skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Prescribed Fire Modeling using Knowledge-Guided Machine Learning for Land Management
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
Award ID(s):
2313174 2134904
PAR ID:
10511791
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Publisher / Repository:
SIAM
Date Published:
Journal Name:
SIAM International Conference on Data Mining (SDM24)
Subject(s) / Keyword(s):
prescribed fire modeling knowledge-guided machine learning probabilistic graphical model surrogate model
Format(s):
Medium: X
Location:
Houston, TX
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Fire)
    GrantWilliamson (Ed.)
    Increasing wildfire activities across the Great Plains has raised concerns about the effectiveness and safety of prescribed fire as a land management tool. This study analyzes wildfire records from 1992 to 2020 to assess spatiotemporal patterns in wildfire risk and evaluate the role of prescribed fires through the combined analysis of wildfire and prescribed fire data. Results show a threefold increase in both wildfire frequency and area burned, with fire size increasing from east to west and frequency rising from north to south. Wildfire seasons are gradually occurring earlier due to climate change. Negative correlation between prescribed fires in spring and wildfires in summer indicated the effectiveness of prescribed fire in mitigating wildfire risk. Drought severity accounted for 51% of the interannual variability in area burned, while grass curing accounted for 60% of monthly variability of wildfires in grasslands. The ratio of wildfire area burned to total area burned (dominated by prescribed fires) declined from over 20% in early March to below 1% by early April. The results will lay a foundation for the development of a localized fire risk assessment tool that integrates various long-term, mid-term, and short-term risk factors, and support more effective fire management in this region. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, Journal of Geophysical Research: Atmospheres)
    Abstract Predicting the evolution of burned area, smoke emissions, and energy release from wildfires is crucial to air quality forecasting and emergency response planning yet has long posed a significant scientific challenge. Here we compare predictions of burned area and fire radiative power from the coupled weather/fire‐spread model WRF‐Fire (Weather and Research Forecasting Tool with fire code), against simpler methods typically used in air quality forecasts. We choose the 2019 Williams Flats Fire as our test case due to a wealth of observations and ignite the fire on different days and under different configurations. Using a novel re‐gridding scheme, we compare WRF‐Fire's heat output to geostationary satellite data at 1‐hr temporal resolution. We also evaluate WRF‐Fire's time‐resolved burned area against high‐resolution imaging from the National Infrared Operations aircraft data. Results indicate that for this study, accounting for containment efforts in WRF‐Fire simulations makes the biggest difference in achieving accurate results for daily burned area predictions. When incorporating novel containment line inputs, fuel density increases, and fuel moisture observations into the model, the error in average daily burned area is 30% lower than persistence forecasting over a 5‐day forecast. Prescribed diurnal cycles and those resolved by WRF‐Fire simulations show a phase offset of at least an hour ahead of observations, likely indicating the need for dynamic fuel moisture schemes. This work shows that with proper configuration and input data, coupled weather/fire‐spread modeling has the potential to improve smoke emission forecasts. 
    more » « less
  3. ; ; ; ; ; ; ; ; (, Fire)
    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
  4. ; ; ; ; ; ; ; ; (, Earth's Future)
    Abstract The area burned in the western United States during the 2020 fire season was the greatest in the modern era. Here we show that the number of human‐caused fires in 2020 also was elevated, nearly 20% higher than the 1992–2019 average. Although anomalously dry conditions enabled ignitions to spread and contributed to record area burned, these conditions alone do not explain the surge in the number of human‐caused ignitions. We argue that behavioral shifts aimed at curtailing the spread of COVID‐19 altered human‐environment interactions to favor increased ignitions. For example, the number of recreation‐caused wildfires during summer was 36% greater than the 1992–2019 average; this increase was likely a function of increased outdoor recreational activity in response to social distancing measures. We hypothesize that the combination of anomalously dry conditions and COVID‐19 social disruptions contributed to widespread increases in human‐caused ignitions, adding complexity to fire management efforts during the 2020 western US fire season. Knowledge of how social behavior changes indirectly contributed to the increased number of ignitions in the 2020 wildfire season can help inform resource management in an increasingly flammable world. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al (, Geoscientific Model Development)
    Abstract. We present the Fire Inventory from National Center for Atmospheric Research (NCAR) version 2.5 (FINNv2.5), a fire emissions inventory that provides publicly available emissions of trace gases and aerosols for various applications, including use in global and regional atmospheric chemistry modeling. FINNv2.5 includes numerous updates to the FINN version 1 framework to better represent burned area, vegetation burned, and chemicals emitted. Major changes include the use of active fire detections from the Visible Infrared Imaging Radiometer Suite (VIIRS) at 375 m spatial resolution, which allows smaller fires to be included in the emissions processing. The calculation of burned area has been updated such that a more rigorous approach is used to aggregate fire detections, which better accounts for larger fires and enables using multiple satellite products simultaneously for emissions estimates. Fuel characterization and emissions factors have also been updated in FINNv2.5. Daily fire emissions for many trace gases and aerosols are determined for 2002–2019 (Moderate Resolution Imaging Spectroradiometer (MODIS)-only fire detections) and 2012–2019 (MODIS + VIIRS fire detections). The non-methane organic gas emissions are allocated to the species of several commonly used chemical mechanisms. We compare FINNv2.5 emissions against other widely used fire emissions inventories. The performance of FINNv2.5 emissions as inputs to a chemical transport model is assessed with satellite observations. Uncertainties in the emissions estimates remain, particularly in Africa and South America during August–October and in southeast and equatorial Asia in March and April. Recommendations for future evaluation and use are given. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email