perimeter, and identify the active fire front shortly after satellite data acquisition. Using this system, we mapped the history of California fires during 2012–2020. Our approach and data stream may be useful for calibration and evaluation of fire spread models, estimation of near-real-time wildfire emissions, and as means for prescribing initial conditions in fire forecast models.
more »
« less
- Award ID(s):
- 1839336
- PAR ID:
- 10396666
- Date Published:
- Journal Name:
- Scientific Data
- Volume:
- 9
- Issue:
- 1
- ISSN:
- 2052-4463
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Fuel break effectiveness in wildland-urban interface (WUI) is not well understood during downslope wind-driven fires even though various fuel treatments are conducted across the western United States. The aim of this paper is to examine the efficacy of WUI fuel breaks under the influence of strong winds and dry fuels, using the 2018 Camp Fire as a case study. The operational fire growth model Prometheus was used to show: (1) downstream impacts of 200 m and 400 m wide WUI fuel breaks on fire behavior and evacuation time gain; (2) how the downstream fire behavior was affected by the width and fuel conditions of the WUI fuel breaks; and (3) the impacts of background wind speeds on the efficacy of WUI fuel breaks. Our results indicate that WUI fuel breaks may slow wildfire spread rates by dispersing the primary advancing fire front into multiple fronts of lower intensity on the downstream edge of the fuel break. However, fuel break width mattered. We found that the lateral fire spread and burned area were reduced downstream of the 400 m wide WUI fuel break more effectively than the 200 m fuel break. Further sensitivity tests showed that wind speed at the time of ignition influenced fire behavior and efficacy of management interventions.more » « less
-
Research Highlights: Flammability of wildland fuels is a key factor influencing risk-based decisions related to preparedness, response, and safety in Alaska. However, without effective measures of current and expected flammability, the expected likelihood of active and problematic wildfires in the future is difficult to assess and prepare for. This study evaluates the effectiveness of diverse indices to capture high-risk fires. Indicators of drought and atmospheric drivers are assessed along with the operational Canadian Forest Fire Danger Rating System (CFFDRS). Background and Objectives: In this study, 13 different indicators of atmospheric conditions, fuel moisture, and flammability are compared to determine how effective each is at identifying thresholds and trends for significant wildfire activity. Materials and Methods: Flammability indices are compared with remote sensing characterizations that identify where and when fire activity has occurred. Results: Among these flammability indicators, conventional tools calibrated to wildfire thresholds (Duff Moisture Code (DMC) and Buildup Index (BUI)), as well as measures of atmospheric forcing (Vapor Pressure Deficit (VPD)), performed best at representing the conditions favoring initiation and size of significant wildfire events. Conventional assessments of seasonal severity and overall landscape flammability using DMC and BUI can be continued with confidence. Fire models that incorporate BUI in overall fire potential and fire behavior assessments are likely to produce effective results throughout boreal landscapes in Alaska. One novel result is the effectiveness of VPD throughout the state, making it a potential alternative to FFMC among the short-lag/1-day indices. Conclusions: This study demonstrates the societal value of research that joins new academic research results with operational needs. Developing the framework to do this more effectively will bring science to action with a shorter lag time, which is critical as we face growing challenges from a changing climate.more » « less
-
Abstract. In the western United States, prolonged drought, a warming climate, and historical fuel buildup have contributed to larger and more intense wildfires as well as to longer fire seasons. As these costly wildfires become more common, new tools and methods are essential for improving our understanding of the evolution of fires and how extreme weather conditions, including heat waves, windstorms, droughts, and varying levels of active-fire suppression, influence fire spread. Here, we develop the Geostationary Operational Environmental Satellites (GOES)-Observed Fire Event Representation (GOFER) algorithm to derive the hourly fire progression of large wildfires and create a product of hourly fire perimeters, active-fire lines, and fire spread rates. Using GOES-East and GOES-West geostationary satellite detections of active fires, we test the GOFER algorithm on 28 large wildfires in California from 2019 to 2021. The GOFER algorithm includes parameter optimizations for defining the burned-to-unburned boundary and correcting for the parallax effect from elevated terrain. We evaluate GOFER perimeters using 12 h data from the Visible Infrared Imaging Radiometer Suite (VIIRS)-derived Fire Event Data Suite (FEDS) and final fire perimeters from the California's Fire and Resource Assessment Program (FRAP). Although the GOES imagery used to derive GOFER has a coarser resolution (2 km at the Equator), the final fire perimeters from GOFER correspond reasonably well to those obtained from FRAP, with a mean Intersection-over-Union (IoU) of 0.77, in comparison to 0.83 between FEDS and FRAP; the IoU indicates the area of overlap over the area of the union relative to the reference perimeters, in which 0 is no agreement and 1 is perfect agreement. GOFER fills a key temporal gap present in other fire tracking products that rely on low-Earth-orbit imagery, where perimeters are available at intervals of 12 h or longer or at ad hoc intervals from aircraft overflights. This is particularly relevant when a fire spreads rapidly, such as at maximum hourly spread rates of over 5 km h−1. Our GOFER algorithm for deriving the hourly fire progression using GOES can be applied to large wildfires across North and South America and reveals considerable variability in the rates of fire spread on diurnal timescales. The resulting GOFER product has a broad set of potential applications, including the development of predictive models for fire spread and the improvement of atmospheric transport models for surface smoke estimates. The resulting GOFER product has a broad set of potential applications, including the development of predictive models for fire spread and the improvement of atmospheric transport models for surface smoke estimates (https://doi.org/10.5281/zenodo.8327264, Liu et al., 2023).more » « less
-
Abstract The purpose of this research is to build an operational model for predicting wildfire occurrence for the contiguous United States (CONUS) in the 1–10-day range using the U-Net 3+ machine learning model. This paper illustrates the range of model performance resulting from choices made in the modeling process, such as how labels are defined for the model and how input variables are codified for the model. By combining the capabilities of the U-Net 3+ model with a neighborhood loss function, fractions skill score (FSS), we can quantify model success by predictions made both in and around the location of the original fire occurrence label. The model is trained on weather, weather-derived fuel, and topography observational inputs and labels representing fire occurrence. Observational weather, weather-derived fuel, and topography data are sourced from the gridded surface meteorological (gridMET) dataset, a daily, CONUS-wide, high-spatial-resolution dataset of surface meteorological variables. Fire occurrence labels are sourced from the U.S. Department of Agriculture’s Fire Program Analysis Fire-Occurrence Database (FPA-FOD), which contains spatial wildfire occurrence data for CONUS, combining data sourced from the reporting systems of federal, state, and local organizations. By exploring the many aspects of the modeling process with the added context of model performance, this work builds understanding around the use of deep learning to predict fire occurrence in CONUS. Significance StatementOur work seeks to explore the limits to which deep learning can predict wildfire occurrence in CONUS with the ultimate goal of providing decision support to those allocating fire resources during high fire seasons. By exploring with what accuracy and lead time we can provide insights to these persons, we hope to reduce loss of life, reduce damage to property, and improve future event preparedness. We compare two models, one trained on all fires in the continental United States and the other on only large lightning fires. We found that a model trained on all fires produced a higher probability of fire.more » « less