An official website of the United States government
Abstract Cloud‐to‐ground lightning with minimal rainfall (“dry” lightning) is a major wildfire ignition source in the western United States (WUS). Although dry lightning is commonly defined as occurring with <2.5 mm of daily‐accumulated precipitation, a rigorous quantification of precipitation amounts concurrent with lightning‐ignited wildfires (LIWs) is lacking. We combine wildfire, lightning and precipitation data sets to quantify these ignition precipitation amounts across ecoprovinces of the WUS. The median precipitation for all LIWs is 2.8 mm but varies with vegetation and fire characteristics. “Holdover” fires not detected until 2–5 days following ignition occur with significantly higher precipitation (5.1 mm) compared to fires detected promptly after ignition (2.5 mm), and with cooler and wetter environmental conditions. Further, there is substantial variation in precipitation associated with promptly‐detected (1.7–4.6 mm) and holdover (3.0–7.7 mm) fires across ecoprovinces. Consequently, the widely‐used 2.5 mm threshold does not fully capture lightning ignition risk and incorporating ecoprovince‐specific precipitation amounts would better inform WUS wildfire prediction and management.
more »
« less
Predicting Cloud‐To‐Ground Lightning in the Western United States From the Large‐Scale Environment Using Explainable Neural Networks
Abstract Lightning is a major source of wildfire ignition in the western United States (WUS). We build and train convolutional neural networks (CNNs) to predict the occurrence of cloud‐to‐ground (CG) lightning across the WUS during June–September from the spatial patterns of seven large‐scale meteorological variables from reanalysis (1995–2022). Individually trained CNN models at each 1° × 1° grid cell (n = 285 CNNs) show high skill at predicting CG lightning days across the WUS (median AUC = 0.8) and perform best in parts of the interior Southwest where summertime CG lightning is most common. Further, interannual correlation between observed and predicted CG lightning days is high (medianr = 0.87), demonstrating that locally trained CNNs realistically capture year‐to‐year variation in CG lightning activity across the WUS. We then use layer‐wise relevance propagation (LRP) to investigate the relevance of predictor variables to successful CG lightning prediction in each grid cell. Using maximum LRP values, our results show that two thermodynamic variables—ratio of surface moist static energy to free‐tropospheric saturation moist static energy, and the 700–500 hPa lapse rate—are the most relevant CG lightning predictors for 93%–96% of CNNs depending on the LRP variant used. As lightning is not directly simulated by global climate models, these CNNs could be used to parameterize CG lightning in climate models to assess changes in future CG lightning occurrence with projected climate change. Understanding changes in CG lightning risk and consequently lightning‐caused wildfire risk across the WUS could inform fire management, planning, and disaster preparedness.
more »
« less
- Award ID(s):
- 2019762
- PAR ID:
- 10597104
- Publisher / Repository:
- AGU
- Date Published:
- Journal Name:
- Journal of Geophysical Research: Atmospheres
- Volume:
- 129
- Issue:
- 22
- ISSN:
- 2169-897X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract. The annual area burned due to wildfires in the western United States (WUS) increased bymore than 300 % between 1984 and 2020. However, accounting for the nonlinear, spatially heterogeneous interactions between climate, vegetation, and human predictors driving the trends in fire frequency and sizes at different spatial scales remains a challenging problem for statistical fire models. Here we introduce a novel stochastic machine learning (SML) framework, SMLFire1.0, to model observed fire frequencies and sizes in 12 km × 12 km grid cells across the WUS. This framework is implemented using mixture density networks trained on a wide suite of input predictors. The modeled WUS fire frequency matches observations at both monthly (r=0.94) and annual (r=0.85) timescales, as do the monthly (r=0.90) and annual (r=0.88) area burned. Moreover, the modeled annual time series of both fire variables exhibit strong correlations (r≥0.6) with observations in 16 out of 18 ecoregions. Our ML model captures the interannual variability and the distinct multidecade increases in annual area burned for both forested and non-forested ecoregions. Evaluating predictor importance with Shapley additive explanations, we find that fire-month vapor pressure deficit (VPD) is the dominant driver of fire frequencies and sizes across the WUS, followed by 1000 h dead fuel moisture (FM1000), total monthly precipitation (Prec), mean daily maximum temperature (Tmax), and fraction of grassland cover in a grid cell. Our findings serve as a promising use case of ML techniques for wildfire prediction in particular and extreme event modeling more broadly. They also highlight the power of ML-driven parameterizations for potential implementation in fire modules of dynamic global vegetation models (DGVMs) and earth system models (ESMs).more » « less
-
Abstract Species distribution models (SDMs) that rely on regional‐scale environmental variables will play a key role in forecasting species occurrence in the face of climate change. However, in the Anthropocene, a number of local‐scale anthropogenic variables, including wildfire history, land‐use change, invasive species, and ecological restoration practices can override regional‐scale variables to drive patterns of species distribution. Incorporating these human‐induced factors into SDMs remains a major research challenge, in part because spatial variability in these factors occurs at fine scales, rendering prediction over regional extents problematic. Here, we used big sagebrush (Artemisia tridentataNutt.) as a model species to explore whether including human‐induced factors improves the fit of the SDM. We applied a Bayesian hurdle spatial approach using 21,753 data points of field‐sampled vegetation obtained from the LANDFIRE program to model sagebrush occurrence and cover by incorporating fire history metrics and restoration treatments from 1980 to 2015 throughout the Great Basin of North America. Models including fire attributes and restoration treatments performed better than those including only climate and topographic variables. Number of fires and fire occurrence had the strongest relative effects on big sagebrush occurrence and cover, respectively. The models predicted that the probability of big sagebrush occurrence decreases by 1.2% (95% CI: −6.9%, 0.6%) when one fire occurs and cover decreases by 44.7% (95% CI: −47.9%, −41.3%) if at least one fire occurred over the 36 year period of record. Restoration practices increased the probability of big sagebrush occurrence but had minimal effect on cover. Our results demonstrate the potential value of including disturbance and land management along with climate in models to predict species distributions. As an increasing number of datasets representing land‐use history become available, we anticipate that our modeling framework will have broad relevance across a range of biomes and species.more » « less
-
Abstract Lightning occurring with less than 2.5 mm of rainfall—typically referred to as ‘dry lightning’—is a major source of wildfire ignition in central and northern California. Despite being rare, dry lightning outbreaks have resulted in destructive fires in this region due to the intersection of dense, dry vegetation and a large population living adjacent to fire-prone lands. Since thunderstorms are much less common in this region relative to the interior West, the climatology and drivers of dry lightning have not been widely investigated in central and northern California. Using daily gridded lightning and precipitation observations (1987–2020) in combination with atmospheric reanalyses, we characterize the climatology of dry lightning and the associated meteorological conditions during the warm season (May–October) when wildfire risk is highest. Across the domain, nearly half (∼46%) of all cloud-to-ground lightning flashes occurred as dry lightning during the study period. We find that higher elevations (>2000 m) receive more dry lightning compared to lower elevations (<1000 m) with activity concentrated in July-August. Although local meteorological conditions show substantial spatial variation, we find regionwide enhancements in mid-tropospheric moisture and instability on dry lightning days relative to background climatology. Additionally, surface temperatures, lower-tropospheric dryness, and mid-tropospheric instability are increased across the region on dry versus wet lightning days. We also identify widespread dry lightning outbreaks in the historical record, quantify their seasonality and spatial extent, and analyze associated large-scale atmospheric patterns. Three of these four atmospheric patterns are characterized by different configurations of ridging over the continental interior and offshore troughing. Understanding the meteorology of dry lightning across this region can inform forecasting of possible wildfire ignitions and is relevant for assessing changes in dry lightning and wildfire risk in climate projections.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
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1029/2024JD042147
