Forest fires can cause enormous damage, such as deforestation and environmental pollution, even with a single occurrence. It takes a lot of effort and long time to restore areas damaged by wildfires. Therefore, it is crucial to know the forest fire risk of a region to appropriately prepare and respond to such disastrous events. The purpose of this study is to develop an hourly forest fire risk index (HFRI) with 1 km spatial resolution using accessibility, fuel, time, and weather factors based on Catboost machine learning over South Korea. HFRI was calculated through an ensemble model that combined an integrated model using all factors and a meteorological model using weather factors only. To confirm the generalized performance of the proposed model, all forest fires that occurred from 2014 to 2019 were validated using the receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) values through one-year-out cross-validation. The AUC value of HFRI ensemble model was 0.8434, higher than the meteorological model. HFRI was compared with the modified version of Fine Fuel Moisture Code (FFMC) used in the Canadian Forest Fire Danger Rating Systems and Daily Weather Index (DWI), South Korea’s current forest fire risk index. When compared to DWI and the revised FFMC, HFRI enabled a more spatially detailed and seasonally stable forest fire risk simulation. In addition, the feature contribution to the forest fire risk prediction was analyzed through the Shapley Additive exPlanations (SHAP) value of Catboost. The contributing variables were in the order of relative humidity, elevation, road density, and population density. It was confirmed that the accessibility factors played very important roles in forest fire risk modeling where most forest fires were caused by anthropogenic factors. The interaction between the variables was also examined.

A prediction model was developed for the wildfire fuel load of Korean red pine (Pinus densiflora) stands with susceptibility to forest fire based on the forest-growth model. Furthermore, a time-series analysis was performed on the variation in forest-fire fuel load according to forest management. National Forest Inventory stand data of 1434 plots for P. densiflora stands were used, and the final forest-fire fuel load prediction model was developed using the Weibull function and mortality model. The fit index of the diameter distribution model ranged from 0.58 (0th percentile) to 0.96 (50th percentile), and that of the mortality model was 0.68. The prediction of the stand growth variation after 20 years based on the growth data of managed and unmanaged stands indicated a mean stand density of 1518 trees per ha for unmanaged stands, and 885 trees per ha for managed stands. Regarding the variation in the available canopy fuel load distribution, the predicted annual increase was approximately 0.7 ton/ha for unmanaged stands and approximately 0.5 ton/ha for managed stands. These findings will contribute to setting fuel management criteria to prevent forest fire spread while providing the quantitative data of the characteristics of stand growth variation and the predicted wildfire fuel load.