Global biomass burning fuel consumption and emissions at 500 m spatial resolution based on the Global Fire Emissions Database (GFED)

In fire emission models, the spatial resolution of both the modelling framework and the satellite data used to quantify burned area can have considerable impact on emission estimates. Consideration of this sensitivity is especially important in areas with heterogeneous land cover and fire regimes and when constraining model output with field measurements. We developed a global fire emissions model with a spatial resolution of 500 m using MODerate resolution Imaging Spectroradiometer (MODIS) data. To accommodate this spatial resolution, our model is based on a simplified version of the Global Fire Emissions Database (GFED) modelling framework. Tree mortality as a result of fire, i.e. fire-related forest loss, was modelled based on the overlap between 30 m forest loss data and MODIS burned area and active fire detections. Using this new 500 m model, we calculated global average carbon emissions from fire of 2.1±0.2 (±1σ interannual variability, IAV) Pg C yr−1 during 2002–2020. Fire-related forest loss accounted for 2.6±0.7 % (uncertainty range =1.9 %–3.3 %) of global burned area and 24±6 % (uncertainty range =16 %–31 %) of emissions, indicating that fuel consumption in forest fires is an order of magnitude higher than the global average. Emissions from the combustion of soil organic carbon (SOC) in the boreal region and tropical peatlands accounted for 13±4 % of global emissions. Our global fire emissions estimate was higher than the 1.5 Pg C yr−1 from GFED4 and similar to 2.1 Pg C yr−1 from GFED4s. Even though GFED4s included more burned area by accounting for small fires undetected by the MODIS burned area mapping algorithm, our emissions were similar to GFED4s due to higher average fuel consumption. The global difference in fuel consumption could mainly be explained by higher SOC emissions from the boreal region as constrained by additional measurements. The higher resolution of the 500 m model also contributed to the difference by improving the simulation of landscape heterogeneity and reducing the scale mismatch in comparing field measurements to model grid cell averages during model calibration. Furthermore, the fire-related forest loss algorithm introduced in our model led to more accurate and widespread estimation of high-fuel-consumption burned area. Recent advances in burned area detection at resolutions of 30 m and finer show a substantial amount of burned area that remains undetected with 500 m sensors, suggesting that global carbon emissions fro