Mapping Forest Fire Risk Zones Using Machine Learning Algorithms in Hunan Province, China

Abstract

Forest fire is a primary disaster that destroys forest resources and the ecological environment, and has a serious negative impact on the safety of human life and property. Predicting the probability of forest fires and drawing forest fire risk maps can provide a reference basis for forest fire control management in Hunan Province. This study selected 19 forest fire impact factors based on satellite monitoring hotspot data, meteorological data, topographic data, vegetation data, and social and human data from 2010–2018. It used random forest, support vector machine, and gradient boosting decision tree models to predict the probability of forest fires in Hunan Province and selected the RF algorithm to create a forest fire risk map of Hunan Province to quantify the potential forest fire risk. The results show that the RF algorithm performs best compared to the SVM and GBDT algorithms with 91.68% accuracy, 91.96% precision, 92.78% recall, 92.37% F1, and 97.2% AUC. The most important drivers of forest fires in Hunan Province are meteorology and vegetation. There are obvious differences in the spatial distribution of seasonal forest fire risks in Hunan Province, and winter and spring are the seasons with high forest fire risks. The medium- and high-risk areas are mostly concentrated in the south of Hunan.

An Integrated Grassland Fire-Danger-Assessment System for a Mountainous National Park Using Geospatial Modelling Techniques

“…For mapping and modelling wildfires, RF is one of the most effective non-parametric ensemble learning techniques proposed by Breiman in 2001 as an inheritance and improvement of the traditional DT [137]. The efficiency of RF is influenced by two parameters: the number of trees in the forest (ntree) and the number of random variables per split node (mtry) [138,139]. Sharma, et al [26] thoroughly explained the RF algorithm for the RF classification and regression algorithms.…”

“…The SVM can solve quite well high dimensional and non-linear pattern recognition problems [42] by using its kernel functions. Kernel functions can map the original input space to a new feature space, making samples that are otherwise linearly indistinguishable potentially distinguishable in the kernel space [139].…”

“…In comparison with SVM, it can quickly and efficiently implement "transduction" inference using a simple and robust algorithm [161]). However, SVM requires consideration to test different kernel functions and model parameters to find the best model and to create an impractical approach for dealing with large samples of datasets [139].…”

Development of a Data-Based Machine Learning Model for Classifying and Predicting Property Damage Caused by Fire

“…The depth can be considered a representative hyper-parameter; however, overfitting is highly likely to occur in the training dataset with increased depth [22]. Examples that use this technique can be found in [23][24][25][26].…”

Development of an Index for Forest Fire Risk Assessment Considering Hazard Factors and the Hazard-Formative Environment

“…In recent years, machine learning methods have gained popularity in fire risk assessment. Support vector machines (SVMs) are commonly used and have demonstrated good performances in fire risk assessment model comparison experiments [33][34][35]. Ensemble algorithms, like random forest (RF), gradient boosting decision tree (GBDT), and XGBoost, demonstrate better accuracy compared to most individual algorithms and have exhibited strong classification and regression prediction capabilities in various forest fire risk assessment studies [36][37][38][39].…”