Forest-Fire-Risk Prediction Based on Random Forest and Backpropagation Neural Network of Heihe Area in Heilongjiang Province, China

被引:14
|
作者
Gao, Chao [1 ,2 ]
Lin, Honglei [3 ]
Hu, Haiqing [1 ]
机构
[1] Northeast Forestry Univ, Coll Forestry, Harbin 150040, Peoples R China
[2] Heilongjiang Shengshan Natl Nat Reserve Serv Ctr, Heihe 164300, Peoples R China
[3] Heilongjiang Univ, Sch Elect Engn, Harbin 150080, Peoples R China
来源
FORESTS | 2023年 / 14卷 / 02期
关键词
random forest; backpropagation neural network; forest-fire occurrence prediction; forest-fire driving factor; HUMAN-CAUSED WILDFIRES; LOGISTIC-REGRESSION; PATTERNS; MODEL; DRIVERS; DANGER; SYSTEM;
D O I
10.3390/f14020170
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
Forest fires are important factors that influence and restrict the development of forest ecosystems. In this paper, forest-fire-risk prediction was studied based on random forest (RF) and backpropagation neural network (BPNN) algorithms. The Heihe area of Heilongjiang Province is one of the key forest areas and forest-fire-prone areas in China. Based on daily historical forest-fire data from 1995 to 2015, daily meteorological data, topographic data and basic geographic information data, the main forest-fire driving factors were first analyzed by using RF importance characteristic evaluation and logistic stepwise regression. Then, the prediction models were established by using the two machine learning methods. Furthermore, the goodness of fit of the models was tested using the receiver operating characteristic test method. Finally, the fire-risk grades were divided by applying the kriging method. The results showed that 11 driving factors were significantly correlated with forest-fire occurrence, and days after the last rain, daily average relative humidity, daily maximum temperature, daily average water vapor pressure, daily minimum relative humidity and distance to settlement had a high correlation with the risk of forest-fire occurrence. The prediction accuracy of the two algorithms in regard to fire points was higher than that for nonfire points. The overall prediction accuracy and goodness of fit of the RF and BPNN algorithms were similar. The two methods were both suitable for forest-fire occurrence prediction. The high-fire-risk zones were mainly concentrated in the northwestern and central parts of the Heihe area.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Forest fire smoke recognition based on convolutional neural network
    Xiaofang Sun
    Liping Sun
    Yinglai Huang
    Journal of Forestry Research, 2021, 32 (05) : 1921 - 1927
  • [32] Forest fire smoke recognition based on convolutional neural network
    Sun, Xiaofang
    Sun, Liping
    Huang, Yinglai
    JOURNAL OF FORESTRY RESEARCH, 2021, 32 (05) : 1921 - 1927
  • [33] Forest Fire Recognition Based on Lightweight Convolutional Neural Network
    Li, Zhixiang
    Jiang, Hongbin
    Mei, Qixiang
    Li, Zhao
    JOURNAL OF INTERNET TECHNOLOGY, 2022, 23 (05): : 1147 - 1154
  • [34] Comparative Study of Random Forest and Neural Network for Prediction in Direct Marketing
    Gupta, Arushi
    Gupta, Garima
    APPLICATIONS OF ARTIFICIAL INTELLIGENCE TECHNIQUES IN ENGINEERING, VOL 2, 2019, 697 : 401 - 410
  • [35] RISK ASSESSMENT OF MOUNTAIN TORRENTS DISASTER IN JIANGXI PROVINCE, CHINA BASED ON RANDOM FOREST ALGORITHM
    Fang Xiuqin
    Wu Xiaojun
    Zhou Chao
    Wu Taoying
    Du Xiaotong
    Wang Wei
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 9752 - 9755
  • [36] A Highly Accurate Forest Fire Prediction Model Based on an Improved Dynamic Convolutional Neural Network
    Zheng, Shaoxiong
    Gao, Peng
    Wang, Weixing
    Zou, Xiangjun
    APPLIED SCIENCES-BASEL, 2022, 12 (13):
  • [37] Reservoir Parameter Prediction Based on the Neural Random Forest Model
    Wang, Mingchuan
    Feng, Dongjun
    Li, Donghui
    Wang, Jiwei
    FRONTIERS IN EARTH SCIENCE, 2022, 10
  • [38] Forest Fire Prediction with Imbalanced Data Using a Deep Neural Network Method
    Lai, Can
    Zeng, Shucai
    Guo, Wei
    Liu, Xiaodong
    Li, Yongquan
    Liao, Boyong
    FORESTS, 2022, 13 (07):
  • [39] Relationship between diversity of forest plant species and environmental gradient in eastern mountainous area of Heilongjiang Province, China
    Qing-gui Wang
    Ya-juan Xing
    Xiao-feng Zhou
    Shi-jie Han
    Journal of Forestry Research, 2006, 17 (3) : 252 - 254
  • [40] Application of the Artificial Neural Network and Support Vector Machines in Forest Fire Prediction in the Guangxi Autonomous Region, China
    Li, Yudong
    Feng, Zhongke
    Chen, Shilin
    Zhao, Ziyu
    Wang, Fengge
    DISCRETE DYNAMICS IN NATURE AND SOCIETY, 2020, 2020