10 June 2021 in Earth's Future
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.
28 September 2020 in Atmospheric Chemistry and Physics
Occurrences of devastating wildfires have been increasing in the United States for the past decades. While some environmental controls, including weather, climate, and fuels, are known to play important roles in controlling wildfires, the interrelationships between these factors and wildfires are highly complex and may not be well represented by traditional parametric regressions. Here we develop a model consisting of multiple machine learning algorithms to predict gridded monthly wildfire burned area over the south central United States during 2002–2015 and then use this model to identify the relative importance of the environmental drivers on the burned area for both the winter–spring and summer fire seasons of that region. The developed model alleviates the issue of unevenly distributed burned-area data, predicts burned grids with area under the curve (AUC) of 0.82 and 0.83 for the two seasons, and achieves temporal correlations larger than 0.5 for more than 70 % of the grids and spatial correlations larger than 0.5 (p<0.01) for more than 60 % of the months. For the total burned area over the study domain, the model can explain 50 % and 79 % of the observed interannual variability for the winter–spring and summer fire season, respectively. Variable importance measures indicate that relative humidity (RH) anomalies and preceding months' drought severity are the two most important predictor variables controlling the spatial and temporal variation in gridded burned area for both fire seasons. The model represents the effect of climate variability by climate-anomaly variables, and these variables are found to contribute the most to the magnitude of the total burned area across the whole domain for both fire seasons. In addition, antecedent fuel amounts and conditions are found to outweigh the weather effects on the amount of total burned area in the winter–spring fire season, while fire weather is more important for the summer fire season likely due to relatively sufficient vegetation in this season.
4 December 2019 in Journal of Geophysical Research: Atmospheres
The diurnal cycle of surface ozone is directly influenced by the chemistry and meteorological processes which affect a region. This study uniquely employs a clustering methodology to examine the complete diurnal pattern of surface ozone for the Houston‐Galveston‐Brazoria region and links the identified patterns to meteorological regimes for June, July, and August of 3 years (2011, 2014, and 2015). Four features were implemented into the clustering algorithm: ozone rate of decrease at night, daily minimum before sunrise, rate of increase after sunrise, and an average of afternoon ozone. Four clusters were chosen, ranging from a mostly flat diurnal pattern with low mixing ratios (~20 ppbv) throughout the day (Cluster 1), to a more variable diurnal cycle with very high mixing ratios (>70 ppbv) in the afternoon (Cluster 4). The clusters are found to associate with distinctive circulation patterns and well‐known regional meteorological processes, such as the low‐level jet and Bermuda High. The uneven distribution of the clusters between the years helps elucidate ozone interannual variability due to meteorology: Cluster 4 had 0 days assigned from 2014 due to the greater influence of circulation patterns bringing clean air from the Gulf of Mexico. We show that the clustering method better characterizes ozone variability than the simplistic method of dividing peak ozone into quantiles. With the clustering analysis, we demonstrate that the ozone diurnal pattern holds more value than just peak ozone hours of the day in providing a clearer understanding of ozone variability and associated meteorological processes.
24 July 2023 in Journal of Geophysical Research: Atmospheres
Increasing temperature and water cycle changes due to warming climate may increase the frequency and intensity of wildfires. Fire emission projections are useful for informing strategies for adaptation and mitigation of fire impacts on societies and ecosystems. Here, we construct a neural network (NN) model explained by the Shapley Additive explanation to predict fire PM2.5 emissions change and understand their drivers over the contiguous US (CONUS) in the mid‐21st century under a high greenhouse gas emissions scenario (SSP5‐8.5). Using future meteorology and leaf area index (LAI) simulated by eight global climate models from the Coupled Model Intercomparison Project Phase 6, future population density, and present‐day land use and land cover (LULC) as input to the NN model, the total fire PM2.5 emissions over CONUS are projected to increase by 4%–75% (model spread). Among different regions, fire emissions in the western US are projected to increase more significantly in June‐July‐August than in other seasons and regions, with the median ratios of future to present‐day fire emissions ranging from 1.67 to 2.86. The increases in fire emissions are mainly driven by increasing normalized temperature (23%–29%) and decreasing soil moisture (2%–10%) in the future. When future LULC change is considered, the projected fire emissions further increase by 58%–83% over the western US compared to projections without LULC change because of future increases in vegetation fraction. The results highlight the important role of warmer temperature, decreasing soil moisture, and LULC change in increasing fire emissions in the future.
14 August 2018 in Journal of Geophysical Research: Atmospheres
Fire emissions from Mexico and Central America are transported regularly to the U.S. Gulf Coast every spring under prevailing circulation patterns and affect U.S. air quality. Here we use a GEOS‐Chem passive tracer simulation to develop the climatology of transport pathways of fire emissions over a long‐term time period of April and May 2002–2015 and estimate their adverse air quality effects for urban areas along the Gulf Coast. A conceptual model is presented to describe the transport mechanisms, which involve southerly low‐level jets in the lower troposphere and warm conveyor belt in the middle troposphere. The warm conveyor belts and the southerly low‐level jets explain 31% and 69% of the interannual variability of the mid‐altitude (1.5–6 km) and low‐altitude events (0–1.5 km), respectively. Considering both transport and fire emissions, approximately 9% of the study period (59–88 days of 854 days) were identified as large pollution events during which Central American fire emissions adversely impacted surface air quality at several major urban centers along the Gulf Coast, including Houston and Corpus Christi in TX, New Orleans in LA, Mobile in AL, and Pensacola in FL. Compared to clean maritime flow from the Gulf of Mexico, these events were estimated to result in average enhancements of maximum daily average 8‐hr (MDA8) ozone and daily PM2.5 (fine particulate matter <2.5 μm in diameter) in the Gulf Coast cities of 3–12 ppbv and 2–5 μg/m3, respectively. Only one ozone exceedance day (79 ppbv, on 18 May 2003) was found among the fire‐impact days for the Houston region.
15 March 2022 in Atmospheric Chemistry and Physics
Annual burned areas in the United States have increased 2-fold during the past decades. With more large fires resulting in more emissions of fine particulate matter, an accurate prediction of fire emissions is critical for quantifying the impacts of fires on air quality, human health, and climate. This study aims to construct a machine learning (ML) model with game-theory interpretation to predict monthly fire emissions over the contiguous US (CONUS) and to understand the controlling factors of fire emissions. The optimized ML model is used to diagnose the process-based models in the Fire Modeling Intercomparison Project (FireMIP) to inform future development. Results show promising performance for the ML model, Community Land Model (CLM), and Joint UK Land Environment Simulator-Interactive Fire And Emission Algorithm For Natural Environments (JULES-INFERNO) in reproducing the spatial distributions, seasonality, and interannual variability of fire emissions over the CONUS. Regional analysis shows that only the ML model and CLM simulate the realistic interannual variability of fire emissions for most of the subregions (r>0.95 for ML and for CLM), except for Mediterranean California, where all the models perform poorly (r=0.74 for ML and r<0.30 for the FireMIP models). Regarding seasonality, most models capture the peak emission in July over the western US. However, all models except for the ML model fail to reproduce the bimodal peaks in July and October over Mediterranean California, which may be explained by the smaller wind speeds of the atmospheric forcing data during Santa Ana wind events and limitations in model parameterizations for capturing the effects of Santa Ana winds on fire activity. Furthermore, most models struggle to capture the spring peak in emissions in the southeastern US, probably due to underrepresentation of human effects and the influences of winter dryness on fires in the models. As for extreme events, both the ML model and CLM successfully reproduce the frequency map of extreme emission occurrence but overestimate the number of months with extremely large fire emissions. Comparing the fire PM2.5 emissions from the ML model with process-based fire models highlights their strengths and uncertainties for regional analysis and prediction and provides useful insights into future directions for model improvements.