Search NASA⌕ Search

SEARCH · Search NASA

Results for “WILDFIRE PREDICTING”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Machine learning and artificial intelligence for wildfire prediction

Wildfire ignition, intensity, and spread rates are tightly linked with water cycle extremes. The science of wildfire prediction has traditionally encompassed the use of physical and empirical models to quantify the direction and speed of fire spread, plume injection and fire-aerosol impacts on atmospheric composition, predictions of fire season severity on subseasonal-to-seasonal (S2S) time scales, and assessment of the spatial and temporal patterns of fire risk across landscapes. Together with expanding observation networks, machine learning and artificial intelligence (AI) have the potential to revolutionize the application of such models for fire science, saving lives, protecting critical infrastructure, and providing more accurate estimates of wildfire-climate feedbacks.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

ELM2.1-XGBfire1.0: improving wildfire prediction by integrating a machine learning fire model in a land surface model

Wildfires have shown increasing trends in both frequency and severity across the contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth system models (ESMs). Alternatively, fire models based on machine learning (ML), which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ELM2.1-XGBFire1.0) that integrates an eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran–C–Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001–2019, the ELM2.1-XGBFire1.0 outperforms process-based fire models in terms of spatial distribution and seasonal variations. The ELM2.1-XGBFire1.0 has proven to be a new tool for studying vegetation–fire interactions and, more importantly, enables seamless exploration of climate–fire feedback, working as an active component of E3SM.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Improving North American Wildfire Prediction by Integrating a Machine-Learning Fire Model in a Land Surface Model

Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001-2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2022

Using Soil Moisture Information to Better Understand and Predict Wildfire Danger: A Review of Recent Developments and Outstanding Questions

Soil moisture conditions are represented in fire danger rating systems mainly through simple drought indices based on meteorological variables, even though better sources of soil moisture information are increasingly available. This review summarises a growing body of evidence indicating that greater use of in situ, remotely sensed, and modelled soil moisture information in fire danger rating systems could lead to better estimates of dynamic live and dead herbaceous fuel loads, more accurate live and dead fuel moisture predictions, earlier warning of wildfire danger, and better forecasts of wildfire occurrence and size. Potential uses of soil moisture information in existing wildfire danger rating systems include (1) as a supplement or replacement for drought indices, (2) for live and (3) dead fuel moisture modelling, (4) for estimating herbaceous fuel curing, and (5) for estimating fuel loads. We identify key remaining research questions and note the logistical challenge of convincing wildfire professionals of the importance of soil moisture compared with more familiar wildfire danger metrics. While obstacles remain, the path forward is clear. Soil moisture information can and should be used to improve fire danger rating systems and contribute to more effective fire management for the protection of communities and ecosystems worldwide.

fuel properties↗
DOE OSTI2021

Improve wildfire predictability driven by extreme water cycle with interpretable physically-guided ML/AI

Focal Area(s): Predictive modeling using AI techniques and AI-derived model components; use of AI and other tools to design a prediction system comprising of a hierarchy of models (Primary); insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods, including explainable AI and physics or knowledge-guided AI (Secondary). Science Challenge: Wildfires modify land surface characteristics, such as vegetation composition, soil and litter carbon stocks, and surface albedo, with significant consequences for the regional carbon cycle. For example, tropical regions (i.e., African and South America) are particularly vulnerable to wildfire, account for more than 80% of the global burned area, and emit ~1.4 PgC y -1 into the atmosphere together with other dust and aerosols that strongly affect regional climate.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Performance of Fire Danger Indices and Their Utility in Predicting Future Wildfire Danger Over the Conterminous United States

Abstract Predicting current and future wildfire frequency and size is central to wildfire control and management. Multiple fire danger indices (FDIs) that incorporate weather and fuel conditions have been developed and utilized to support wildfire predictions and risk assessment. However, the scale‐dependent performance of individual FDIs remains poorly understood, which leads to large uncertainty in the estimated fire sizes under climate change. Here, we calculate four commonly used FDIs over the conterminous United States using high‐resolution (4 km) climate and fuel data sets for the 1984–2019 period. The relationships of these four FDIs to the observed wildfire sizes show that higher values of FDIs correlate to larger total fire sizes; this correlation is more robust at larger spatial scales. Sensitivity analysis indicates that the daily minimum relative humidity and precipitation are the most important drivers of the annual mean fire danger. In the instances of extreme fire danger, wind speed becomes a critical factor and should be considered in the calculation of the FDI. To assess the impact of climate change on future fire size, we calculate the present‐day and end‐of‐century FDIs using the 12 km regional climate model simulations. The four FDIs generally predict consistent changes in future fire potential, suggesting an overall higher fire potential in conjunction with a prolonged wildfire season in future climate. Regionally, the four FDIs also reveal similar seasonal patterns as the enhancement arises mostly in spring and summer over the southwest US while in summer and fall over the northern and eastern US.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Advancing Wildfire Monitoring with TEMPO and ML tools: Hourly Smoke and Fire‑Front Mapping and Near‑Surface NO₂ Predictions

Wildfires impose substantial impacts on communities and regions downwind of wildfire smoke. We present a TEMPO‑enabled workflow that generates value‑added Level‑3 smoke‑plume masks and fire‑front maps for large wildfires, such as 2024 Park Fire, using the self‑supervised deep learning system SIT‑FUSE, along with near‑surface NO₂ predictions produced by a foundation model (Microsoft Aurora). We conclude by outlining a roadmap for expanding these capabilities to additional Western U.S. wildfire events and for delivering actionable tools to stakeholders. This open-source, reproducible workflow provides a scalable framework for cross-agency wildfire monitoring to overcome traditional limitations in smoke-cloud discrimination and air-quality forecasting by incorporating TEMPO data and beyond.

Xiaohua Pan↗
DOE OSTI2023

The drivers and predictability of wildfire re-burns in the western United States (US)

Evidence is mounting that the effectiveness of using prescribed burns as a management tactic may be diminishing due to the higher incidence of wildfire re-burns. The development of predictive models of re-burns is thus essential to better understand their primary drivers so that forest management practices can be updated to account for these events. First, we assess the potential for human activity as a driver of re-burns by evaluating re-burn trends both within and outside of the wildland–urban interface (WUI) of the western US. Next, we investigate the predictability of re-burns through the application of both random forest and the explanatory machine learning non-negative matrix factorization using k-means clustering (NMFk) algorithms to predict re-burn occurrence over California based on a number of climate factors. Our findings indicate that while most states showed increasing trends within the WUI when trends were conducted over longer moving windows (e.g. 20 years), California was the only state where the rate of increase was consistently higher in the WUI, indicating a stronger potential for human activity as a driver in that location. Furthermore, we find model performance was found to be robust over most of California (Testing F1 scores = 0.688), although results were highly variable based on EPA level III Ecoregion (F1 scores = 0.0–0.778). Insights provided from this study will lead to a better understanding of climate and human activity drivers of re-burns and how these vary at broad spatial scales so that improvements in forest management practices can be tuned according to the level of change that is expected for a given region.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2001

Modeling and Prediction of Wildfire Hazard in Southern California, Integration of Models with Imaging Spectrometry

Large urban wildfires throughout southern California have caused billions of dollars of damage and significant loss of life over the last few decades. Rapid urban growth along the wildland interface, high fuel loads and a potential increase in the frequency of large fires due to climatic change suggest that the problem will worsen in the future. Improved fire spread prediction and reduced uncertainty in assessing fire hazard would be significant, both economically and socially. Current problems in the modeling of fire spread include the role of plant community differences, spatial heterogeneity in fuels and spatio-temporal changes in fuels. In this research, we evaluated the potential of Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Airborne Synthetic Aperture Radar (AIRSAR) data for providing improved maps of wildfire fuel properties. Analysis concentrated in two areas of Southern California, the Santa Monica Mountains and Santa Barbara Front Range. Wildfire fuel information can be divided into four basic categories: fuel type, fuel load (live green and woody biomass), fuel moisture and fuel condition (live vs senesced fuels). To map fuel type, AVIRIS data were used to map vegetation species using Multiple Endmember Spectral Mixture Analysis (MESMA) and Binary Decision Trees. Green live biomass and canopy moisture were mapped using AVIRIS through analysis of the 980 nm liquid water absorption feature and compared to alternate measures of moisture and field measurements. Woody biomass was mapped using L and P band cross polarimetric data acquired in 1998 and 1999. Fuel condition was mapped using spectral mixture analysis to map green vegetation (green leaves), nonphotosynthetic vegetation (NPV; stems, wood and litter), shade and soil. Summaries describing the potential of hyperspectral and SAR data for fuel mapping are provided by Roberts et al. and Dennison et al. To utilize remotely sensed data to assess fire hazard, fuel-type maps were translated into standard fuel models accessible to the FARSITE fire spread simulator. The FARSITE model and BEHAVE are considered industry standards for fire behavior analysis. Anderson level fuels map, generated using a binary decision tree classifier are available for multiple dates in the Santa Monica Mountains and at least one date for Santa Barbara. Fuel maps that will fill in the areas between Santa Barbara and the Santa Monica Mountains study sites are in progress, as part of a NASA Regional Earth Science Application Center, the Southern California Wildfire Hazard Center. Species-level maps, were supplied to fire managing agencies (Los Angeles County Fire, California Department of Forestry). Research results were published extensively in the refereed and non-refereed literature. Educational outreach included funding of several graduate students, undergraduate intern training and an article featured in the California Alliance for Minorities Program (CAMP) Quarterly Journal.

Roberts, Dar A.↗
DOE OSTI2023

Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior

The increasing incidence and severity of wildfires underscores the necessity of accurately predicting their behavior. While high-fidelity models derived from first principles offer physical accuracy, they are too computationally expensive for use in real-time fire response. Low-fidelity models sacrifice some physical accuracy and generalizability via the integration of empirical measurements, but enable real-time simulations for operational use in fire response. Machine learning techniques have demonstrated the ability to bridge these objectives by learning first-principles physics while achieving computational speedups. While deep learning approaches have demonstrated the ability to predict wildfire propagation over large time periods, time-resolved fire-spread predictions are needed for active fire management. Here, in this work, we evaluate the ability of deep learning approaches in accurately modeling the time-resolved dynamics of wildfires. We use an autoregressive process in which a convolutional recurrent deep learning model makes predictions that propagate a wildfire over 15 min increments. We apply the model to four simulated datasets of increasing complexity, containing both field fires with homogeneous fuel distribution as well as real-world topologies sampled from the California region of the United States. We show that even after 100 autoregressive predictions representing more than 24 h of simulated fire spread, the resulting models generate stable and realistic propagation dynamics, achieving a Jaccard score between 0.89 and 0.94 when predicting the resulting fire scar. The inference time of the deep learning models are examined and compared, and directions for future work are discussed.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Identifying Key Drivers of Wildfires in the Contiguous US Using Machine Learning and Game Theory Interpretation

Abstract Understanding the complex interrelationships between wildfire and its environmental and anthropogenic controls is crucial for wildfire modeling and management. Although machine learning (ML) models have yielded significant improvements in wildfire predictions, their limited interpretability has been an obstacle for their use in advancing understanding of wildfires. This study builds an ML model incorporating predictors of local meteorology, land‐surface characteristics, and socioeconomic variables to predict monthly burned area at grid cells of 0.25° × 0.25° resolution over the contiguous United States. Besides these predictors, we construct and include predictors representing the large‐scale circulation patterns conducive to wildfires, which largely improves the temporal correlations in several regions by 14%–44%. The Shapley additive explanation is introduced to quantify the contributions of the predictors to burned area. Results show a key role of longitude and latitude in delineating fire regimes with different temporal patterns of burned area. The model captures the physical relationship between burned area and vapor pressure deficit, relative humidity (RH), and energy release component (ERC), in agreement with the prior findings. Aggregating the contribution of predictor variables of all the grids by region, analyses show that ERC is the major contributor accounting for 14%–27% to large burned areas in the western US. In contrast, there is no leading factor contributing to large burned areas in the eastern US, although large‐scale circulation patterns featuring less active upper‐level ridge‐trough and low RH two months earlier in winter contribute relatively more to large burned areas in spring in the southeastern US.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

An Inventory of AI-ready Benchmark Data for US Fires, Heatwaves, and Droughts

Extreme weather events, including fires, heatwaves, and droughts, have significant impacts on earth, environmental, and energy systems. Mechanistic and predictive understanding, as well as probabilistic risk assessment of these extreme weather events, are crucial for detecting, planning for, and responding to these extremes. Records of extreme weather events provide an important data source for understanding present and future extremes, but the existing data needs preprocessing before it can be used for analysis. Moreover, there are many nonstandard metrics defining the levels of severity or impacts of extremes. In this study, we compile a comprehensive benchmark data inventory of extreme weather events, including fires, heatwaves, and droughts. The dataset covers the period from 2001 to 2020 with a daily temporal resolution and a spatial resolution of 0.5°×0.5° (~55km×55km) over the continental United States (CONUS), and a spatial resolution of 1km × 1km over the Pacific Northwest (PNW) region, together with the co-located and relevant meteorological variables. By exploring and summarizing the spatial and temporal patterns of these extremes in various forms of marginal, conditional, and joint probability distributions, we gain a better understanding of the characteristics of climate extremes. The resulting AI/ML-ready data products can be readily applied to ML-based research, fostering and encouraging AI/ML research in the field of extreme weather. This study can contribute significantly to the advancement of extreme weather research, aiding researchers, policymakers, and practitioners in developing improved preparedness and response strategies to protect communities and ecosystems from the adverse impacts of extreme weather events. Usage Notes We presented a long term (2001-2020) and comprehensive data inventory of historical extreme events with daily temporal resolution covering the separate spatial extents of CONUS (0.5°×0.5°) and PNW(1km×1km) for various applications and studies. The dataset with 0.5°×0.5° resolution for CONUS can be used to help build more accurate climate models for the entire CONUS, which can help in understanding long-term climate trends, including changes in the frequency and intensity of extreme events, predicting future extreme events as well as understanding the implications of extreme events on society and the environment. The data can also be applied for risk accessment of the extremes. For example, ML/AI models can be developed to predict wildfire risk or forecast HWs by analyzing historical weather data, and past fires or heateave , allowing for early warnings and risk mitigation strategies. Using this dataset, AI-driven risk assessment models can also be built to identify vulnerable energy and utilities infrastructure, imrpove grid resilience and suggest adaptations to withstand extreme weather events. The high-resolution 1km×1km dataset ove PNW are advantageous for real-time, localized and detailed applications. It can enhance the accuracy of early warning systems for extreme weather events, helping authorities and communities prepare for and respond to disasters more effectively. For example, ML models can be developed to provide localized HW predictions for specific neighborhoods or cities, enabling residents and local emergency services to take targeted actions; the assessment of drought severity in specific communities or watersheds within the PNW can help local authorities manage water resources more effectively.

Lin, Xinming↗
DOE OSTI2026

Multi-ignition fire complexes drive extreme fire years and impacts

Climate change is intensifying fire behavior, with the largest and fastest-spreading fires causing the greatest impacts on people and ecosystems. Yet the mechanisms driving variability and trends in large fires remain poorly understood. Using 12-hour satellite-derived fire tracking data from 2012 to 2023, we show that the merging of separate ignitions into multi-ignition complexes is a key process amplifying fire size and destructive potential across temperate and boreal ecoregions. Multi-ignition fires account for 31% of the burned area in California and 59% in the Arctic-boreal domain, spread faster and persist longer than single-ignition fires, and disproportionately contribute to extreme fire years in California, Canada, and Siberia. They also generate stronger atmospheric feedbacks, produce more pyrocumulonimbus events, and strain firefighting capacity by dispersing suppression resources. Recognizing and accounting for fire-merging dynamics are critical for improving wildfire prediction, risk assessment, and management.

Environmental sciences↗
DOE OSTI2025

Basic Research Needs for Inverse Methods for Complex Systems under Uncertainty

Inverse problems, which aim to infer unknown properties of a system using experimental and observational data, are central to addressing many of the U.S. Department of Energy’s (DOE) most critical scientific and engineering challenges. Accurate, computationally efficient, and data-efficient solutions to inverse problems are essential for advancing DOE mission-critical science drivers, including analyzing data from large-scale experimental facilities, optimizing fusion reactor performance, accelerating materials discovery, enhancing geophysical imaging, improving wildfire predictions, and enabling autonomous systems and digital twins. However, these problems are becoming increasingly complex, often involving nonlinear, highdimensional, and interconnected systems and models that span multiple physics and scales, while relying on data with varying quantity, quality, and information content. Compounding these challenges is the uncertainty inherent in DOE-relevant systems, where errors in inputs, noise in data, incompleteness of data, and discrepancies between models and reality constrain the accuracy and precision of solutions. At the same time, the convergence of recent scientific computing trends—scientific machine learning, artificial intelligence, and computing advances such as exascale computing—is creating unprecedented opportunities for tackling these challenges. The cross-cutting nature of inverse problems, combined with their growing complexity and rapidly evolving data and algorithmic demands, strongly motivates the formulation of a prioritized research agenda to maximize their capabilities and impact. In response to this need, DOE’s Advanced Scientific Computing Research (ASCR) program in the Office of Science convened the Workshop on Basic Research Needs for Inverse Problems for Complex Systems Under Uncertainty in June 2025. This workshop brought together experts across disciplines to identify grand challenges and major opportunities in the field. Through collaborative discussions, the workshop defined transformative research directions aimed at addressing the mathematical, statistical, and computational challenges posed by inverse problems under uncertainty. As a result of these efforts, four priority research directions (PRDs) were identified to guide future research and development in this area. These PRDs, summarized below, represent a roadmap for advancing the foundational science and mathematics of inverse problems, enabling robust, scalable, and uncertainty-aware solutions that are critical for DOE applications.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2005

A Testbed Demonstration of an Intelligent Archive in a Knowledge Building System

The last decade's influx of raw data and derived geophysical parameters from several Earth observing satellites to NASA data centers has created a data-rich environment for Earth science research and applications. While advances in hardware and information management have made it possible to archive petabytes of data and distribute terabytes of data daily to a broad community of users, further progress is necessary in the transformation of data into information, and information into knowledge that can be used in particular applications in order to realize the full potential of these valuable datasets. In examining what is needed to enable this progress in the data provider environment that exists today and is expected to evolve in the next several years, we arrived at the concept of an Intelligent Archive in context of a Knowledge Building System (IA/KBS). Our prior work and associated papers investigated usage scenarios, required capabilities, system architecture, data volume issues, and supporting technologies. We identified six key capabilities of an IA/KBS: Virtual Product Generation, Significant Event Detection, Automated Data Quality Assessment, Large-Scale Data Mining, Dynamic Feedback Loop, and Data Discovery and Efficient Requesting. Among these capabilities, large-scale data mining is perceived by many in the community to be an area of technical risk. One of the main reasons for this is that standard data mining research and algorithms operate on datasets that are several orders of magnitude smaller than the actual sizes of datasets maintained by realistic earth science data archives. Therefore, we defined a test-bed activity to implement a large-scale data mining algorithm in a pseudo-operational scale environment and to examine any issues involved. The application chosen for applying the data mining algorithm is wildfire prediction over the continental U.S. This paper reports a number of observations based on our experience with this test-bed. While proof-of-concept for data mining scalability and utility has been a major goal for the research reported here, it was not the only one. The other five capabilities of an WKBS named above have been considered as well, and an assessment of the implications of our experience for these other areas will also be presented. The lessons learned through the testbed effort and presented in this paper will benefit technologists, scientists, and system operators as they consider introducing IA/KBS capabilities into production systems.

Ramapriyan, Hampapuram↗
NASA NTRS2023

Impacts of Estimated Plume Rise on PM 2.5 Exceedance Prediction During Extreme Wildfire Events: A Comparison of Three Schemes (Briggs, Freitas, and Sofiev)

Plume height plays a vital role in wildfire smoke dispersion and the subsequent effects on air quality and human health. In this study, we assess the impact of different plume rise schemes on predicting the dispersion of wildfire air pollution and the exceedances of the National Ambient Air Quality Standards (NAAQS) for fine particulate matter (PM 2.5 ) during the 2020 western United States wildfire season. Three widely used plume rise schemes (Briggs, 1969; Freitas et al., 2007; Sofiev et al., 2012) are compared within the Community Multiscale Air Quality (CMAQ) modeling framework. The plume heights simulated by these schemes are comparable to the aerosol height observed by the Multi-angle Imaging SpectroRadiometer (MISR) and Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO). The performance of the simulations with these schemes varies by fire case and weather conditions. On average, simulations with higher plume injection heights predict lower aerosol optical depth (AOD) and surface PM 2.5 concentrations near the source region but higher AOD and PM 2.5 in downwind regions due to the faster spread of the smoke plume once ejected. The 2-month mean AOD difference caused by different plume rise schemes is approximately 20 %–30 % near the source regions and 5 %–10 % in the downwind regions. Thick smoke blocks sunlight and suppresses photochemical reactions in areas with high AOD. The surface PM 2.5 difference reaches 70 % on the West Coast of the USA, and the difference is lower than 15 % in the downwind regions. Moreover, the plume injection height affects pollution exceedance (>35 µg m−3) predictions. Higher plume heights generally produce larger downwind PM 2.5 exceedance areas. The PM 2.5 exceedance areas predicted by the three schemes largely overlap, suggesting that all schemes perform similarly during large wildfire events when the predicted concentrations are well above the exceedance threshold. At the edges of the smoke plumes, however, there are noticeable differences in the PM 2.5 concentration and predicted PM 2.5 exceedance region. For the whole period of study, the difference in the total number of exceedance days could be as large as 20 d in northern California and 4 d in the downwind regions. This disagreement among the PM 2.5 exceedance forecasts may affect key decision-making regarding early warning of extreme air pollution episodes at local levels during large wildfire events.

Yunyao Li↗