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. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 生态系统研究网络观测与模拟重点实验室
  5. 外文论文
Intelligent retrieval of leaf traits using hyperspectral reflectance and deep learning

文献类型：期刊论文

作者Qi, Wenchao3; Yu, Le3,4,5; Liu, Tao3; Wu, Hui6; Zhao, Qiang3; Wu, Linsheng7; Kang, Xiaoyan8; Wang, Yibo9; Zhang, Lifu1,2
刊名EUROPEAN JOURNAL OF AGRONOMY
出版日期2026-03-01
卷号174页码:127960
关键词Leaf trait retrieval Hyperspectral spectroscopy Intelligent modelling Kolmogorov-Arnold Network Transformer Temporal convolutional network
ISSN号1161-0301
DOI10.1016/j.eja.2025.127960
产权排序6
文献子类Article
英文摘要Reliable and intelligent retrieval of leaf traits from hyperspectral reflectance is crucial for assessing ecosystem functions, yet conventional approaches struggle with spectral complexity and nonlinearities. To address these challenges, we developed the Leaf Trait Retrieval Network (LTRN), a novel deep learning framework that integrates Kolmogorov-Arnold Network (KAN), Transformer, and Temporal Convolutional Networks (TCN) for end-to-end trait estimation. Model validation was carried out using a large spectral-trait database covering hundreds of plant species and four functional traits. Experimental results demonstrated that LTRN model outperforms state-of-the-art deep learning models, achieving R2 values greater than 0.78 for estimating chlorophyll content (Chla+b), equivalent water thickness (EWT), carotenoid content (Ccar), and leaf mass per area (LMA). Further analyses indicated that the LTRN model delivers stable estimation performance across spectral resolutions of 10-25 nm. Moreover, the model demonstrates strong stability across varying proportions of training samples. These findings underscore the robustness and stability of LTRN for large-scale vegetation trait retrieval, offering a valuable framework for advancing the intelligent estimation of other ecological parameters.
URL标识查看原文
WOS研究方向Agriculture
语种英语
WOS记录号WOS:001645748700001
出版者ELSEVIER
源URL[http://ir.igsnrr.ac.cn/handle/311030/219662]  
专题生态系统网络观测与模拟院重点实验室_外文论文
通讯作者Yu, Le
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China;
3.Tsinghua Univ, Inst Global Change Studies, Dept Earth Syst Sci, Minist Educ,Key Lab Earth Syst Modeling, Beijing 100084, Peoples R China;
4.Tsinghua Univ, Dept Earth Syst Sci, Minist Educ, Ecol Field Stn East Asian Migratory Birds, Beijing 100084, Peoples R China;
5.Tsinghua Univ, Inst Carbon Neutral, Beijing 100084, Peoples R China;
6.Northeast Forestry Univ, Coll Forestry, Northeast Asia Biodivers Res Ctr, Harbin 150040, Peoples R China;
7.Nanjing Univ, Int Inst Earth Syst Sci, Nanjing, Peoples R China;
8.Chinese Acad Sci, Key Lab Ecosyst Network Observat & Modeling, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China;
9.Guangzhou Univ, Inst Aerosp Remote Sensing Innovat, Guangzhou 510006, Guangdong, Peoples R China;
推荐引用方式
GB/T 7714		 Qi, Wenchao,Yu, Le,Liu, Tao,et al. Intelligent retrieval of leaf traits using hyperspectral reflectance and deep learning[J]. EUROPEAN JOURNAL OF AGRONOMY,2026,174:127960.
APA Qi, Wenchao.,Yu, Le.,Liu, Tao.,Wu, Hui.,Zhao, Qiang.,...&Zhang, Lifu.(2026).Intelligent retrieval of leaf traits using hyperspectral reflectance and deep learning.EUROPEAN JOURNAL OF AGRONOMY,174,127960.
MLA Qi, Wenchao,et al."Intelligent retrieval of leaf traits using hyperspectral reflectance and deep learning".EUROPEAN JOURNAL OF AGRONOMY 174(2026):127960.

入库方式： OAI收割

来源：地理科学与资源研究所

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。