PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 21, 2026Journal of the Korean Society of Surveying Geodesy Photogrammetry and Cartography0 citations

Seasonal Forest Fire Susceptibility Mapping in South Korea Using Explainable Machine Learning

View Full Paper
WKWulan Salle KarurungKyungpook National UniversityKLKi Hoon LeeWLWon Hee LeeKookmin University

Key Points

  • The research aims to map the risk of seasonal forest fires using various climatic and environmental factors in South Korea.
  • Utilized multivariable data from 2019 to 2023, including topography, climate, and human activity.
  • Compared three machine learning models: RF, XGBoost, and LGBM for prediction accuracy.
  • Employed SHAP and PDP for model interpretation and feature importance evaluation.
  • XGBoost model demonstrated the highest prediction accuracy compared to RF and LGBM.
  • Key features impacting fire risk varied seasonally, with temperature being crucial in spring.
  • NDR and population density were consistently among the top five important features across all seasons.

Abstract

Seasonal forest fire dynamics in monsoon-influenced temperate regions, such as South Korea, reflect complex interactions among climate variability, vegetation stress, topography, and human activities. Despite increasing national attention to forest fire hazards, seasonal-level susceptibility mapping remains limited, and the interpretability of models is rarely addressed. This study aimed to map the risk of fire using multivariable data, including topographic, climatic, biophysical, and anthropogenic factors, from 2019 to 2023 and validate the results using 2024 data, utilizing near-real-time fire data from the FIRMS (Fire Information for Resource Management System). Three ML (Machine Learning) models, RF (Random Forest), XGBoost (eXtreme Gradient Boosting), and LGBM (Light Gradient Boosting Model), were compared to evaluate prediction accuracy and interpretability using SHAP (Shapley Additive exPlanations) and PDP (Partial Dependence Plots). Based on the final accuracy results, the XGBoost model exhibited the highest accuracy compared to the RF and LGBM models. The top feature importance based on SHAP results revealed that spring was characterized by land surface temperature, summer and fall by the NDR (Normalized Burn Ratio), and winter by population density. Notably, NBR and population density consistently ranked among the top five most influential features across all seasons. The relative importance of predictors varied by season, with thermal conditions being the most influential in spring, vegetation indices in summer and autumn, and human-related factors in winter. Overall, this study demonstrated that utilizing machine learning and interpretable models enhances our understanding of how the dynamics of key driver factors vary in response to forest fires across different seasons, which can inform specific forest fire management and mitigation strategies tailored to each season.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Karurung et al. (2026) studied this question.

synapsesocial.com/papers/69be38596e48c4981c678b02https://doi.org/10.7848/ksgpc.2026.44.1.29
Ask AI
Helpful
Bookmark
Share
View Full Paper