Identification and prediction models of driving factors for forest fires in Daxing’an Mountains of Inner Mongolia, northern China

Zhou Qing; Zhang Heng; Zhang Qiuliang; Zhao Pengwu; Nuo Min; Wang Jiafu; Gao Jian; Zhao Mengyu; Yang Zehua

doi:10.12171/j.1000-1522.20230161

Journal of Beijing Forestry University > 2024 > 46(12): 114-125. > DOI: 10.12171/j.1000-1522.20230161

Zhou Qing, Zhang Heng, Zhang Qiuliang, Zhao Pengwu, Nuo Min, Wang Jiafu, Gao Jian, Zhao Mengyu, Yang Zehua. Identification and prediction models of driving factors for forest fires in Daxing’an Mountains of Inner Mongolia, northern China[J]. Journal of Beijing Forestry University, 2024, 46(12): 114-125. DOI: 10.12171/j.1000-1522.20230161

Citation:

PDF (4071 KB)

Identification and prediction models of driving factors for forest fires in Daxing’an Mountains of Inner Mongolia, northern China

Zhou Qing^{1, 2, 3, 4,},
Zhang Heng^{1, 2, ,},
Zhang Qiuliang^{1, 2},
Zhao Pengwu¹,
Nuo Min⁵,
Wang Jiafu⁶,
Gao Jian⁷,
Zhao Mengyu⁸,
Yang Zehua⁸

1.
College of Forestry, Inner Mongolia Agricultural University, Hohhot 010019, Inner Mongolia, China
2.
Forest Ecosystem National Observation and Research Station of Greater Khingan Mountains, Genhe 022350, Inner Mongolia, China
3.
International Institute for Earth System Science, Nanjing University, Nanjing 210023, Jiangsu, China
4.
Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing 210023, Jiangsu, China
5.
Keyihe Forestry Company, Hulunbuir 021000, Inner Mongolia, China
6.
Inner Mongolia Daxing’an Mountains Forestry Science and Technology Research Institute, Yakeshi 022150, Inner Mongolia, China
7.
Beijing Municipal Forest and Parks Bureau, Beijing 102100, China
8.
Hohhot Meteorological Service in Inner Mongolia Autonomous Region, Hohhot 010020, Inner Mongolia, China

More Information

Received Date: June 26, 2023
Revised Date: October 23, 2023
Available Online: November 25, 2024

Graphical Abstract

Abstract

Abstract

Objective
This paper aims to select and validate suitable forest fire prediction models for the study area, identify key driving factors of fire occurrence, and map fire risk zoning, then providing scientific basis and decision support for forest fire prevention and management.
Method
Using historical fire data from 1981 to 2020 and integrating multi-source data (meteorological conditions, topography, vegetation, human activities, and socio-economic factors), the applicability of four machine learning methods in predicting forest fires in the Daxing’an Mountains of Inner Mongolia of northern China was compared. Based on the significant factors influencing fire occurrence, maps of fire occurrence probability and fire risk zoning were generated.
Result
(1) The boosted regression tree model (BRT) showed an area under the curve (AUC) value of 0.967, and the random forest model (RF) achieved an AUC of 0.947, both demonstrating excellent predictive performance. The predictive accuracy of the Logistic regression model (LR) and the Gompit regression model (GR) was slightly lower than former two models, but still met the basic predictive requirements for the study area, with AUC values of 0.852 and 0.851, respectively. (2) Meteorological factors, such as diurnal temperature range and daily minimum relative humidity, were the dominant factors influencing forest fires in the Daxing’an Mountains of Inner Mongolia. Elevation also ranked high in the relative importance of driving factors. Human activities and socio-economic factors, such as distance to roads, distance to fire lookout towers, and per capita GDP, also had some influence on fire occurrence. (3) Large areas of medium to high fire risk were present in the eastern and southeastern parts of the Daxing’an Mountains of Inner Mongolia, while the northern China-Russia border and the southwestern China-Mongolia border also exhibited elevated fire risk. Factors such as average temperature and average surface temperature during fire prevention period in autumn of previous year influenced forest fire occurrences in the following year.
Conclusion
Among the four models compared, the BRT was identified as the most suitable one for predicting forest fire occurrence in the Daxing’an Mountains of Inner Mongolia. Meteorological factors and elevation significantly influence fire occurrence, while human activities and socio-economic factors also have a certain impact on the occurrence of fires. The high and medium fire risk areas are primarily concentrated in the eastern and southeastern parts of the study area, with some fire risks presenting in the northern and southwestern regions.
- Daxing’an Mountains,
- model comparison,
- probability of forest fires,
- driving factors of forest fires,
- fire risk zoning

FullText(HTML)

References (33)

References

[1]	Thom D, Seidl R. Natural disturbance impacts on ecosystem services and biodiversity in temperate and boreal forests[J]. Biological Reviews, 2016, 91: 760−781. doi: 10.1111/brv.12193
[2]	Pang Y Q, Li Y D, Feng Z K, et al. Forest fire occurrence prediction in China based on machine learning methods[J/OL]. Remote Sensing, 2022, 14: 5546[2024−01−21]. https://doi.org/10.3390/rs14215546.
[3]	Mundo I A, Wiegand T, Kanagaraj R, et al. Environmental drivers and spatial dependency in wildfire ignition patterns of northwestern Patagonia[J]. Journal of Environmental Management, 2013, 123: 77−87.
[4]	Phelps N, Woolford D G. Comparing calibrated statistical and machine learning methods for wildland fire occurrence prediction: a case study of human-caused fires in Lac La Biche, Alberta, Canada[J]. International Journal of Wildland Fire, 2021, 30: 850−870. doi: 10.1071/WF20139
[5]	Nguyen N T, Dang B T N, Pham X C, et al. Spatial pattern assessment of tropical forest fire danger at Thuan Chau area (Vietnam) using GIS-based advanced machine learning algorithms: a comparative study[J]. Ecological Informatics, 2018, 46: 74−85. doi: 10.1016/j.ecoinf.2018.05.009
[6]	曾爱聪, 蔡奇均, 苏漳文, 等. 基于MODIS卫星火点的浙江省林火季节变化及驱动因子[J]. 应用生态学报, 2020, 31(2): 399−406. Zeng A C, Cai Q J, Su Z W, et al. Seasonal variation and driving factors of forest fire in Zhejiang Province, China, based on MODIS satellite hot spots, Chinese[J]. Journal of Applied Ecology, 2020, 31(2): 399−406.
[7]	Guris S, Akya E C, Un T. Estimating of probability of home-ownership in rural and urban areas: Logit, Probit and Gompit model[J]. European Journal of Social Sciences, 2011, 21: 405−411.
[8]	苏漳文, 曾爱聪, 蔡奇均, 等. 基于Gompit回归模型的大兴安岭林火预测模型及驱动因子研究[J]. 林业工程学报, 2019, 4(4): 135−142. Su Z W, Zeng A C, Cai Q J, et al. Study on prediction model and driving factors of forest fire in Da Hinggan Mountains using Gompit regression method[J]. Journal of Forestry Engineering, 2019, 4(4): 135−142.
[9]	高超, 林红蕾, 胡海清, 等. 我国林火发生预测模型研究进展[J]. 应用生态学报, 2020, 31(9): 3227−3240. Gao C, Lin H L, Hu H Q, et al. A review of models of forest fire occurrence prediction in China[J]. Chinese Journal of Applied Ecology, 2020, 31(9): 3227−3240.
[10]	Oliveira S, Oehler F, San-Miguel-Ayanz J, et al. Modeling spatial patterns of fire occurrence in Mediterranean Europe using multiple regression and random forest[J]. Forest Ecology and Management, 2012, 275: 117−129. doi: 10.1016/j.foreco.2012.03.003
[11]	Eskandari S, Amiri M, Sadhasivam N, et al. Comparison of new individual and hybrid machine learning algorithms for modeling and mapping fire hazard: a supplementary analysis of fire hazard in different counties of Golestan Province in Iran[J]. Natural Hazards, 2020, 104: 305−327. doi: 10.1007/s11069-020-04169-4
[12]	Chang C, Chang Y, Xiong Z P, et al. Predicting grassland fire-occurrence probability in Inner Mongolia Autonomous Region, China[J/OL]. Remote Sensing, 2023, 15(12): 2999[2024−01−23]. https://doi.org/10.3390/rs15122999.
[13]	Ruffault J, Mouillot F. Contribution of human and biophysical factors to the spatial distribution of forest fire ignitions and large wildfires in a French Mediterranean region[J]. International Journal of Wildland Fire, 2017, 26: 498−508. doi: 10.1071/WF16181
[14]	Wu Z W, He H S, Keane R E, et al. Current and future patterns of forest fire occurrence in China[J]. International Journal of Wildland Fire, 2020, 29: 104−119. doi: 10.1071/WF19039
[15]	Massada A B, Syphard A D, Stewart S I, et al. Wildfire ignition-distribution modelling: a comparative study in the Huron-Manistee National Forest, Michigan, USA[J]. International Journal of Wildland Fire, 2013, 22: 174−183. doi: 10.1071/WF11178
[16]	刘璞. 内蒙古大兴安岭典型森林积雪化学特征研究[D]. 哈尔滨: 东北林业大学, 2022. Liu P. Study up on chemical characteristics of snow cover in typical forests of Daxing’an Mountains, Inner Mongolia[D]. Harbin: Northeast Forestry University, 2022.
[17]	赵鹏武, 葛晨赫, 王嘉夫, 等. 内蒙古大兴安岭森林火险等级评价与区划研究[J]. 西南林业大学学报(自然科学), 2021, 41(2): 151−158. Zhao P W, Ge C H, Wang J F, et al. Study on rating and classification of forest fire risk in Daxing’an Mountains, Inner Mongolia[J]. Journal of Southwest Forestry University (Natural Sciences), 2021, 41(2): 151−158.
[18]	徐化成. 中国大兴安岭森林[M]. 北京: 科学出版社, 1998: 40−41. Xu H C. Da Hinggan Ling Mountains forests in China[M]. Beijing: Science Press, 1998: 40−41.
[19]	Chang Y, Zhu Z L, Bu R C, et al. Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China[J]. Landscape Ecology, 2013, 28: 1989−2004. doi: 10.1007/s10980-013-9935-4
[20]	Littell J S, McKenzie D, Peterson D L, et al. Climate and wildfire area burned in western U. S. ecoprovinces, 1916−2003[J]. Ecological Applications, 2009, 19: 1003−1021. doi: 10.1890/07-1183.1
[21]	Zhang H J, Qi P C, Guo G M. Improvement of fire danger modelling with geographically weighted logistic model[J]. International Journal of Wildland Fire, 2014, 23: 1130−1146. doi: 10.1071/WF13195
[22]	内蒙古自治区统计局. 改革开放30年的内蒙古[M]. 北京: 中国统计出版社, 2008. Inner Mongolia Autonomous Region Bureau of Statistics. Inner Mongolia in the 30 years of reform and opening up[M]. Beijing: China Statistics Press, 2008.
[23]	白海峰, 刘晓东, 牛树奎, 等. 基于贝叶斯模型平均法的森林火灾预测模型构建研究以云南省大理州为例[J]. 北京林业大学学报, 2021, 43(5): 44−52. Bai H F, Liu X D, Niu S K, et al. Construction of forest fire prediction model based on Bayesian model averaging method: taking Dali Prefecture, Yunnan Province of southwestern China as an example[J]. Journal of Beijing Forestry University, 2021, 43(5): 44−52.
[24]	Frank E H. Regression modeling strategies-with applications to linear models, logistic regression, and survival analysis[M]. New York: Springer, 2001.
[25]	Guo F T, Selvalakshmi S, Lin F F, et al. Geospatial information on geographical and human factors improved anthropogenic fire occurrence modeling in the Chinese boreal forest[J]. Canadian Journal of Forest Research, 2016, 46: 582−594. doi: 10.1139/cjfr-2015-0373
[26]	陈锋, 林向东, 牛树奎, 等. 气候变化对云南省森林火灾的影响[J]. 北京林业大学学报, 2012, 34(6): 7−15. Chen F, Lin X D, Niu S K, et al. Influence of climate change on forest fire in Yunnan Province, southwestern China[J]. Journal of Beijing Forestry University, 2012, 34(6): 7−15.
[27]	Wu Z W, He H S, Yang J, et al. Relative effects of climatic and local factors on fire occurrence in boreal forest landscapes of northeastern China[J]. Science of the Total Environment, 2014, 493: 472−480. doi: 10.1016/j.scitotenv.2014.06.011
[28]	舒展. 气候变化对大兴安岭塔河林业局森林火灾的影响研究[D]. 哈尔滨: 东北林业大学, 2011. Shu Z. Impacts research of climate change on forest fires in Tahe Forestry Bureau in Great Xing’an Mountain Region[D]. Harbin: Northeast Forestry University, 2011.
[29]	Guo F T, Su Z W, Wang G Y, et al. Understanding fire drivers and relative impacts in different Chinese forest ecosystems[J]. Science of the Total Environment, 2017, 605: 411−425.
[30]	Guo F T, Zhang L J, Jin S, et al. Modeling anthropogenic fire occurrence in the boreal forest of China using logistic regression and random forests[J/OL]. Forests, 2016, 7: 250[2023−01−23]. https://www.mdpi.com/1999-4907/7/11/250.
[31]	Su Z W, Hu H Q, Tigabu M, et al. Geographically weighted negative binomial regression model predicts wildfire occurrence in the Great Xing’an Mountains better than negative binomial model[J/OL]. Forests, 2019, 10: 377[2023−01−23]. http://dx.doi.org/10.3390/f10050377.
[32]	周粉粉, 郭蒙, 钟超, 等. 呼伦贝尔草原火时空格局及特征分析[J]. 地理科学, 2022, 42(10): 1838−1847. Zhou F F, Guo M, Zhong C, et al. Spatial-temporal patterns and characteristics of grassland fire in the Hulunbuir Grassland[J]. Scientia Geographica Sinica, 2022, 42(10): 1838−1847.
[33]	杨少斌, 曹萌, 祝鑫海, 等. 2001—2019年内蒙古大兴安岭北部原始林区森林火灾发生规律研究[J]. 灾害学, 2022, 37(3): 122−128. Yang S B, Cao M, Zhu X H, et al. Research on occurrence law of forest fire in the northern primitive forest area of Greater Khingan Range, Inner Mongolia from 2001 to 2019[J]. Journal of Catastrophology, 2022, 37(3): 122−128.

Cited By

Cited by

Periodical cited type(3)

1.	王丹，盖立新，田恒玖，蒋健，范雅倩，张洪亮，吴记贵. 北京松山国家级自然保护区野生兰科植物多样性及其生存状况研究. 自然保护地. 2022(01): 93-101 .
2.	沐先运，童玲，雷丰玮，沈雪梨，马頔. 北京市被子植物新记录科与兰科新记录种. 首都师范大学学报(自然科学版). 2022(05): 31-34 .
3.	李国权. 河北省被子植物新资料. 河北科技师范学院学报. 2018(03): 22-23+39 .

Other cited types(0)

Get Citation

PDF

XML

Article views (214) PDF downloads (51) Cited by(3)

Turn off MathJax

Article Contents

Abstract

References

Identification and prediction models of driving factors for forest fires in Daxing’an Mountains of Inner Mongolia, northern China

Abstract

References

Cited by

Periodical cited type(3)

Other cited types(0)

Catalog

Export File

Citation

Format

Content