Machine Learning–Based Observation-Constrained Projections Reveal Elevated Global Socioeconomic Risks from Wildfire
A hybrid machine learning (ML) and emergent constraint (EC) framework were developed to constrain the future fire carbon emissions simulated by the latest Earth system models and to provide reliable projections of wildfire-related socioeconomic risks.
The constrained wildfire projections call for mitigation and/or adaptation strategies to minimize the potential socioeconomic loss caused by wildfires in rapidly developing countries, and the new framework can be expanded to estimate reasonable evolution of other global and regional climate or ecosystem properties, especially those with extensive local impacts.
Reliable projections of wildfires and associated socioeconomic risks are crucial for the development of efficient and effective adaptation and mitigation strategies. The lack of or limited observational constraints for modeling outputs impairs the credibility of wildfire projections. Here, we present a combined ML and EC framework to constrain the future fire carbon emissions simulated by 13 Earth system models from the Coupled Model Intercomparison Project phase 6, using historical, observed joint states of fire-relevant variables. During the twenty-first century, the observation-constrained ensemble indicates a weaker increase in global fire carbon emissions but a higher increase in global wildfire exposure in the population, gross domestic production, and agricultural area, compared with the default ensemble. Such elevated socioeconomic risks are primarily caused by the compound regional enhancement of future wildfire activity and socioeconomic development in the western and central African countries, necessitating an emergent strategic preparedness for wildfires in these countries.