Lightning-Ignited Wildfires On A Global Scale: Prediction and Climate Change Projections based on Explainable Machine Learning Models

Wildfires pose a significant natural disaster risk to populations and contribute to accelerated climate change. As wildfires are also affected by climate change, extreme wildfires are becoming increasingly frequent. Although they occur less frequently globally than those sparked by human activities, lightning-ignited wildfires play a substantial role in carbon emissions andaccount for the majority of burned areas in certain regions. While existing computational models, especially those based on machine learning, aim to predict lightning-ignited wildfires, they are typically tailored to specific regions with unique characteristics, limiting their global applicability. In this study, we present machine learning models designed to characterize and predict lightning-ignited wildfires on a global scale. Our approach involves classifying lightning-ignited versus anthropogenic wildfires globally over a long timespan, and estimating with high accuracy of over 91% the probability of lightning to ignite a fire based on a wide spectrum of factors such as meteorological conditions and vegetation. Utilizing these models, we analyze seasonal and spatial trends in lightning-ignited wildfires shedding light on the impact of climate change on this phenomenon. Our findings highlight significant global differences between anthropogenic and lightning-ignited wildfires. Moreover, we demonstrate that, even over a short time span of less than a decade, climate changes have steadily increased the global risk of lightning-ignited wildfires. We also find that models trained to predict lightning-ignited wildfires and models trained to predict anthropogenic wildfires are very different. This dramatically reduces the predictive performance of models trained on anthropogenic wildfires when applied to lightning-ignited ignitions, and vice versa. This distinction underscores the imperative need for dedicated predictive models and fire weather indices tailored specifically to each type of wildfire.