Remote sensing monitoring of forest fire hazard based on random forest method
- Pages: 1-15(2024)
Published Online: 12 March 2024
DOI: 10.11834/jrs.20243323
扫 描 看 全 文
浏览全部资源
扫码关注微信
Published Online: 12 March 2024 ,
扫 描 看 全 文
徐雨飞,孙睿,黄薪豫.XXXX.基于随机森林方法的森林火险遥感监测.遥感学报,XX(XX): 1-15
XU Yufei,SUN Rui,HUANG Xinyu. XXXX. Remote sensing monitoring of forest fire hazard based on random forest method. National Remote Sensing Bulletin, XX(XX):1-15
近年来森林火灾发生频繁,给人们正常工作生活以及自然生态系统带来了很大的影响。火险的评估对森林火灾的预防,消防资源的配置有着重要的意义。本文通过收集国内的历史森林火灾事件,综合不同地区的气象因子、植被指数、地形因子等,利用随机森林方法,建立了一个综合的火险评估模型。研究中,火灾事件结合FIRMS数据选取,火灾影响因素则由不同数据产品计算得到,气象因子、地形因子、植被指数分别利用ERA5-land数据、SRTM DEM产品和MODIS反射率产品MCD43A4计算得到。从测试案例结果来看,所建立的火险评估模型准确性比较高,ROC曲线下面积达到了0.84,在火险时序预测以及火险空间分布评估方面都取得较好的效果。虽然火灾发生的区域不同,影响火灾发生的因素也不同,但是火险值均在火灾发生前一周较高,其他时间火险值较低;火险空间分布比较合理,火灾发生区域的火险值从火灾发生前两个月至火灾发生当天逐渐升高。本文建立的火险评估模型涉及指标较全面,可以比较准确评估火险情况,同时可以应用在中国不同地区,部分解决地域限制性问题。
In recent years
the frequent occurrence of forest fires has brought great impact to people's normal work and life as well as the natural ecosystem. The assessment of fire hazard is of great significance to the prevention of forest fire and the allocation of fire resources. This paper collects the historical forest fire events in China from 2002 to 2020
which are distributed in 5 climate regions in China: plateau mountain climate
temperate continental climate
temperate monsoon climate
subtropical monsoon climate
and tropical monsoon climate.
integrated meteorological factors
vegetation index
topographic factors in different regions
and used the random forest method to establish a comprehensive forest fire hazard assessment model. Fire influencing factors were calculated from different data products
fire events were selected using FIRMS images
meteorological factors were calculated using ERA5-land data
topographic factors were calculated using SRTM DEM products
and vegetation indices were calculated using MODIS reflectance product MCD43A4. The fire hazard assessment model can predict the time series of fire hazard and evaluate the spatial distribution of fire hazard. The fire occurrence location of the test data is different from that of the training data. From the test case results
the accuracy of the established fire hazard assessment model is relatively high
and the area under the ROC curve reaches 0.84
which achieves good results in the time series prediction of forest fire hazard and the spatial distribution assessment of forest fire hazard. Also
the predicted fire hazard value is close to the pre-calibrated fire hazard value. The results of time series prediction of fire hazard and evaluation of fire hazard spatial distribution are good
which are close to the actual situation. At the same time
the model established in this paper ranked the importance of the factors affecting the occurrence of fires. The most important factor was the annual diurnal sequence factor
reflecting the seasonal factor
followed by the moisture factor and the growth of vegetation
and the importance of topographic factors was lower. Importance ranking can help to understand the driving effect of different factors on the occurrence of fires
and understand which factors have a greater impact on the occurrence of forest fires. Although the area of forest fire occurrence is different and the factors affecting the fire occurrence are different
the change rule of fire hazard value was similar
the fire hazard value is higher in the week before the fire
and the fire hazard value is lower in other times. The spatial distribution of fire hazard is reasonable
and the fire hazard value in the fire area gradually increases from two months before the fire to the day of the fire. Also
the fire hazard in the same area 1 year before was significantly lower than the fire hazard value on the day of the fire
which can accurately assess the fire hazard situation. The forest fire hazard assessment model established in this paper involves comprehensive indicators
which can accurately assess the fire hazard situation. At the same time
it can be applied to different regions in China to partially solve the problem of regional restrictions.
森林火灾火险遥感随机森林危险监测
Forest firefire hazardRemote sensingrandom foresthazard monitoring
Adhikari B, Xu C, Hodza P and Minckley T. 2021. Developing a geospatial data-driven solution for rapid natural wildfire risk assessment. Applied Geography, 126, 102382 [DOI:10.1016/j.apgeog.2020.102382http://dx.doi.org/10.1016/j.apgeog.2020.102382]
An J Y, Feng Z K, Ma T T and Gao K K. 2022. Classification of forest fire risk in Hechuan District of Chongqing based on GIS grid. Journal of Central South University of Forestry and Technology, 42(9): 91-101
安佳怡, 冯仲科, 马天天, 高可可. 2022. 基于GIS格网的重庆合川区森林火险等级区划. 中南林业科技大学学报, 42(9): 91-101 [DOI:10.14067/j.cnki.1673-923x.2022.09.011http://dx.doi.org/10.14067/j.cnki.1673-923x.2022.09.011]
Arganaraz J P, Landi M A, Bravo S J, Gavier-Pizarro G I, Scavuzzo C M and Bellis L M. 2016. Estimation of Live Fuel Moisture Content from MODIS images for fire danger assessment in southern Gran Chaco. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(12): 5339-5349 [DOI:10.1109/JSTARS.2016.2575366http://dx.doi.org/10.1109/JSTARS.2016.2575366]
Bacon E A, Kopsco H, Gronemeyer P, Mateus-Pinilla N and Smith R L. 2022. Effects of climate on the variation in abundance of three tick species in Illinois. Journal of Medical Entomology, 59(2): 700-709 [DOI:10.1093/jme/tjab189http://dx.doi.org/10.1093/jme/tjab189]
Bergado J R, Persello C, Reinke K and Stein A. 2021. Predicting wildfire burns from big geodata using deep learning. Safety Science, 140, 105276 [DOI:10.1016/j.ssci.2021.105276http://dx.doi.org/10.1016/j.ssci.2021.105276]
Bhowmik R T, Jung Y S, Aguilera J A, Prunicki M and Nadeau K. 2023. A multi-modal wildfire prediction and early-warning system based on a novel machine learning framework. Journal of Environmental Management, 341, 117908 [DOI:10.1016/j.jenvman.2023.117908http://dx.doi.org/10.1016/j.jenvman.2023.117908]
Chen C, Xu T, Sun F and Zhao D. 2023. A fire danger index assessment method for short-term pre-warning of wildfires: a case study of Xiangxi, China. Safety Science, 167106287[DOI:10.1016/j.ssci.2023.106287http://dx.doi.org/10.1016/j.ssci.2023.106287]
Chen Z J, Yang W N, Zhang W L, Liu M X, Dong X J and He X D. 2023. Evaluation of forest flammability based on inversion data of vegetation canopy water content. Bulletin of Surveying and Mapping. (4): 99-105
陈宗杰, 杨武年, 张琬琳, 刘明鑫, 董秀军, 何先定. 2023. 基于植被冠层含水量反演数据的森林易燃程度评价. 测绘通报. (4): 99-105
Çolak E and Sunar F. 2020. The importance of ground-truth and crowdsourcing data for the statistical and spatial analyses of the NASA FIRMS active fires in the Mediterranean Turkish forests. Remote Sensing Applications: Society and Environment, 19, 100327[DOI:10.1016/j.rsase.2020.100327http://dx.doi.org/10.1016/j.rsase.2020.100327]
Cui L, Zhang J Q, Bao Y L, Tong Z J and Liu X P. 2012. Study on fire risk warning in Hulunbuir grassland. Journal of Pratacultural Science, 21(04): 282-292
崔亮, 张继权, 包玉龙, 佟志军, 刘兴朋. 2012. 呼伦贝尔草原火灾风险预警研究. 草业学报, 21(04): 282-292
Dennison P E, Lamb B T, Campbell M J, Kokaly R F, Hively W D, Vermote E, Dabney P, Serbin G, Quemada M, Daughtry C S T, Masek J and Wu Z. 2023. Modeling global indices for estimating non-photosynthetic vegetation cover. Remote Sensing of Environment, 295113715[DOI:10.1016/j.rse.2023.113715http://dx.doi.org/10.1016/j.rse.2023.113715]
Ding H, Hu P, Tang G X and Fu Y X. 2022. Review and analysis of forest fire risk index model in China. Forestry Survey and Design in Inner Mongolia, 45(2): 25-29,44
丁虹, 胡鹏, 唐国祥, 付耀先. 2022. 我国森林火险指数模型综述分析. 内蒙古林业调查设计, 45(2): 25-29,44[DOI:10.13387/j.cnki.nmld.2022.02.017http://dx.doi.org/10.13387/j.cnki.nmld.2022.02.017]
Feng J C. 2023. Analysis and research of wildfire detection model based on machine learning: Harbin Normal University, 62
冯俊辰. 2023. 基于机器学习的野火检测模型的分析与研究: 哈尔滨师范大学, 62
Fu X C. 2023. Production of Potential Forest Fire Risk Map in Xupu County Based on GIS, Southern Agriculture, 17 (6): 74-77
付小春. 2023. 基于GIS的溆浦县森林火灾潜在风险地图制作,南方农业, 17(6): 74-77[DOI:10.19415/j.cnki.1673-890x.2023.06.024http://dx.doi.org/10.19415/j.cnki.1673-890x.2023.06.024]
Gitelson A A, Kaufman Y J, Stark R and Rundquist D. 2002. Novel algorithms for remote estimation of vegetation fraction. Remote sensing of environment, 80(1): 76-87[DOI:10.1016/S0034-4257(01)00289-9http://dx.doi.org/10.1016/S0034-4257(01)00289-9]
Huete A R, Liu H Q, Batchily K and van Leeuwen W. 1997. A comparison of vegetation indices over a global set of TM images for EOS-MODIS. Remote sensing of environment, 59(3): 440-451[DOI:10.1016/S0034-4257(96)00112-5http://dx.doi.org/10.1016/S0034-4257(96)00112-5]
Hunt E R and Rock B N. 1989. Detection of changes in leaf water content using near- and middle-infrared reflectances. Remote Sensing of Environment, 30(1): 43-54[DOI:https://doi.org/10.1016/0034-4257(89)90046-1https://doi.org/10.1016/0034-4257(89)90046-1]
Iban M C and Sekertekin A. 2022. Machine learning based wildfire susceptibility mapping using remotely sensed fire data and GIS: a case study of Adana and Mersin provinces, Turkey. Ecological Informatics, 69, 101647 [DOI:10.1016/j.ecoinf.2022.101647http://dx.doi.org/10.1016/j.ecoinf.2022.101647]
Klemas V and Smart R. 1983. The influence of soil salinity, growth form, and leaf moisture on-the spectral radiance of. Photogramm. Eng. Remote Sens, 49, 77-83.
Li R N, Li J L, Zheng G W, Liu D W, Ma X Y, Ning D K, Shen B, Wu J L, Li W B and Liu M. 2018. Research and software development of forest fire weather grade forecast in Fushun City. Modern Agricultural Science and Technology 3: 162-163,168
李若楠, 李俊乐, 郑国伟, 刘多文, 马晓颖, 宁大可, 沈斌, 吴佳丽, 李文博, 刘明. 2018. 抚顺市森林火险气象等级预报研究与软件开发. 现代农业科技3: 162-163,168[DOI:10.3969/j.issn.1007-5739.2018.03.103http://dx.doi.org/10.3969/j.issn.1007-5739.2018.03.103]
Li S X, Zhang F Q and Lin H F. 2023. Research on Forest Fire Risk Assessment Based on Machine Learning Algorithms Journal of Nanjing Forestry University (Natural Science Edition): 1-9
李史欣, 张福全, 林海峰. 2023. 基于机器学习算法的森林火灾风险评估研究. 南京林业大学学报(自然科学版): 1-9
Liu J L, Tian X R, Zong X Z, Peng Y X and Zhao W T. 2023. Forest fire risk assessment in the Greater Hinggan Mountains. Journal of Terrestrial Ecosystems and Conservation, 3(03): 77-88
刘嘉雷, 田晓瑞, 宗学政, 彭玉娴, 赵文太. 2023. 大兴安岭森林火灾风险评估. 陆地生态系统与保护学报, 3(03): 77-88
Liu Q P, Zhu C, Tian H Z, Cai W M and Qiao R F. 2020. The spatiotemporal differentiation characteristics of construction land in China from 2001 to 2017 Resources and Environment of the Yangtze River Basin, 29 (10): 2113-2123
刘沁萍, 朱闯, 田洪阵, 蔡为民, 乔荣锋. 2020. 2001~2017年中国建设用地时空分异特征. 长江流域资源与环境, 29(10): 2113-2123
Li Y J, Gao X Q, Ma J J and Yang L W.2020. Effect of the Western Pacific subtropical high on forest fires in China. Plateau Meteorology, 39(3): 662-672
李瑜洁, 高晓清, 马京津, 杨丽薇. 2020. 西太平洋副热带高压对中国森林火灾的影响. 高原气象, 39(3): 662-672[DOI:10.7522/j.issn.1000-0534.2020.00015http://dx.doi.org/10.7522/j.issn.1000-0534.2020.00015]
Li Z Q, Zhang G, Tan S Q and Wu X. 2021. Forest fire risk warning based on satellite remote sensing. Journal of Central South University of Forestry and Technology, 41(7): 26-33
李哲全, 张贵, 谭三清, 吴鑫. 2021. 基于卫星遥感的森林火灾风险预警研究. 中南林业科技大学学报, 41(7): 26-33[DOI:10.14067/j.cnki.1673-923x.2021.07.004http://dx.doi.org/10.14067/j.cnki.1673-923x.2021.07.004]
McFEETERS S K. 1996. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International journal of remote sensing, 17(7): 1425-1432[DOI:10.1080/01431169608948714http://dx.doi.org/10.1080/01431169608948714]
National Forestry and Grassland Administration. 2021. Technical code for forest fire risk assessment
国家林业和草原局. 2021. 森林火灾危险性评估技术规程
Qi X H. 2022. Study on forest fire occurrence and risk regionalization in Hubei Province: Huazhong Agricultural University
祁雄辉. 2022. 湖北省林火发生规律及风险区划研究: 华中农业大学
Que H F. 2019. Forest fire early warning research and system implementation based on deep learning: Central South University of Forestry and Technology, 70
阙华斐. 2019. 基于深度学习的森林火灾预警研究及系统实现: 中南林业科技大学, 70
Qu Y H. 2020. Spatio-temporal distribution comparison of forest fire and fire risk factors in Honghe-Wenshan Prefecture and Greater Khinganling Mountains: Beijing Forestry University, 72
曲延浩. 2020. 红河-文山州与大兴安岭地区林火时空分布对比及火险因子研究: 北京林业大学, 72
Ren H, Zhang B and Guo X. 2018. Estimation of litter mass in nongrowing seasons in arid grasslands using MODIS satellite data. European journal of remote sensing, 51(1): 222-230[DOI:10.1080/22797254.2017.1418186http://dx.doi.org/10.1080/22797254.2017.1418186]
Rihan M, Ali Bindajam A, Talukdar S, Shahfahad, Waseem Naikoo M, Mallick J and Rahman A. 2023. Forest fire susceptibility mapping with sensitivity and uncertainty analysis using machine learning and deep learning algorithms. Advances in Space Research, 72(2): 426-443[DOI:https://doi.org/10.1016/j.asr.2023.03.026https://doi.org/10.1016/j.asr.2023.03.026]
Rock B N, Vogelmann J E, Williams D L, Vogelmann A F and Hoshizaki T. 1986. Remote detection of forest damage. Bioscience, 36(7): 439-445[DOI:10.2307/1310339http://dx.doi.org/10.2307/1310339]
Rouse J W, Haas R H, Schell J A and Deering D W (1974). Monitoring vegetation systems in the Great Plains with ERTS. NASA Spec. Publ, 351(1), 309.
Serra-Burriel F, Delicado P, Prata A T and Cucchietti F M. 2021. Estimating heterogeneous wildfire effects using synthetic controls and satellite remote sensing. Remote Sensing of Environment, 265, 112649 [DOI:10.1016/j.rse.2021.112649http://dx.doi.org/10.1016/j.rse.2021.112649]
Tang Z T, Tian Q, Wang Y L, Zhou X L, Zhao A and Du J J. 2022. Relationship between forest fuel moisture content of different forest types and environmental factors in Taizi Mountain, Gansu Province. Journal of Gansu Agricultural University, 57(6): 140-147
唐子桐, 田青, 王艳莉, 周晓雷, 赵安, 杜佳囝. 2022. 甘肃太子山不同林型森林可燃物含水率与环境因子的关系. 甘肃农业大学学报, 57(6): 140-147 [DOI:10.13432/j.cnki.jgsau.2022.06.017http://dx.doi.org/10.13432/j.cnki.jgsau.2022.06.017]
Tianjin Fire Research Institute of Ministry of Public Security, Sichuan Fire Research Institute of Ministry of Public Security, University of Science and Technology of China and China Academy of Building Research. GB/T 31593.3-2015 Fire safety engineering - Part 3: Fire risk assessment guide
公安部天津消防研究所, 公安部四川消防研究所, 中国科学技术大学, 中国建筑科学研究院. GB/T 31593.3-2015 消防安全工程 第3部分:火灾风险评估指南
Van Deventer A P, Ward A D, Gowda P H and Lyon J G. 1997. Using thematic mapper data to identify contrasting soil plains and tillage practices. Photogrammetric engineering and remote sensing, 63, 87-93.
Wang B, He B H, Lin N, Wang W and Li T Y. 2022. Remote sensing extraction of tea garden based on random forest feature selection. Journal of Jilin University (Engineering and Technology Edition), 52(07): 1719-1732
王斌, 何丙辉, 林娜, 王伟, 李天阳. 2022. 基于随机森林特征选择的茶园遥感提取. 吉林大学学报(工学版), 52(07): 1719-1732
Weston C J, Di Stefano J , Hislop S and Volkova L. 2022. Effect of recent fuel reduction treatments on wildfire severity in southeast Australian Eucalyptus Sieberi forests. Forest Ecology and Management, 505119924[DOI:10.1016/j.foreco.2021.119924http://dx.doi.org/10.1016/j.foreco.2021.119924]
Xiao J B, Zhao R N and Xue C H .2022. Research on population spatialization driven by multi-source remote sensing data and Random forest model: a case study of Nanjing Proceedings of the 2022 Academic Annual Conference of the Jiangsu Society of Surveying and Mapping Geographic Information Online Meeting: 7
肖金榜, 赵蕤楠, 薛朝辉. 2022. 多源遥感数据和随机森林模型驱动的人口空间化研究——以南京为例. 江苏省测绘地理信息学会2022年学术年会论文集. 线上会议: 7
Zhai J X, Li Y, Zhang B, Wang A B, Yan C, Ai J Y, Jiang J Z and Yin J Y. 2022. Overview analysis of forest fires and lightning fires in the world's major fire-prone countries. Journal of Subtropical Resources and Environment, 17(4): 72-79
翟杰休, 李勇, 张博, 王爱斌, 闫淳, 艾金毅, 蒋金佐, 殷继艳. 2022. 世界主要林火多发国家的森林火灾与雷击火概况分析. 亚热带资源与环境学报, 17(4): 72-79 [DOI:10.3969/j.issn.1673-7105.2022.04.011http://dx.doi.org/10.3969/j.issn.1673-7105.2022.04.011]
Zheng R W, Zhang Y, Wang Q M and Gui Y P. 2022. Prediction and attribution analysis of the future evolution trend of ET0 in China climate zone. Journal of Yangtze River Scientific Research Institute: 1-10
郑荣伟, 张越, 王庆明, 桂云鹏. 2022. 中国气候分区ET0未来演变趋势预测及归因分析. 长江科学院院报: 1-10
相关文章
相关作者
相关机构