Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model

Plant traits play a pivotal role in steering ecosystem dynamics. As plant canopies have evolved to interact with light, spectral data convey information on a variety of plant traits. Machine learning techniques have been used successfully to retrieve diverse traits from hyperspectral data. Nonethele...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniel Mederer, Hannes Feilhauer, Eya Cherif, Katja Berger, Tobias B. Hank, Kyle R. Kovach, Phuong D. Dao, Bing Lu, Philip A. Townsend, Teja Kattenborn
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:ISPRS Open Journal of Photogrammetry and Remote Sensing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667393224000243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344349607821312
author Daniel Mederer
Hannes Feilhauer
Eya Cherif
Katja Berger
Tobias B. Hank
Kyle R. Kovach
Phuong D. Dao
Bing Lu
Philip A. Townsend
Teja Kattenborn
author_facet Daniel Mederer
Hannes Feilhauer
Eya Cherif
Katja Berger
Tobias B. Hank
Kyle R. Kovach
Phuong D. Dao
Bing Lu
Philip A. Townsend
Teja Kattenborn
author_sort Daniel Mederer
collection DOAJ
description Plant traits play a pivotal role in steering ecosystem dynamics. As plant canopies have evolved to interact with light, spectral data convey information on a variety of plant traits. Machine learning techniques have been used successfully to retrieve diverse traits from hyperspectral data. Nonetheless, the efficacy of machine learning is restricted by limited access to high-quality reference data for training. Previous studies showed that aggregating data across domains, sensors, or growth forms provided by collaborative efforts of the scientific community enables the creation of transferable models. However, even such curated databases are still sparse for several traits. To address these challenges, we investigated the potential of filling such data gaps with simulated hyperspectral data generated through the most widely-used radiative transfer model (RTM) PROSAIL. We coupled trait information from the TRY plant trait database with information on plant communities from the sPlot database, to build a realistic input trait dataset for the RTM-based simulation of canopy spectra. Our findings indicate that simulated data can alleviate the effects of data scarcity for highly underrepresented traits. In most other cases, however, the effects of including simulated data from RTMs are negligible or even negative. While more complex RTM models promise further improvements, their parameterization remains challenging. This highlights two key observations: firstly, RTM models, such as PROSAIL, exhibit limitations in producing realistic spectra across diverse ecosystems; secondly, real-world data repurposed from various sources exhibit superior retrieval success compared to simulated data. As a result, we advocate to emphasize the importance of active data sharing over secrecy and overreliance on modeling to address data limitations.
format Article
id doaj-art-7aec010db093446eaba43defc41f3c56
institution Kabale University
issn 2667-3932
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series ISPRS Open Journal of Photogrammetry and Remote Sensing
spelling doaj-art-7aec010db093446eaba43defc41f3c562025-08-20T03:42:41ZengElsevierISPRS Open Journal of Photogrammetry and Remote Sensing2667-39322025-01-011510008010.1016/j.ophoto.2024.100080Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL modelDaniel Mederer0Hannes Feilhauer1Eya Cherif2Katja Berger3Tobias B. Hank4Kyle R. Kovach5Phuong D. Dao6Bing Lu7Philip A. Townsend8Teja Kattenborn9Institute for Earth System Science and Remote Sensing, Leipzig University, Talstr. 35, 04103, Leipzig, Germany; Corresponding author.Institute for Earth System Science and Remote Sensing, Leipzig University, Talstr. 35, 04103, Leipzig, Germany; Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Leipzig University - TU Dresden, Germany; German Centre for Integrative Biodiversity Research (iDiv), Halle-Jena-Leipzig, Germany; Helmholtz-Centre for Environmental Research (UFZ), Permoserstraße 15, 04318, Leipzig, GermanyInstitute for Earth System Science and Remote Sensing, Leipzig University, Talstr. 35, 04103, Leipzig, Germany; Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Leipzig University - TU Dresden, GermanyGFZ Helmholtz Centre for Geosciences, Telegrafenberg, 14473, Potsdam, GermanyDepartment of Geography, Faculty of Geosciences, Ludwig-Maximilians-Universität München (LMU), Luisenstr. 37, 80333, Munich, GermanyDepartment of Forest and Wildlife Ecology, University of Wisconsin-Madison, 1630 Linden Drive, Madison, WI, 53706, USADepartment of Agricultural Biology, Colorado State University, 307 University Avenue, Fort Collins, CO, 80523, USADepartment of Geography, Simon Fraser University, 8888 University Drive, Burnaby, BC, V5A 1S6, CanadaDepartment of Forest and Wildlife Ecology, University of Wisconsin-Madison, 1630 Linden Drive, Madison, WI, 53706, USASensor-based Geoinformatics (geosense), University of Freiburg, Tennenbacherstr. 4, 79106, Freiburg, GermanyPlant traits play a pivotal role in steering ecosystem dynamics. As plant canopies have evolved to interact with light, spectral data convey information on a variety of plant traits. Machine learning techniques have been used successfully to retrieve diverse traits from hyperspectral data. Nonetheless, the efficacy of machine learning is restricted by limited access to high-quality reference data for training. Previous studies showed that aggregating data across domains, sensors, or growth forms provided by collaborative efforts of the scientific community enables the creation of transferable models. However, even such curated databases are still sparse for several traits. To address these challenges, we investigated the potential of filling such data gaps with simulated hyperspectral data generated through the most widely-used radiative transfer model (RTM) PROSAIL. We coupled trait information from the TRY plant trait database with information on plant communities from the sPlot database, to build a realistic input trait dataset for the RTM-based simulation of canopy spectra. Our findings indicate that simulated data can alleviate the effects of data scarcity for highly underrepresented traits. In most other cases, however, the effects of including simulated data from RTMs are negligible or even negative. While more complex RTM models promise further improvements, their parameterization remains challenging. This highlights two key observations: firstly, RTM models, such as PROSAIL, exhibit limitations in producing realistic spectra across diverse ecosystems; secondly, real-world data repurposed from various sources exhibit superior retrieval success compared to simulated data. As a result, we advocate to emphasize the importance of active data sharing over secrecy and overreliance on modeling to address data limitations.http://www.sciencedirect.com/science/article/pii/S2667393224000243Hyperspectral remote sensingPlant trait retrievalDeep learningRadiative transfer modelingImaging spectroscopyCanopy properties
spellingShingle Daniel Mederer
Hannes Feilhauer
Eya Cherif
Katja Berger
Tobias B. Hank
Kyle R. Kovach
Phuong D. Dao
Bing Lu
Philip A. Townsend
Teja Kattenborn
Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model
ISPRS Open Journal of Photogrammetry and Remote Sensing
Hyperspectral remote sensing
Plant trait retrieval
Deep learning
Radiative transfer modeling
Imaging spectroscopy
Canopy properties
title Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model
title_full Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model
title_fullStr Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model
title_full_unstemmed Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model
title_short Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model
title_sort plant trait retrieval from hyperspectral data collective efforts in scientific data curation outperform simulated data derived from the prosail model
topic Hyperspectral remote sensing
Plant trait retrieval
Deep learning
Radiative transfer modeling
Imaging spectroscopy
Canopy properties
url http://www.sciencedirect.com/science/article/pii/S2667393224000243
work_keys_str_mv AT danielmederer planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT hannesfeilhauer planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT eyacherif planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT katjaberger planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT tobiasbhank planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT kylerkovach planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT phuongddao planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT binglu planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT philipatownsend planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel
AT tejakattenborn planttraitretrievalfromhyperspectraldatacollectiveeffortsinscientificdatacurationoutperformsimulateddataderivedfromtheprosailmodel