基于GEE的中国不同生态系统林火驱动力研究

doi:10.3969/j.issn.0255-8297.2024.04.010

摘要/Abstract

摘要： 针对同时对大尺度范围内的不同生态系统林火驱动力研究的难题，提出一种基于谷歌地球引擎（google earth engine,GEE）实现大范围不同生态系统林火驱动力的分析方法。首先基于GEE在线获取中国4个主要不同生态系统林火数据集、Sentinel-2卫星影像和驱动因子等信息，再通过Sentinel-2影像提取的归一化燃烧率差值筛选真实林火点，然后利用随机森林、支持向量机和增强回归树法对林火点分类并评价其表现，最后筛选最佳方法进行林火驱动力重要性分析。研究结果表明：随机森林预测林火的精度最高，均超过92%；山西省长治市和内蒙古大兴安岭地区林火最重要的驱动力分别为人口分布和最高温度，而四川省凉山彝族自治州和江西省赣州市林火发生最重要的两个驱动因子均为帕默尔干旱指数和土壤湿度。研究证明基于GEE的方法可有效地同时实现大范围内中国不同生态系统林火驱动力研究。

关键词: 林火, 驱动力, 随机森林, 支持向量机, 增强回归树, 谷歌地球引擎

Abstract: Focused on studying wildfire and driving forces across various ecosystems on a large scale, this paper presents a novel method utilizing the google earth engine (GEE) platform. Firstly, the fire information for resource management system database, Sentinel-2 images and driving factor information in four different Chinese ecosystems were accessed on online via GEE platform. Then, the differential normalized burn ratio was extracted from Sentinel-2 images to sieve fire spots. Three machine learning algorithms, namely random forest, support vector machine and augmented regression tree, were used to classify fire locations. Furthermore, we determined the optimal-performing classification algorithms for each ecosystem and assessed variable importance. The results showed that random forest performed best with accuracy exceeding 92% among the three machine methods and the fire drivers varied significantly among four different ecosystems. In Changzhi City of Shanxi Province, and the Great Xing′an Mountains of Inner Mongolia, population distribution and maximum temperature were identified as the most influential drivers, respectively. While for Liangshan Yi Autonomous Prefecture in Sichuan Province and Ganzhou City in Jiangxi Province, the palmer drought index and soil moisture emerged as the primary drivers. This study demonstrates the efficacy of the proposed GEE-based method in studying wildfire and driving forces across different ecosystems in large scale regions.

Key words: wildfire, driving force, random forest, support vector machines, enhanced return tree, google earth engine (GEE)

中图分类号:

X87
TP79

马丹, 汤志伟, 马小玉, 邵尔辉, 黄达沧. 基于GEE的中国不同生态系统林火驱动力研究[J]. 应用科学学报, 2024, 42(4): 684-694.

MA Dan, TANG Zhiwei, MA Xiaoyu, SHAO Erhui, HUANG Dacang. Exploration Analysis of Fire Drives in Different Chinese Ecosystems Based on Google Earth Engine[J]. Journal of Applied Sciences, 2024, 42(4): 684-694.

参考文献

[1] Bowman D M J S, Williamson G J, Abatzoglou J T, et al. Human exposure and sensitivity to globally extreme wildfire events [J]. Nature Ecology & Evolution, 2017, 1(3): 58.
[2] 岳超, 罗彩访, 舒立福, 等．全球变化背景下野火研究进展[J]．生态学报, 2020, 40(2): 385-401． Yue C, Luo C F, Shu L F, et al. A review on wildfire studies in the context of global change [J]. Acta Ecologica Sinica, 2020, 40(2): 385-401. (in Chinese)
[3] Turner D, Lewis M, Ostendorf B. Spatial indicators of fire risk in the arid and semi-arid zone of Australia [J]. Ecological Indicators, 2011, 11(1): 149-167．
[4] 李晓炜, 赵刚, 于秀波, 等. 不同区域森林火灾对生态因子的响应及其概率模型[J]. 生态学报, 2013, 33(4): 1219-1229. Li X W, Zhao G, Yu X B, et al. Probability models of forest fire risk based on ecology factors in different vegetation regions over China [J]. Acta Ecologica Sinica, 2013, 33(4): 1219-1229. (in Chinese)
[5] 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[J]. 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 patteren of forest fire in Fujian Province [J]. Journal of Natural Disasters, 2016, 25(2): 110-119. (in Chinese)
[6] 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[J]. 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 [J]. Journal of Forest and Environment, 2017, 37(1): 88-94. (in Chinese)
[7] 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 [J]. Chinese Journal of Applied Ecology, 2020, 31(2): 399-406. (in Chinese)
[8] 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[J]. 火灾科学, 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 Province based on random forest algorithm [J]. Fire Safety Science, 2015, 24(4): 191- 200. (in Chinese)
[9] 顾先丽, 吴志伟, 张宇婧, 等. 气候变化背景下江西省林火空间预测[J]. 生态学报, 2020, 40(2): 667-677. Gu X L, Wu Z W, Zhang Y J, et al. Prediction research of the forest fire in Jiangxi Province in the background of climate change [J]. Acta Ecologica Sinica, 2020, 40(2): 667-677. (in Chinese)
[10] 苏佳佳, 刘志华, 焦珂伟, 等. 气候变化对中国林火干扰空间格局的影响[J]. 生态学杂志, 2021, 40(12): 3810-3821. Su J J, Liu Z H, Jiao K W, et al. Effects of climate change on spatial pattern of forest fire regime in China [J]. Chinese Journal of Ecology, 2021, 40(12): 3810-3821. (in Chinese)
[11] 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[J]. 中南林业科技大学学报, 2020, 40(9): 57-69. Ma W Y, Feng Z K, Cheng Z X, et al. Study on driving factors and distribution pattern of forest fires in Shanxi Province [J]. Journal of Central South University of Forestry & Technology, 2020, 40(9): 57-69. (in Chinese)
[12] Viedma O, Chico F, Fernández J J, et al. Disentangling the role of prefire vegetation vs. burning conditions on fire severity in a large forest fire in SE Spain [J]. Remote Sensing of Environment, 2020, 247: 111891.
[13] 曾超, 曾珍, 曹振宇, 等. 多源时序国产卫星影像的森林火灾动态监测——以四川省木里县及其周边林区为例[J]. 遥感技术与应用, 2021, 36(3): 521-532. Zeng C, Zeng Z, Cao Z Y, et al. Forest fire dynamic monitoring based on time series and multi-source satellite images: a case study of the Muli County forest areas in Sichuan Province [J]. Remote Sensing Technology and Application, 2021, 36(3): 521-532. (in Chinese)
[14] 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[J]. 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 [J]. World Forestry Research, 2017, 30(2): 41-45. (in Chinese)
[15] 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. (in Chinese)
[16] Guo F, Su Z, Wang G, et al. Understanding fire drivers and relative impacts in different Chinese forest ecosystems [J]. Science of the Total Environment, 2017, 605-606: 411-425.
[17] 付东杰, 肖寒, 苏奋振, 等. 遥感云计算平台发展及地球科学应用[J]. 遥感学报, 2021, 25(1): 220- 230. Fu D J, Xiao H, Su F Z, et al. Remote sensing cloud computing platform development and Earth science application [J]. National Remote Sensing Bulletin, 2021, 25(1): 220-230. (in Chinese)
[18] 陈虹, 郭兆成, 贺鹏. 1988—2018年间洱海流域植被覆盖度时空变换特征探究[J]. 国土资源遥感, 2021, 33(2): 116-123. Chen H, Guo Z, He P. Spatial and temporal change characteristics of vegetation coverage in Erhai Lake basin during 1988—2018[J]. Remote Sensing for Land & Resources, 2021, 33(2): 116-123. (in Chinese)
[19] 盛艳玲, 张荫, 乔纪纲. 基于GEE的亚马逊生态区火灾变化特征及与降水关系[J]. 生态学杂志, 2021, 40(8): 2553-2562. Sheng Y L, Zhang Y, Qiao J G. Changes of fire and the relationship with precipitation in Amazon ecological area based on GEE [J]. Chinese Journal of Ecology, 2021, 40(8): 2553-2562. (in Chinese)
[20] Sulova A, Arsanjani J J. Exploratory analysis of driving force of wildfires in Australia: an application of machine learning within google earth engine [J]. Remote Sensing, 2021, 13(1): 10.
[21] 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[J]. 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 [J]. Journal of Northwest A&F University (Natural Science Edition), 2020, 48(2): 102-109. (in Chinese)
[22] 贾旭, 高永, 魏宝成, 等. 基于MODIS数据的内蒙古地形因子对火灾分布的影响分析[J]. 北京林业大学学报, 2017, 39(5): 34-40. Jia X, Gao Y, Wei B C, et al. Impact of topographic features on the distribution of fire based on MODIS data in Inner Mongolia, Northern China [J]. Journal of Beijing Forestry University, 2017, 39(5): 34-40. (in Chinese)
[23] 杜建华, 宫殷婷, 蒋丽伟. 中国森林火灾发生特征及其与主要气候因子的关系研究[J]. 林业资源管理, 2019, (2): 7-14. Du J H, Gong Y T, Jiang L W. Study on the characteristics of forest fires in china and their relationship with major climatic factors [J]. Forest Resources Management, 2019(2): 7-14. (in Chinese)
[24] 付婧婧, 吴志伟, 闫赛佳, 等. 气候、植被和地形对大兴安岭林火烈度空间格局的影响[J]. 生态学报, 2020, 40(5): 1672-1682. Fu J J, Wu Z W, Yan S J, et al. Effects of climate, vegetation， and topography on spatial patterns of burn severity in the Great Xing'an Mountains [J]. Acta Ecologica Sinica, 2020, 40(5): 1672-1682. (in Chinese)
[25] Castro A C M, Nunes A, Sousa A, et al. Mapping the causes of forest fires in Portugal by clustering analysis [J]. Geosciences, 2020, 10(2): 53.
[26] Nolan R H, Boer M M, Collins L, et al. Causes and consequences of eastern Australia’s 2019-20 season of mega-fires [J]. Global Change Biology, 2020, 26(3): 1039-1041.
[27] Ganteaume A, Camia A, Jappiot M, et al. A review of the main driving factors of forest fire ignition over Europe [J]. Environmental Management, 2013, 51(3): 651-662.
[28] Miranda B R, Sturtevant B R, Stewart S I, et al. Spatial and temporal drivers of wildfire occurrence in the context of rural development in Northern Wisconsin, USA [J]. International Journal of Wildland Fire, 2012, 21(2): 141-154.
[29] 国家统计局. 中国统计年鉴[EB/OL]. 2021[2023-02-16]. http://www.stats.gov.cn/tjsj/ndsj/2021/indexch.htm.
[30] 谷鑫志, 曾庆伟, 谌华, 等. 高分三号影像水体信息提取[J]. 遥感学报, 2019, 23(3): 555-565. Gu X Z, Zeng Q W, Shen H, et al. Study on water information extraction using domestic GF-3 image [J]. Journal of Remote Sensing, 2019, 23(3): 555-565. (in Chinese)
[31] Furniss T J, Kane V R, Larson A J, et al. Detecting tree mortality with Landsat-derived spectral indices: improving ecological accuracy by examining uncertainty [J]. Remote Sensing of Environment, 2020, 237: 111497.
[32] Collins L, Griffioen P, Newell G, et al. The utility of random forests for wildfire severity mapping [J]. Remote Sensing of Environment, 2018, 216: 374-384.
[33] Lin H T, Lam T Y, Peng P H, et al. Embedding boosted regression trees approach to variable selection and cross-validation in parametric regression to predict diameter distribution after thinning [J]. Forest Ecology and Management, 2021, 499: 119631.
[34] 冯发杰, 吏军平, 丁亚洲, 等. 基于多尺度视觉特征组合的高分遥感影像目标检测[J]. 应用科学学报, 2018, 36(3): 471-484. Feng F J, Li J P, Ding Y Z, et al. Target detection from high resolution remote sensing images based on combination of multi-scale visual features [J]. Journal of Applied Sciences, 2018, 36(3): 471-484. (in Chinese)