Distinct seasonality and trends of natural and anthropogenic wildfires in boreal forests

Distinguishing wildfire ignition causes and characterizing their respective fire regimes are critical for developing targeted prevention and management strategies. However, wildfire ignition information remains sparse across boreal forests due to their remoteness and lack of in-situ observations. Based on satellite observations from 2002 to 2022, this study employs a novel machine-learning attribution framework to distinguish natural and anthropogenic wildfires in boreal forests and characterize their distinct seasonal patterns and temporal variations. Results demonstrate that human activities drive a significant increase in anthropogenic fires in spring, whereas natural fires prevail in summer. In contrast to the relative stability of natural fires, anthropogenic fires decline significantly over 2002–2022, potentially reflecting the combined effects of reduced traditional burning practices and intensified fire suppression efforts. The proposed framework provides a scalable, data-driven approach for quantifying human impacts on boreal fire regimes, supporting evidence-based wildfire management at broader spatial scales.