Burned area mapping across the Arctic-boreal zone with Landsat and Sentinel-2 imagery

Wildfires in the Arctic-boreal zone have increased in frequency over recent decades, carrying substantial ecological, social, and economic consequences. Remote sensing is crucial for mapping burned areas, monitoring wildfire dynamics, and evaluating their impacts. However, existing high-latitude burned area products suffer from significant discrepancies, particularly in Siberia, and their coarse spatial resolutions limit accuracy and utility. To address these gaps, we developed a convolutional neural network model to map burned areas at a 30 m resolution across the Arctic- boreal zone using Landsat and Sentinel-2 imagery. Using vegetation indices including the normalized burn ratio, normalized difference vegetation index, and normalized difference infrared index our model achieved strong performance, with an Intersection Over Union (IOU) of 0.77 and an F1 score of 0.85 on unseen test data. Performance was higher in North America (IOU = 0.84) than in Eurasia (IOU = 0.72), reflecting regional differences in fire regimes and data quality. Predictions for six representative years showed our model’s burned area closely matched the median values of Landsat, MODIS, and VIIRS-based products, although alignment varied annually and spatially. Visual assessments indicated our approach was generally more accurate, notably in detecting unburned vegetation islands within fire perimeters missed by other products. This research has numerous potential applications, such as analysing feedback between vegetation and burn patterns, characterizing spatial dynamics of unburned islands, and improving carbon emission estimates through detailed burn severity assessments.