应用生态学报 ›› 2020, Vol. 31 ›› Issue (9): 3227-3240.doi: 10.13287/j.1001-9332.202009.014
• 综合评述 • 上一篇
高超1, 林红蕾2, 胡海清1, 宋红1*
收稿日期:
2020-04-16
接受日期:
2020-07-01
出版日期:
2020-09-15
发布日期:
2021-03-15
通讯作者:
* E-mail: 851100942@qq.com
作者简介:
高 超, 男, 1985年生, 博士研究生。主要从事林火生态与管理和林火预测预报研究。E-mail: gaochaozfb@163.com
基金资助:
GAO Chao1, LIN Hong-lei2, HU Hai-qing1, SONG Hong1*
Received:
2020-04-16
Accepted:
2020-07-01
Online:
2020-09-15
Published:
2021-03-15
Contact:
* E-mail: 851100942@qq.com
Supported by:
摘要: 通过文献回顾,总结了国内林火发生预测模型的研究现状,并从林火发生驱动因子、林火发生概率预测模型、林火发生频次预测模型和模型检验方法等方面进行归纳分析。得出以下结论: 1)气象、地形、植被、可燃物、人类活动等因素是影响林火发生及模型预测精度的主要驱动因子;2)林火发生概率模型中,地理加权逻辑斯蒂回归模型考虑了变量之间的空间相关性,Gompit回归模型适宜非对称结构的林火数据,随机森林模型不需要多重共线性检验,在避免过度拟合的同时提高了预测精度,是林火发生概率预测模型的优选方法之一;3)林火发生频次模型中,负二项回归模型更适合对过度离散数据进行模拟,零膨胀模型和栅栏模型可以处理林火数据中包含大量零值的问题;4)ROC检验、AIC检验、似然比检验和Wald检验方法是林火概率和频次模型的常用检验方法。林火发生预测模型研究仍是我国当前林火管理工作的重点,预测模型的选择需要依据不同地区林火数据特点。此外,构建林火预测模型时需要考虑更多的影响因素,以提高模型预测精度;未来,需要进一步探索其他数学模型在林火发生预测中的应用,不断提高林火发生预测模型的准确度。
高超, 林红蕾, 胡海清, 宋红. 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 Chao, LIN Hong-lei, HU Hai-qing, SONG Hong. A review of models of forest fire occurrence prediction in China[J]. Chinese Journal of Applied Ecology, 2020, 31(9): 3227-3240.
[1] 舒立福, 张小罗, 戴兴安, 等. 林火研究综述(Ⅱ)——林火预测预报. 世界林业研究, 2003, 16(4): 34-37 [Shu L-F, Zhang X-L, Dai X-A, et al. Forest fire research (Ⅱ): Fire forecast. World Forestry Research, 2003, 16(4): 34-37] [2] 张洁, 赵浩彦, 张民侠, 等. 广义线性模型在林火发生预报中的应用. 林业工程学报, 2017, 2(1): 135-142 [Zhang J, Zhao H-Y, Zhang M-X, et al. Research on generalized linear models applied to forest fire forecast. Journal of Forestry Engineering, 2017, 2(1): 135-142] [3] Crosby JS. Probability of Fire Occurrence Can Be Predicted. Northern Ozark Forest Research Centre. Washtington DC: USDA Forest Service, Central States Forest Experiment Station, Technical Paper, 1954 [4] Wotton BM, Martell DL. A lightning fire occurrence model for Ontario. Canadian Journal of Forest Research, 2005, 35: 1389-1401 [5] Boubeta M, Lombardía MJ, Marey-Perez MF, et al. Prediction of forest fires occurrences with area-level Poisson mixed models. Journal of Environmental Mana-gement, 2015, 154: 151-158 [6] Cunningham AA, Martell DL. A stochastic model for the occurrence of man-caused forest fires. Canadian Journal of Forestry Research, 1973, 3: 282-287 [7] Magnussen S, Taylor SW. Prediction of daily lightning- and human-caused fires in British Columbia. International Journal of Wildland Fire, 2012, 3: 1-15 [8] Dayananda PWA. Stochastic models for forest fires. Ecological Modeling, 1977, 3: 309-313 [9] Garcia CV, Woodard PM, Titus SJ, et al. A Logit Model for predicting the daily occurrence of human caused forest fires. International Journal of Wildland Fire, 1995, 5: 101-111 [10] Vasconcelos M, Sllva S, Tome M, et al. Spatial prediction of fire ignition probabilities: Comparing Logistic regression and neural networks. Photogrammetric Engineering & Remote Sensing, 2001, 67: 73-81 [11] Vilar L, Woolford DG, Martell DL, et al. A model for predicting human-caused wildfire occurrence in the region of Madrid, Spain. International Journal of Wildland Fire, 2010, 19: 325-337 [12] Monjarás-Vega NA, Briones-Herrera CI, Vega-Nieva D J, et al. Predicting forest fire kernel density at multiple scales with geographically weighted regression in Mexico. Science of the Total Environment, 2020, 718: 137313, https://doi.org/10.1016/j.scitotenv.2020.137313 [13] Rodrigues M, Riva JDL, Fotheringham S. Modeling the spatial variation of the explanatory factors of human-caused wildfires in Spain using geographically weighted logistic regression. Applied Geography, 2014, 48: 52-63 [14] Zheng Z, Huang W, Li SN, et al. Forest fire spread simulating model using cellular automaton with extreme learning machine. Ecological Modelling, 2017, 348: 33-43 [15] Buia DT, Hoang ND, Samuid P. Spatial pattern analysis and prediction of forest fire using new machine learning approach of multivariate adaptive regression splines and differential flower pollination optimization: A case study at Lao Cai province (Viet Nam). Journal of Environmental Management, 2019, 237: 476-487 [16] Sevinca V, Kucukb O, Goltasc M. A Bayesian network model for prediction and analysis of possible forest fire causes. Forest Ecology and Management, 2020, 457: 117723 [17] Sandra O, Friderike O, Jesús SMA, et al. Modeling spatial patterns of fire occurrence in Mediterranean Europe using multiple regression and random forest. Forest Ecology and Management, 2012, 275: 117-129 [18] Yago M, María ZA, Marcos RM. Modelling temporal variation of fire-occurrence towards the dynamic prediction of human wildfire ignition danger in northeast Spain. Geomatics, Natural Hazards and Risk, 2019, 10: 385-411 [19] Sakr GE, Elhajj IH, Mitri G. Efficient forest fire occurrence prediction for developing countries using two weather parameters. Engineering Applications of Artificial Intelligence, 2011, 24: 888-894 [20] Elia M, Giannico V, Lafortezza R, et al. Modeling fire ignition patterns in Mediterranean urban interface. Stochastic Environmental Research and Risk Assessment, 2019, 33: 169-181 [21] Camp PE, Krawchuk MA. Spatially varying constraints of human-caused fire occurrence in British Columbia, Canada. International Journal of Wildland Fire, 2017, 26: 219-229 [22] 李顺, 吴志伟, 梁宇, 等. 北方森林林火发生驱动因子及其变化趋势研究进展. 世界林业研究, 2017, 30(2): 41-45 [Li S, Wu Z-W, Liang Y, et al. A review of fire controlling factors and their dynamics in boreal forests. World Forestry Research, 2017, 30(2): 41-45] [23] 魏书精, 罗斯生, 罗碧珍, 等. 气候变化背景下森林火灾发生规律研究. 林业与环境科学, 2020, 36(2):133-143 [Wei S-J, Luo S-S, Luo B-Z, et al. Occurrence regularity of forest fire under the background of climate change. Forestry and Environmental Science, 2020, 36(2): 133-143] [24] 金森, 王晓红, 于宏洲. 林火行为预测和森林火险预报中气象场的插值方法. 中南林业科技大学学报, 2012, 32(6): 1-7 [Jin S, Wang X-H, Yu H-Z. A review on weather data interpolation methods used in forest fire danger forecast and behavior modelling. Journal of Central South University of Forestry & Technology, 2012, 32(6): 1-7] [25] Hu TY, Zhou GS. Drivers of lightning- and human-caused fire regimes in the Great Xing’an Mountains. Forest Ecology and Management, 2014, 329: 49-58 [26] Guo FT, Su ZW, Wang GY, et al. Understanding fire drivers and relative impacts in different Chinese forest ecosystems. Science of the Total Environment, 2017, 605-606: 411-425 [27] Opitz T, Bonneu F, Gabriel E. Point-process based Bayesian modeling of space-time structures of forest fire occurrences in Mediterranean France. Spatial Statistics, 2020, doi.org/10.1016/j.spasta.2020.100429 [28] 邓欧, 李亦秋, 冯仲科, 等. 基于空间Logistic的黑龙江省林火风险模型和火险区划. 农业工程学报, 2012, 28(8): 200-205 [Deng O, Li Y-Q, Feng Z-K, et al. Model and zoning of forest fire risk in Heilongjiang Province based on spatial Logistic. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(8): 200-205] [29] 郭福涛, 苏漳文, 王光玉, 等. 我国北方针叶林人为火发生的预测模型. 应用生态学报, 2015, 26(7): 2099-2106 [Guo F-T, Su Z-W, Wang G-Y, et al. Prediction model of human-caused fire occurrence in the boreal forest of northern China. Chinese Journal of Applied Ecology, 2015, 26(7): 2099-2106] [30] 陈岱. 基于Logistic 回归模型的大兴安岭林火预测研究. 林业资源管理, 2019(1): 116-122 [Chen D. Prediction of forest fire occurrence in Daxing’an mountians based on Logistic regression model. Forest Resources Management, 2019(1): 116-122] [31] 苏漳文, 刘爱琴, 梁慧玲, 等. 基于气象因子的福建省森林火险预测模型. 森林与环境学报, 2015, 35(4): 370-376 [Su Z-W, Liu A-Q, Liang H-L, et al. Model to predict forest fire occurrence in Fujian Province based on meteorological factors. Journal of Forest and Environment, 2015, 35(4): 370-376] [32] 苏漳文, 刘爱琴, 郭福涛, 等. 福建林火发生的驱动因子及空间格局分析. 自然灾害学报, 2016, 25(2): 110-119 [Su Z-W, Liu A-Q, Guo F-T, et al. Driving factors and spatial distribution pattern of forest fire in Fujian Province. Journal of Natural Disasters, 2016, 25(2): 110-119] [33] 田超, 苏漳文, 杨夏捷, 等. 福建西部地区林火发生格局及驱动因子分析. 森林与环境学报, 2017, 37(1): 88-94 [Tian C, Su Z-W, Yang X-J, et al. Investigations on spatial distribution and driving factors of forest fire in western Fujian. Journal of Forest and Environment, 2017, 37(1): 88-94] [34] 蔡奇均, 曾爱聪, 苏漳文, 等. 基于Logistic回归模型的浙江省林火发生驱动因子分析. 西北农林科技大学学报: 自然科学版, 2020, 48(2): 102-109 [Cai Q-J, Zeng A-C, Su Z-W, et al. Driving factors of forest fire in Zhejiang Province based on Logistic regression model. Journal of Northwest A&F University: Natural Sciences, 2020, 48(2): 102-109] [35] 马文苑, 冯仲科, 成竺欣, 等. 山西省林火驱动因子及分布格局研究. 中南林业科技大学学报, 2020, 40(9): 1-13 [Ma W-Y, Feng Z-K, Cheng Z-X, et al. Study on driving factors and distribution pattern of forest fires in Shanxi Province. Journal of Central South University of Forestry & Technology, 2020, 40(9): 1-13] [36] 梁慧玲, 王文辉, 郭福涛, 等. 比较逻辑斯蒂与地理加权逻辑斯蒂回归模型在福建林火发生的适用性. 生态学报, 2017, 37(12): 4128-4141[Liang H-L, Wang W-H, Guo F-T, et al. Comparing the application of logistic and geographically weighted logistic regression models for Fujian forest fire forecasting. Acta Ecologica Sinica, 2017, 37(12): 4128-4141] [37] 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. 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. Journal of Forestry Engineering, 2019, 4(4):135-142] [38] 梁慧玲, 郭福涛, 苏漳文, 等. 基于随机森林算法的福建省林火发生主要气象因子分析. 灾害科学, 2015, 24(4): 191-200 [Liang H-L, Guo F-T, Su Z-W, et al. Analysis of meteorological factors on forest fire occurrence of Fujian based on random forest algorithm. Fire Safety Science, 2015, 24(4): 191-200] [39] 潘登, 郁培义, 吴强. 基于气象因子的随机森林算法在湘中丘陵区林火预测中的应用. 西北林学院学报, 2018, 33(3): 169-177 [Pan D, Yu P-Y, Wu Q. Application of random forest algorithm on the forest fire prediction based on meteorological factors in the Hilly area, central Henan Province. Journal of Northwest Forestry University, 2018, 33(3): 169-177] [40] 孙立研, 刘美玲, 周礼祥, 等. 基于气象因子深度学习的森林火灾预测方法. 林业工程学报, 2019, 4(3): 132-136 [Sun L-Y, Liu M-L, Zhou L-X, et al. Research on forest fire prediction method based on deep learning. Journal of Forestry Engineering, 2019, 4(3): 132-136] [41] 谭宏卫, 曾捷. Logistic回归模型的影响分析. 数理统计与管理, 2013, 32(3): 476-485 [Tan H-W, Zeng J. Influence analysis for Logistic regression model. Journal of Applied Statistics and Management, 2013, 32(3): 476-485] [42] 张吉利, 毕武, 王晓红, 等. 雷击火发生的影响因子与预测研究进展. 应用生态学报, 2013, 24(9): 2674-2684 [Zhang G-L, Bi W, Wang X-H, et al. Lightning-caused fire, its affecting factors and prediction: A review. Chinese Journal of Applied Ecology, 2013, 24(9): 2674-2684] [43] Zhang HJ, Qi PC, Guo GM. Improvement of fire danger modelling with geographically weighted logistic model. International Journal of Wildland Fire, 2014, 23: 1130-1146 [44] Breiman L. Random forests. Machine Learning, 2001, 45: 5-32 [45] 方匡南, 吴见彬, 朱建平, 等. 随机森林方法综述. 统计与信息论坛, 2011, 26(3): 32-37 [Fang K-N, Wu J-B, Zhu J-P, et al. A review of technologies on random forests. Statistics & Information Forum, 2011, 26(3): 32-37] [46] Liaw A, Wiener M. Classification and regression by random forests. R News, 2002, 2: 18-22 [47] 梁慧玲, 林玉蕊, 杨光, 等. 基于气象因子的随机森林算法在塔河地区林火预测中的应用. 林业科学, 2016, 52(1): 89-98 [Liang H-L, Lin Y-R, Yang G, et al. Application of random forest algorithm on the forest fire prediction in Tahe area based on meteorological factors. Scientia Silvae Sinicae, 2016, 52(1): 89-98] [48] 梁慧玲, 郭福涛, 王文辉, 等. 小兴安岭伊春地区林火发生自然影响因子及其影响力. 东北林业大学学报, 2015, 43(12) : 29-35 [Liang H-L, Guo F-T, Wang W-H, et al. Driving factors and their effect power on forest fire occurrence of Yichun, Xiaoxing’an Mountains. Journal of Northeast Forestry University, 2015, 43(12): 29-35] [49] 杨景标, 马晓茜. 人工神经网络预测广东省森林火灾的发生. 林业科学, 2005, 41(4): 127-132 [Yang J-B, Ma X-X. On the basis of artificial neural network to forecast the forest fire in Guangdong Province. Scientia Silvae Sinicae, 2005, 41(4): 127-132] [50] 柳生吉, 杨健. 基于广义线性模型和最大熵模型的黑龙江省林火空间分布模拟. 生态学杂志, 2013, 32(6): 1620-1628 [Liu S-J, Yang J. Modeling spatial patterns of forest fire in Heilongjiang Province using Generalized Linear Model and Maximum Entropy Model. Chinese Journal of Ecology, 2013, 32(6): 1620-1628] [51] Chen F, Du Y, Niu S, et al. Modeling forest lightning fire occurrence in the Daxinganling mountains of Northeastern China with MAXENT. Forests, 2015, 6: 1422-1438 [52] 高学攀, 廖士中. 基于贝叶斯网络的林火概率预测系统设计与实现. 计算机工程与应用, 2017, 53(13): 246-251 [Gao X-P, Liao S-Z. Design and implementation of forest fire probability prediction system based on Bayesian network. Computer Engineering and Applications, 2017, 53(13): 246-251] [53] 孙龙, 尚喆超, 胡海清, 等. Poisson回归模型和负二项回归模型在林火预测领域的应用. 林业科学, 2012, 48(5): 126-129 [Sun L, Shang Z-C, Hu H-Q, et al. Application of a Poisson regression model and a negative binomial regression model in the forest fire forecasting. Scientia Silvae Sinicae, 2012, 48(5): 126-129] [54] 陈峰, 杨树勤. 论负二项分布的应用条件. 中国卫生统计, 1995, 21(4): 21-22 [Chen F, Yang S-Q. Discussion on the negative binomial distribution and its application. Chinese Journal of Health Statistics, 1995, 21(4): 21-22] [55] 郭福涛, 胡海清, 马志海, 等. 不同模型对拟合大兴安岭林火发生与气象因素关系的适用性. 应用生态学报, 2010, 21(1): 159-164 [Guo F-T, Hu H-Q, Ma Z-H, et al. Applicability of different models in simulating the relationships between forest fire occurrence and weather factors in Daxing’an Mountains. Chinese Journal of Applied Ecology, 2010, 21(1): 159-164] [56] 刘克珍, 赵凤君, 王明玉, 等. 基于零膨胀负二项模型对大兴安林地区夏季火发生预报模型研究. 林业机械与木工设备, 2018, 46(6): 7-11 [Liu K-Z, Zhao F-J, Wang M-Y, et al. ZINB-based research on a model for forecasting occurrence of forest fires inDaxing’anling area in summer. Forestry Machinery & Woodworking Equipment, 2018, 46(6): 7-11] [57] 郭福涛, 胡海清, 金森, 等. 基于负二项和零膨胀负二项回归模型的大兴安岭地区雷击火与气象因素的关系. 植物生态学报, 2010, 34(5): 571-577 [Guo F-T, Hu H-Q, Jin S, et al. Relationship between forest lighting fire occurrence and weather factors in Daxing’an Mountains based on negative binomial model and zero-inflated negative binomial models. Chinese Journal of Plant Ecology, 2010, 34(5): 571-577] [58] Mullahy J. Specification and testing of some modified count data models. Journal of Econometrics, 1986, 33: 341-365 [59] 秦凯伦, 郭福涛, 邸雪颖, 等. 大兴安岭塔河地区林火发生的优势预测模型选择. 应用生态学报, 2014, 25(3): 731-737 [Qin K-L, Guo F-T, Di X-Y, et al. Selection of advantage prediction model for forest fire occurrence in Tahe, Daxing’an Mountain. Chinese Journal of Applied Ecology, 2014, 25(3): 731-737] [60] Xiao YD, Zhang XQ, Ji P. Modeling forest fire occurrences using count data mixed models in Qiannan Autono-mous Prefecture of Guizhou Province in China. PLoS One, 2015, 10(3): e0120621 [61] Akaike H. A new look at the statistical model identification. IEEE Transactions on Automatic Control, 1974, 19: 716-723 [62] 许志卿, 苏喜友, 张颐. 基于支持向量机方法的森林火险预测研究. 中国农学通报, 2012, 28(13): 126-131 [Xu Z-Q, Su X-Y, Zhang S. Forest fire prediction based on Support Vector Machine. Chinese Agricultural Science Bulletin, 2012, 28(13): 126-131] [63] 张春霞, 蒋红卫, 尹平. 一种空间负二项回归模型及其应用. 中国卫生统计, 2012, 29(6): 805-807 [Zhang C-X, Jiang H-W, Yin P. A spatial negative binomial regression model and its application. Chinese Journal of Health Statistics, 2012, 29(6): 805-807] |
[1] | 朱润苗, 陈松林. 1980—2020年福建省景观生态风险与生态系统服务价值的空间关系 [J]. 应用生态学报, 2022, 33(6): 1599-1607. |
[2] | 崔晏华, 刘淑德, 张云雷, 徐宾铎, 纪毓鹏, 张崇良, 任一平, 薛莹. 海州湾春季短蛸的栖息分布特征及其与环境因子的关系 [J]. 应用生态学报, 2022, 33(6): 1686-1692. |
[3] | 刘家腾, 赵雪晗, 刘伟韬, 李建荣, 蒋丽娟, 周宇航, 高慧淋, 顾巍. 基于边际回归的沈阳市绿化树种人工油松冠形模拟 [J]. 应用生态学报, 2022, 33(11): 2915-2922. |
[4] | 曾爱聪, 蔡奇均, 苏漳文, 郭新彬, 靳全锋, 郭福涛. 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. |
[5] | 王世航, 卢宏亮, 赵明松, 周玲美. 基于不同特征挖掘方法结合广义提升回归模型估测安徽省土壤pH [J]. 应用生态学报, 2020, 31(10): 3509-3517. |
[6] | 孔维尧, 李欣海, 邹红菲. 最大熵模型在物种分布预测中的优化 [J]. 应用生态学报, 2019, 30(6): 2116-2128. |
[7] | 梁照凤, 陈文波, 郑蕉, 卢陶捷. 南昌市中心城区主要大气污染物分布模拟及土地利用对其影响 [J]. 应用生态学报, 2019, 30(3): 1005-1014. |
[8] | 贾炜玮, 朱飞燕, 李凤日. 长白落叶松人工林心材变化规律 [J]. 应用生态学报, 2018, 29(7): 2277-2285. |
[9] | 赵羽西, 谢平, 桑燕芳, 吴子怡. 基于相关系数的水文相依性变异分级方法——以自回归模型为例 [J]. 应用生态学报, 2018, 29(4): 1089-1097. |
[10] | 褚琳,张欣然,王天巍,李朝霞,蔡崇法. 基于CA-Markov和InVEST模型的城市景观格局与生境质量时空演变及预测 [J]. 应用生态学报, 2018, 29(12): 4106-4118. |
[11] | 郑杨, 董利虎, 李凤日. 黑龙江省红松人工林枝条分布数量模拟 [J]. 应用生态学报, 2016, 27(7): 2172-2180. |
[12] | 王苗苗, 陈洪松, 付同刚, 张 伟, 王克林. 典型喀斯特小流域不同植被类型间土壤养分的差异性及其空间预测方法 [J]. 应用生态学报, 2016, 27(6): 1759-1766. |
[13] | 李明泽, 高元科, 邸雪颖, 范文义. 基于微波遥感技术探测森林地表土壤含水率 [J]. 应用生态学报, 2016, 27(3): 785-793. |
[14] | 高林1,2,3,李长春1,王宝山1,杨贵军2,3*,王磊1,2,3,付奎1. 基于多源遥感数据的大豆叶面积指数估测精度对比 [J]. 应用生态学报, 2016, 27(1): 191-200. |
[15] | 刘康1,李月娥2,吴群1**,沈键芬3. 基于Probit回归模型的经济发达地区土地利用变化驱动力分析——以南京市为例 [J]. 应用生态学报, 2015, 26(7): 2131-2138. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||