Large-scale information on several vegetation properties (‘plant traits’) is critical to assess ecosystem functioning, functional diversity and their role in the Earth system. Hyperspectral remote sensing of plant canopies offers a key tool to map multiple plant traits. However, we are still lacking generalized methods to translate hyperspectral reflectance into a suite of relevant plant traits across biomes, land cover and sensor types. The absence of globally representative data sets and the gap between the available reflectance data with corresponding in-situ measurements have hampered such approaches. In recent years, the scientific community acquired multiple data sets encompassing canopy hyperspectral reflectance and plant traits from different plant types and sensors. To combine these heterogeneous data sets, we propose three multi-trait modeling approaches based on Convolutional Neural Networks (CNNs …
%0 Journal Article
%1 cherif2023spectra
%A Cherif, Eya
%A Feilhauer, Hannes
%A Berger, Katja
%A Dao, Phuong D
%A Ewald, Michael
%A Hank, Tobias B
%A He, Yuhong
%A Kovach, Kyle R
%A Lu, Bing
%A Townsend, Philip A
%A Kattenborn, Teja
%D 2023
%I Elsevier
%J Remote Sensing of Environment
%K imported topic_earthenvironment
%P 113580
%T From spectra to plant functional traits: Transferable multi-trait models from heterogeneous and sparse data
%V 292
%X Large-scale information on several vegetation properties (‘plant traits’) is critical to assess ecosystem functioning, functional diversity and their role in the Earth system. Hyperspectral remote sensing of plant canopies offers a key tool to map multiple plant traits. However, we are still lacking generalized methods to translate hyperspectral reflectance into a suite of relevant plant traits across biomes, land cover and sensor types. The absence of globally representative data sets and the gap between the available reflectance data with corresponding in-situ measurements have hampered such approaches. In recent years, the scientific community acquired multiple data sets encompassing canopy hyperspectral reflectance and plant traits from different plant types and sensors. To combine these heterogeneous data sets, we propose three multi-trait modeling approaches based on Convolutional Neural Networks (CNNs …
@article{cherif2023spectra,
abstract = {Large-scale information on several vegetation properties (‘plant traits’) is critical to assess ecosystem functioning, functional diversity and their role in the Earth system. Hyperspectral remote sensing of plant canopies offers a key tool to map multiple plant traits. However, we are still lacking generalized methods to translate hyperspectral reflectance into a suite of relevant plant traits across biomes, land cover and sensor types. The absence of globally representative data sets and the gap between the available reflectance data with corresponding in-situ measurements have hampered such approaches. In recent years, the scientific community acquired multiple data sets encompassing canopy hyperspectral reflectance and plant traits from different plant types and sensors. To combine these heterogeneous data sets, we propose three multi-trait modeling approaches based on Convolutional Neural Networks (CNNs …},
added-at = {2024-11-29T11:49:51.000+0100},
author = {Cherif, Eya and Feilhauer, Hannes and Berger, Katja and Dao, Phuong D and Ewald, Michael and Hank, Tobias B and He, Yuhong and Kovach, Kyle R and Lu, Bing and Townsend, Philip A and Kattenborn, Teja},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2fbd4b1f99b3db29fa868b78da7410657/joum576e},
citation = {Remote Sensing of Environment 292, 113580, 2023},
interhash = {9e2bdc0f20193a6e8df0568ad4681089},
intrahash = {fbd4b1f99b3db29fa868b78da7410657},
journal = {Remote Sensing of Environment},
keywords = {imported topic_earthenvironment},
pages = 113580,
publisher = {Elsevier},
timestamp = {2024-11-29T11:49:51.000+0100},
title = {From spectra to plant functional traits: Transferable multi-trait models from heterogeneous and sparse data},
volume = 292,
year = 2023
}
