| Abstrakt: |
Dry lightning is a prevalent episodic natural ignition source for wildfires, particularly in remote regions where such fires can escalate into uncontrollable events, burning extensive areas. In this study, we aimed to understand the interplay of environmental, fuel, and geographical factors in evaluating the probability of fire initiation following dry lightning strikes in Tasmania, Australia. We integrated dry lightning, active fire records, and gridded data on fire weather, fuel, and topography into a binary classification framework for both fire‐initiating and non‐fire‐causing lightning strikes. Employing statistical and machine learning techniques, we quantified the likelihood of fire initiation due to dry lightning, with the resampled Random Forest model exhibiting notable performance with an ROC‐AUC value of 0.98. Our findings highlight how fuel characteristics and moisture content associated with particular vegetation types influence fire initiation and provide an objective approach for identifying susceptible regions of dry lightning ignitions, informing associated fire management responses. Plain Language Summary: Lightning strikes occurring with minimal rainfall, known as dry lightning strikes, often ignite wildfires in dry vegetation, especially in remote areas. These fires can remain undetected for hours to days and quickly grow out of control under favorable conditions, causing extensive damage and burning large areas. Our study investigated how environmental factors such as weather, terrain, and fuel variables (fuel load, fuel type, and fuel moisture) affect the probability of a fire starting after a dry lightning strike in Tasmania, Australia. We analyzed data on lightning strikes, active fires, topography, fuel (via vegetation and fire history), and weather conditions, to build advanced machine learning models to predict the chances of a fire started following a dry lightning strike. Our findings indicate a high probability of ignition in scenarios characterized by high fuel loads and low fuel moisture content, particularly in treeless vegetation types such as buttongrass sedgelands. This information can help fire authorities identify areas or times most at risk of dry lightning‐ignited wildfires, allowing for better fire prevention and response strategies. Key Points: Random Forest modeling accurately identified fires ignited by dry lightning strikes in TasmaniaWestern Tasmania exhibits heightened vulnerability to wildfires ignited by lightning strikesTreeless fuel types have higher risk than forests of dry lightning ignitions [ABSTRACT FROM AUTHOR] |
Plný text