Developing a New Hourly Forest Fire Risk Index Based on Catboost in South Korea

Yoojin Kang,Eunna Jang,Sungyong Kim,Chungeun Kwon,Jungho Im

doi:10.3390/app10228213

Yoojin Kang, Eunna Jang + Show 3 more

Open Access

https://doi.org/10.3390/app10228213

Copy DOI

Abstract

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.

Highlights

Forest fires have a profound impact on ecological processes on the Earth, such as deforestation, habitat destruction, and loss of soil nutrients, as well as the environmental, economic, and social sectors [1,2,3]
About 50% and 70% of the forest fires occurred in the early morning and at night (22:00–08:00) had low risk for hourly forest fire risk index (HFRI) and Daily Weather Index (DWI), respectively. This is because both HFRI and DWI are affected by the temporal distribution of forest fires since they are empirical models: samples were not evenly distributed on the temporal domain
Existing forest fire risk indices as an operational use are mostly based on weather and fuel data, and often require complex processes through various conditions based on statistics

Summary

Introduction

Forest fires have a profound impact on ecological processes on the Earth, such as deforestation, habitat destruction, and loss of soil nutrients, as well as the environmental, economic, and social sectors [1,2,3]. It takes a long time and significant effort to restore areas with forest fires to their previous state. It is necessary to make efforts to reduce the damage caused by forest fires One such effort is to identify areas with high forest fire risk in advance to establish proper mitigation and response plans from a management perspective. Many studies have tried to predict where a forest fire is likely to occur [1,4,5,6].

Objectives

Methods

Results

Conclusion