An official website of the United States government
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
This content will become publicly available on October 1, 2026
Stochastic Behaviour of Directional Fire Spread: A Segmentation-Based Analysis of Experimental Burns
Understanding the dynamics of fire propagation is essential in improving predictive models and developing effective fire management strategies. This study applies computer vision techniques to complement traditional fire behaviour modelling. We employ the Segment Anything Model to achieve the accurate segmentation of experimental fire videos, enabling the frame-by-frame segmentation of fire perimeters, quantification of the rate of spread in multiple directions, and explicit analysis of slope effects. Our laboratory experiments reveal that the ROS increases exponentially with slope, but with coefficients differing from those prescribed in the Canadian Fire Behaviour Prediction System, reflecting differences in field conditions. Complementary field data from prescribed burns in coniferous fuels (C-7) further demonstrate that slope effects vary under operational conditions, suggesting field-dependent dynamics not fully captured by existing deterministic models. Our experiments show that, even under controlled laboratory conditions, substantial variability in spread rate is observed, underscoring the inherent stochasticity of fire spread. Together, these findings highlight the value of vision-based perimeter extraction in generating precise spread data and reinforce the need for probabilistic modelling approaches that explicitly account for uncertainty and emergent dynamics in fire behaviour.
more »
« less
- Award ID(s):
- 2330582
- PAR ID:
- 10641469
- Publisher / Repository:
- Applications of Computational Statistics to Wildfire Science and Management
- Date Published:
- Journal Name:
- Fire
- Volume:
- 8
- Issue:
- 10
- ISSN:
- 2571-6255
- Page Range / eLocation ID:
- 384
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Williamson, Grant (Ed.)As wildfire activity increases worldwide, developing effective methods for estimating how fast it can spread is critical. This study aimed to develop and validate a computer vision algorithm for fire spread estimation. Using visual flame data from laboratory experiments on excelsior and pine needle fuel beds, we explored fire spread predictions for two types of experiments. In the first, the experiments were conducted in an environment where the flame was maintained visually undisturbed while in the second, real-world scenarios were simulated with visual obstructions. Algorithm performance evaluation was conducted by computing the index of agreement and normalized root mean square deviation (NRMSD) error. Results show that the algorithm estimates fire spread well in pristine visual environments with varying accuracy depending on the fuel type. For instance, the index of agreement between the rate of spread values estimated by the algorithm and the measured values is 0.56 for excelsior fuel beds and 0.51 for pine needle fuel beds. For visual obstructions, varying impacts on the rate of spread predictions were observed. Adding an orange background behind the flame had the least effect on algorithm performance (IAmedian = 0.45), followed by placing a Y-shape element resembling a branch (IAmedian = 0.31) and adding an LED light near the flame (IAmedian = 0.30).more » « less
-
BackgroundPrescribed fire is vital for fuel reduction and ecological restoration, but the effectiveness and fine-scale interactions are poorly understood. AimsWe developed methods for processing uncrewed aircraft systems (UAS) imagery into spatially explicit pyrometrics, including measurements of fuel consumption, rate of spread, and residence time to quantitatively measure three prescribed fires. MethodsWe collected infrared (IR) imagery continuously (0.2 Hz) over prescribed burns and one experimental calibration burn, capturing fire progression and combustion for multiple hours. Key resultsPyrometrics were successfully extracted from UAS-IR imagery with sufficient spatiotemporal resolution to effectively measure and differentiate between fires. UAS-IR fuel consumption correlated with weight-based measurements of 10 1-m2 experimental burn plots, validating our approach to estimating consumption with a cost-effective UAS-IR sensor (R2 = 0.99; RMSE = 0.38 kg m-2). ConclusionsOur findings demonstrate UAS-IR pyrometrics are an accurate approach to monitoring fire behaviour and effects, such as measurements of consumption. Prescribed fire is a fine-scale process; a ground sampling distance of <2.3 m2 is recommended. Additional research is needed to validate other derived measurements. ImplicationsRefined fire monitoring coupled with refined objectives will be pivotal in informing fire management of best practices, justifying the use of prescribed fire and providing quantitative feedback in an uncertain environment.more » « less
-
null (Ed.)Modelling of cardiac electrical behaviour has led to important mechanistic insights, but important challenges, including uncertainty in model formulations and parameter values, make it difficult to obtain quantitatively accurate results. An alternative approach is combining models with observations from experiments to produce a data-informed reconstruction of system states over time. Here, we extend our earlier data-assimilation studies using an ensemble Kalman filter to reconstruct a three-dimensional time series of states with complex spatio-temporal dynamics using only surface observations of voltage. We consider the effects of several algorithmic and model parameters on the accuracy of reconstructions of known scroll-wave truth states using synthetic observations. In particular, we study the algorithm’s sensitivity to parameters governing different parts of the process and its robustness to several model-error conditions. We find that the algorithm can achieve an acceptable level of error in many cases, with the weakest performance occurring for model-error cases and more extreme parameter regimes with more complex dynamics. Analysis of the poorest-performing cases indicates an initial decrease in error followed by an increase when the ensemble spread is reduced. Our results suggest avenues for further improvement through increasing ensemble spread by incorporating additive inflation or using a parameter or multi-model ensemble. This article is part of the theme issue ‘Uncertainty quantification in cardiac and cardiovascular modelling and simulation’.more » « less
-
Extreme, downslope mountain winds often generate dangerous wildfire conditions. We used the wildfire spread model Fire Area Simulator (FARSITE) to simulate two wildfires influenced by strong wind events in Santa Barbara, CA. High spatial-resolution imagery for fuel maps and hourly wind downscaled to 100 m were used as model inputs, and sensitivity tests were performed to evaluate the effects of ignition timing and location on fire spread. Additionally, burn area rasters from FARSITE simulations were compared to minimum travel time rasters from FlamMap simulations, a wildfire model similar to FARSITE that holds environmental variables constant. Utilization of two case studies during strong winds revealed that FARSITE was able to successfully reconstruct the spread rate and size of wildfires when spotting was minimal. However, in situations when spotting was an important factor in rapid downslope wildfire spread, both FARSITE and FlamMap were unable to simulate realistic fire perimeters. We show that this is due to inherent limitations in the models themselves, related to the slope-orientation relative to the simulated fire spread, and the dependence of ember launch and land locations. This finding has widespread implications, given the role of spotting in fire progression during extreme wind events.more » « less
