Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

PROSPECT-GPR : Exploring spectral associations among vegetation traits in wavelength selection for leaf mass per area and water contents

He, Chunmei ; Sun, Jia ; Chen, Yuwen ; Wang, Lunche ; Shi, Shuo ; Qiu, Feng ; Wang, Shaoqiang ; Yang, Jian and Tagesson, Torbern LU (2023) In Science of Remote Sensing 8.
Abstract

Leaf mass per area (LMA) and equivalent water thickness (EWT) are key indicators providing information on plant growth status and agricultural management, and their retrieval is commonly done through radiative transfer models (RTMs) such as the PROSPECT model. However, the PROSPECT model is frequently hampered by the ill-posed problem as a consequence of measurement and model uncertainties. Here, we propose a wavelength selection method to improve the inversion of EWT and LMA by integrating PROSPECT with a machine learning algorithm (Gaussian process regression (GPR); PROSPECT-GPR for short). The GPR model conducted sorting of wavelengths and the PROSPECT-D was used to determine the optimal number of characteristic wavelengths. The... (More)

Leaf mass per area (LMA) and equivalent water thickness (EWT) are key indicators providing information on plant growth status and agricultural management, and their retrieval is commonly done through radiative transfer models (RTMs) such as the PROSPECT model. However, the PROSPECT model is frequently hampered by the ill-posed problem as a consequence of measurement and model uncertainties. Here, we propose a wavelength selection method to improve the inversion of EWT and LMA by integrating PROSPECT with a machine learning algorithm (Gaussian process regression (GPR); PROSPECT-GPR for short). The GPR model conducted sorting of wavelengths and the PROSPECT-D was used to determine the optimal number of characteristic wavelengths. The results demonstrated that the estimation of EWT (R2 = 0.80; RMSE = 0.0021) and LMA (R2 = 0.71; RMSE = 0.0021) using the proposed wavelengths and PROSPECT inversion all exhibited superior accuracy in comparison with those from previous studies. The efficacy of PROSPECT-GPR in exploring the spectral linkage among vegetation traits was demonstrated by selecting wavelengths associated with leaf structure parameter N and EWT (1368 nm) that turn out to contribute to the estimation of LMA. The findings lay a strong foundation for understanding the spectral linkage among vegetation traits, and the proposed wavelength selection method provides valuable insights for selecting informative spectral wavelengths for RTMs inversion and designing future remote sensors.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Gaussian process regression, Leaf mass per area, Leaf water content, PROSPECT model, Wavelength selection
in
Science of Remote Sensing
volume
8
article number
100100
publisher
Elsevier
external identifiers
  • scopus:85171143663
ISSN
2666-0172
DOI
10.1016/j.srs.2023.100100
language
English
LU publication?
yes
id
51e1090f-6815-441c-9f04-80625344240e
date added to LUP
2023-12-05 14:49:55
date last changed
2023-12-05 14:49:55
@article{51e1090f-6815-441c-9f04-80625344240e,
  abstract     = {{<p>Leaf mass per area (LMA) and equivalent water thickness (EWT) are key indicators providing information on plant growth status and agricultural management, and their retrieval is commonly done through radiative transfer models (RTMs) such as the PROSPECT model. However, the PROSPECT model is frequently hampered by the ill-posed problem as a consequence of measurement and model uncertainties. Here, we propose a wavelength selection method to improve the inversion of EWT and LMA by integrating PROSPECT with a machine learning algorithm (Gaussian process regression (GPR); PROSPECT-GPR for short). The GPR model conducted sorting of wavelengths and the PROSPECT-D was used to determine the optimal number of characteristic wavelengths. The results demonstrated that the estimation of EWT (R<sup>2</sup> = 0.80; RMSE = 0.0021) and LMA (R<sup>2</sup> = 0.71; RMSE = 0.0021) using the proposed wavelengths and PROSPECT inversion all exhibited superior accuracy in comparison with those from previous studies. The efficacy of PROSPECT-GPR in exploring the spectral linkage among vegetation traits was demonstrated by selecting wavelengths associated with leaf structure parameter N and EWT (1368 nm) that turn out to contribute to the estimation of LMA. The findings lay a strong foundation for understanding the spectral linkage among vegetation traits, and the proposed wavelength selection method provides valuable insights for selecting informative spectral wavelengths for RTMs inversion and designing future remote sensors.</p>}},
  author       = {{He, Chunmei and Sun, Jia and Chen, Yuwen and Wang, Lunche and Shi, Shuo and Qiu, Feng and Wang, Shaoqiang and Yang, Jian and Tagesson, Torbern}},
  issn         = {{2666-0172}},
  keywords     = {{Gaussian process regression; Leaf mass per area; Leaf water content; PROSPECT model; Wavelength selection}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{Science of Remote Sensing}},
  title        = {{PROSPECT-GPR : Exploring spectral associations among vegetation traits in wavelength selection for leaf mass per area and water contents}},
  url          = {{http://dx.doi.org/10.1016/j.srs.2023.100100}},
  doi          = {{10.1016/j.srs.2023.100100}},
  volume       = {{8}},
  year         = {{2023}},
}