Artificial neural networks reveal a high-resolution climatic signal in leaf physiognomy

doi:10.1016/j.palaeo.2015.11.005

	Artificial neural networks reveal a high-resolution climatic signal in leaf physiognomy
	Li, Shu-Feng 1,5; Jacques, Frederic M. B.1; Spicer, Robert A.3; Su, Tao 1; Spicer, Teresa E. V.4; Yang, Jian 4; Zhou, Zhe-Kun1,2
	2016-01-15
发表期刊	PALAEOGEOGRAPHY PALAEOCLIMATOLOGY PALAEOECOLOGY
卷号	442 页码:1-11
摘要	The relationship linking leaf physiognomy and climate has long been used in paleoclimatic reconstructions, but current models lose precision when worldwide data sets are considered because of the broader range of physiognomies that occur under the wider range of climate types represented. Our aim is to improve the predictive power of leaf physiognomy to yield climate signals, and here we explore the use of an algorithm based on the general regression neural network (GRNN), which we refer to as Climate Leaf Analysis with Neural Networks (CLANN). We then test our algorithm on Climate Leaf Analysis Multivariate Program (CLAMP) data sets and digital leaf physiognomy (DLP) data sets, and compare our results with those obtained from other computation methods. We explore the contribution of different physiognomic characters and test fossil sites from North America. The CLANN algorithm introduced here gives high predictive precision for all tested climatic parameters in both data sets. For the CLAMP data set neural network analysis improves the predictive capability as measured by R-2, to 0.86 for MAT on a worldwide basis, compared to 0.71 using the vector-based approach used in the standard analysis. Such a high resolution is attained due to the nonlinearity of the method, but at the cost of being susceptible to 'noise' in the calibration data. Tests show that the predictions are repeatable, and robust to information loss and applicable to fossil leaf data. The CLANN neural network algorithm used here confirms, and better resolves, the global leaf form-climate relationship, opening new approaches to paleoclimatic reconstruction and understanding the evolution of complex leaf function. (C) 2015 Elsevier B.V. All rights reserved.
关键词	Artificial Neural Networks Climate Clamp Clann Fossil Leaf Physiognomy
DOI	10.1016/j.palaeo.2015.11.005
收录类别	SCI
语种	英语
WOS记录号	WOS:000369681300001
引用统计
文献类型	期刊论文
条目标识符	http://ir.kib.ac.cn/handle/151853/25959
专题	中国科学院东亚植物多样性与生物地理学重点实验室
作者单位	1.Chinese Acad Sci, Key Lab Trop Forest Ecol, Xishuangbanna Trop Bot Garden, Mengla 666303, Peoples R China 2.Chinese Acad Sci, Kunming Inst Bot, Key Lab Biogeog & Biodivers, Kunming 650204, Peoples R China 3.Open Univ, Ctr Earth Planetary Space & Astron Res, Environm Earth & Ecosyst, Milton Keynes, Bucks, England 4.Chinese Acad Sci, Inst Bot, State Key Lab Systemat & Evolutionary Bot, Beijing 100093, Peoples R China 5.Chinese Acad Sci, Nanjing Inst Geol & Paleontol, State Key Lab Paleobiol & Stratig, Nanjing 210008, Peoples R China
推荐引用方式 GB/T 7714	Li, Shu-Feng,Jacques, Frederic M. B.,Spicer, Robert A.,et al. Artificial neural networks reveal a high-resolution climatic signal in leaf physiognomy[J]. PALAEOGEOGRAPHY PALAEOCLIMATOLOGY PALAEOECOLOGY,2016,442:1-11.
APA	Li, Shu-Feng.,Jacques, Frederic M. B..,Spicer, Robert A..,Su, Tao.,Spicer, Teresa E. V..,...&Zhou, Zhe-Kun.(2016).Artificial neural networks reveal a high-resolution climatic signal in leaf physiognomy.PALAEOGEOGRAPHY PALAEOCLIMATOLOGY PALAEOECOLOGY,442,1-11.
MLA	Li, Shu-Feng,et al."Artificial neural networks reveal a high-resolution climatic signal in leaf physiognomy".PALAEOGEOGRAPHY PALAEOCLIMATOLOGY PALAEOECOLOGY 442(2016):1-11.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
1-s2.0-S003101821500（614KB）			开放获取	CC BY-NC-SA	浏览下载