中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 南京地质古生物研究所
  3. 中国科学院南京地质古生物研究所
Machine-learning-based morphological analyses of leaf epidermal cells in modern and fossil ginkgo and their implications for palaeoclimate studies

文献类型：期刊论文

作者Zhang, Li4,5,6,7; Wang, Yongdong6,7; Ruhl, Micha4,5; Xu, Yuanyuan3,6; Zhu, Yanbin3,6; An, Pengcheng3,6; Chen, Hongyu3,6; Yan, Defei1,2
刊名PALAEONTOLOGY
出版日期2023-11-01
卷号66期号:6页码:16
ISSN号0031-0239
关键词Ginkgo epidermal cell micro-character machine learning palaeoclimate parameter
DOI10.1111/pala.12684
通讯作者Wang, Yongdong(ydwang@nigpas.ac.cn) ; Ruhl, Micha(ruhlm@tcd.ie)
英文摘要Leaf stomata form an essential conduit between plant tissue and the atmosphere, thus presenting a link between plants and their environments. Changes in their properties in fossil leaves have been studied widely to infer palaeo-atmospheric-CO(2 )in deep time, ranging from the Palaeozoic to the Cenozoic. Epidermal cells of leaves, however, have often been neglected for their usefulness in reconstructing past-environments, as their irregular shape makes the manual analyses of epidermal cells a challenging and error-prone task. Here, we used machine-learning (using the U-Net architecture, which evolved from a fully convolutional network) to segment epidermal cells automatically, to efficiently reduce artificial errors. We furthermore applied minimum bounding rectangles to extract length-to-width ratios (R-L/W) from the irregularly shaped cells. We applied this to a dataset including over 21 000 stomata and 170 000 epidermal cells in 114 Ginkgo leaves from 16 locations spanning three climate zones in China. Our results show negative correlations between the R-L/W and specific climatic parameters, suggesting that local temperature and precipitation conditions may have affected the R-L/W of epidermal cells. We subsequently tested this methodology and the observations from the modern dataset on 15 fossil ginkgoaleans from the Lower to the Middle Jurassic (China). It suggested that the R-L/W values of fossil ginkgo generally had a similar negative response to warmer climatic backgrounds as modern G. biloba. The automated analyses of large palaeo-floral datasets provide a new direction for palaeoclimate reconstructions and emphasize the importance of hidden morphological characters of epidermal cells in ginkgoaleans.
WOS关键词ATMOSPHERIC CARBON-DIOXIDE ; STOMATAL DENSITY ; CO2 CONCENTRATIONS ; BILOBA L. ; PLANTS ; RESPONSES ; LEAVES ; ULTRASTRUCTURE ; DIVISION ; PAVEMENT
资助项目National Natural Science Foundation of China ; Institute of Geochemistry at CAS ; Strategic Priority Research Program (B) of the Chinese Academy of Sciences[XDB26000000] ; State Key Laboratory of Palaeobiology and Stratigraphy[20172103] ; State Key Laboratory of Palaeobiology and Stratigraphy[20191103] ; State Key Laboratory of Palaeobiology and Stratigraphy[20192101] ; China Scholarship Council[202006190261] ; ICDP Integrated Understanding of the Early Jurassic Earth System[IGCP 632] ; ICDP Integrated Understanding of the Early Jurassic Earth System[IGCP 655] ; ICDP Integrated Understanding of the Early Jurassic Earth System[IGCP 739] ; [NSFC 42330208] ; [41702004] ; [41790454] ; [42002023]
WOS研究方向Paleontology
语种英语
出版者WILEY
WOS记录号WOS:001126644000001
资助机构National Natural Science Foundation of China ; Institute of Geochemistry at CAS ; Strategic Priority Research Program (B) of the Chinese Academy of Sciences ; State Key Laboratory of Palaeobiology and Stratigraphy ; China Scholarship Council ; ICDP Integrated Understanding of the Early Jurassic Earth System
源URL[http://ir.nigpas.ac.cn/handle/332004/42838]  
专题中国科学院南京地质古生物研究所
通讯作者Wang, Yongdong; Ruhl, Micha
作者单位1.Lanzhou Univ, Sch Earth Sci, Lanzhou, Peoples R China
2.Lanzhou Univ, Key Lab Mineral Resources Western China Gansu Prov, Lanzhou 730000, Peoples R China
3.Univ Chinese Acad Sci, Beijing 10049, Peoples R China
4.Univ Dublin, Trinity Coll Dublin, Irish Ctr Res Appl Geosci iCRAG, Dublin, Ireland
5.Univ Dublin, Trinity Coll Dublin, Dept Geol, Dublin, Ireland
6.Chinese Acad Sci, State Key Lab Palaeobiol & Stratig, Nanjing Inst Geol & Palaeontol, Nanjing 210008, Peoples R China
7.Nanjing Univ, Ctr Res & Educ Biol Evolut & Environm, Sch Earth Sci & Engn, Nanjing 210023, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Li,Wang, Yongdong,Ruhl, Micha,et al. Machine-learning-based morphological analyses of leaf epidermal cells in modern and fossil ginkgo and their implications for palaeoclimate studies[J]. PALAEONTOLOGY,2023,66(6):16.
APA Zhang, Li.,Wang, Yongdong.,Ruhl, Micha.,Xu, Yuanyuan.,Zhu, Yanbin.,...&Yan, Defei.(2023).Machine-learning-based morphological analyses of leaf epidermal cells in modern and fossil ginkgo and their implications for palaeoclimate studies.PALAEONTOLOGY,66(6),16.
MLA Zhang, Li,et al."Machine-learning-based morphological analyses of leaf epidermal cells in modern and fossil ginkgo and their implications for palaeoclimate studies".PALAEONTOLOGY 66.6(2023):16.

入库方式： OAI收割

来源：南京地质古生物研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。