Advancing Eurasia Fire Understanding Through Machine Learning Techniques

TL;DR

This work addresses data scarcity in Eurasian wildfire research by presenting FiresRu, an open-access dataset of 26,681 fire events in Russia with associated meteorological conditions over 13 consecutive months. Using this dataset, the authors apply descriptive analytics and ensemble ML models, showing that solar radiation, temperature, and wind are key predictors of fire occurrence and type, with Extra Trees and Random Forest achieving ~88% accuracy. The study demonstrates the value of open data for understanding diverse Eurasian fire dynamics and provides insights to support data-driven fire management under changing environmental conditions. It also outlines directions for enriching datasets with fuel-moisture, terrain, and high-resolution forecasts to enable proactive risk assessment.

Abstract

Modern fire management systems increasingly rely on satellite data and weather forecasting; however, access to comprehensive datasets remains limited due to proprietary restrictions. Despite the ecological significance of wildfires, large-scale, multi-regional research is constrained by data scarcity. Russian diverse ecosystems play a crucial role in shaping Eurasian fire dynamics, yet they remain underexplored. This study addresses existing gaps by introducing an open-access dataset that captures detailed fire incidents alongside corresponding meteorological conditions. We present one of the most extensive datasets available for wildfire analysis in Russia, covering 13 consecutive months of observations. Leveraging machine learning techniques, we conduct exploratory data analysis and develop predictive models to identify key fire behavior patterns across different fire categories and ecosystems. Our results highlight the critical influence of environmental factor patterns on fire occurrence and spread behavior. By improving the understanding of wildfire dynamics in Eurasia, this work contributes to more effective, data-driven approaches for proactive fire management in the face of evolving environmental conditions.

Figures (7)

• Figure 1: Unique Fire Locations.
• Figure 2: Feature Values Distribution.
• Figure 3: Average Profiles of Fire Types.
• Figure 4: Fire Type Clusters in 3D PCA Space.
• Figure 5: Feature Importance in Random Forest Model.