文献类型： 外文期刊

作者： Janssen, Thomas A. J. ¹ ; Jones, Matthew W. ² ; Finney, Declan ³ ; Van der Werf, Guido R. ¹ ; van Wees, Dave ¹ ; Xu, Wenxuan ⁶ ; Veraverbeke, Sander ¹ ;

作者机构： 1.Vrije Univ Amsterdam, Fac Sci, Amsterdam, Netherlands

2.Univ East Anglia, Sch Environm Sci, Tyndall Ctr Climate Change Res, Norwich, Norfolk, England

3.Univ Leeds, Sch Earth & Environm, Leeds, W Yorkshire, England

4.Wageningen Univ & Res, Meteorol & Air Qual Grp, Wageningen, Netherlands

5.BeZero Carbon Ltd, London, England

6.Jiangsu Acad Agr Sci, Inst Agr Informat, Nanjing, Peoples R China

期刊名称：NATURE GEOSCIENCE （ 影响因子：18.3； 五年影响因子：19.6 ）

ISSN： 1752-0894

年卷期： 2023 年 16 卷 12 期

页码：

收录情况： SCI

摘要： Fires can be ignited by people or by natural causes, which are almost exclusively lightning strikes. Discriminating between lightning and anthropogenic fires is paramount when estimating impacts of changing socioeconomic and climatological conditions on fire activity. Here we use reference data of fire ignition locations, cause and burned area from seven world regions in a machine-learning approach to obtain a global attribution of lightning and anthropogenic ignitions as dominant fire ignition sources. We show that 77% (uncertainty expressed as one standard deviation = 8%) of the burned area in extratropical intact forests currently stems from lightning and that these areas will probably experience 11 to 31% more lightning per degree warming. Extratropical forests are of global importance for carbon storage. They currently experience high fire-related forest losses and have, per unit area, among the largest fire emissions on Earth. Future increases in lightning in intact forest may therefore compound the positive feedback loop between climate change and extratropical wildfires.