Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery

Non-photosynthetic vegetation (NPV) biomass has been identified as a priority variable for upcoming spaceborne imaging spectroscopy missions, calling for a quantitative estimation of lignocellulosic plant material as opposed to the sole indication of surface coverage. Therefore, we propose a hybrid...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Katja Berger, Tobias Hank, Andrej Halabuk, Juan Pablo Rivera-Caicedo, Matthias Wocher, Matej Mojses, Katarina Gerhátová, Giulia Tagliabue, Miguel Morata Dolz, Ana Belen Pascual Venteo, Jochem Verrelst
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	PRISMA CHIME NPV Gaussian process regression hybrid retrieval active learning Science Q
Acceso en línea:	https://doaj.org/article/b67b72b2c2b04aa3b26cbc5ac254af74
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b67b72b2c2b04aa3b26cbc5ac254af74
record_format	dspace
spelling	oai:doaj.org-article:b67b72b2c2b04aa3b26cbc5ac254af742021-11-25T18:55:39ZAssessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery10.3390/rs132247112072-4292https://doaj.org/article/b67b72b2c2b04aa3b26cbc5ac254af742021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4711https://doaj.org/toc/2072-4292Non-photosynthetic vegetation (NPV) biomass has been identified as a priority variable for upcoming spaceborne imaging spectroscopy missions, calling for a quantitative estimation of lignocellulosic plant material as opposed to the sole indication of surface coverage. Therefore, we propose a hybrid model for the retrieval of non-photosynthetic cropland biomass. The workflow included coupling the leaf optical model PROSPECT-PRO with the canopy reflectance model 4SAIL, which allowed us to simulate NPV biomass from carbon-based constituents (CBC) and leaf area index (LAI). PROSAIL-PRO provided a training database for a Gaussian process regression (GPR) algorithm, simulating a wide range of non-photosynthetic vegetation states. Active learning was employed to reduce and optimize the training data set. In addition, we applied spectral dimensionality reduction to condense essential information of non-photosynthetic signals. The resulting NPV-GPR model was successfully validated against soybean field data with normalized root mean square error (nRMSE) of 13.4% and a coefficient of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>) of 0.85. To demonstrate mapping capability, the NPV-GPR model was tested on a PRISMA hyperspectral image acquired over agricultural areas in the North of Munich, Germany. Reliable estimates were mainly achieved over senescent vegetation areas as suggested by model uncertainties. The proposed workflow is the first step towards the quantification of non-photosynthetic cropland biomass as a next-generation product from near-term operational missions, such as CHIME.Katja BergerTobias HankAndrej HalabukJuan Pablo Rivera-CaicedoMatthias WocherMatej MojsesKatarina GerhátováGiulia TagliabueMiguel Morata DolzAna Belen Pascual VenteoJochem VerrelstMDPI AGarticlePRISMACHIMENPVGaussian process regressionhybrid retrievalactive learningScienceQENRemote Sensing, Vol 13, Iss 4711, p 4711 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	PRISMA CHIME NPV Gaussian process regression hybrid retrieval active learning Science Q
spellingShingle	PRISMA CHIME NPV Gaussian process regression hybrid retrieval active learning Science Q Katja Berger Tobias Hank Andrej Halabuk Juan Pablo Rivera-Caicedo Matthias Wocher Matej Mojses Katarina Gerhátová Giulia Tagliabue Miguel Morata Dolz Ana Belen Pascual Venteo Jochem Verrelst Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery
description	Non-photosynthetic vegetation (NPV) biomass has been identified as a priority variable for upcoming spaceborne imaging spectroscopy missions, calling for a quantitative estimation of lignocellulosic plant material as opposed to the sole indication of surface coverage. Therefore, we propose a hybrid model for the retrieval of non-photosynthetic cropland biomass. The workflow included coupling the leaf optical model PROSPECT-PRO with the canopy reflectance model 4SAIL, which allowed us to simulate NPV biomass from carbon-based constituents (CBC) and leaf area index (LAI). PROSAIL-PRO provided a training database for a Gaussian process regression (GPR) algorithm, simulating a wide range of non-photosynthetic vegetation states. Active learning was employed to reduce and optimize the training data set. In addition, we applied spectral dimensionality reduction to condense essential information of non-photosynthetic signals. The resulting NPV-GPR model was successfully validated against soybean field data with normalized root mean square error (nRMSE) of 13.4% and a coefficient of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>) of 0.85. To demonstrate mapping capability, the NPV-GPR model was tested on a PRISMA hyperspectral image acquired over agricultural areas in the North of Munich, Germany. Reliable estimates were mainly achieved over senescent vegetation areas as suggested by model uncertainties. The proposed workflow is the first step towards the quantification of non-photosynthetic cropland biomass as a next-generation product from near-term operational missions, such as CHIME.
format	article
author	Katja Berger Tobias Hank Andrej Halabuk Juan Pablo Rivera-Caicedo Matthias Wocher Matej Mojses Katarina Gerhátová Giulia Tagliabue Miguel Morata Dolz Ana Belen Pascual Venteo Jochem Verrelst
author_facet	Katja Berger Tobias Hank Andrej Halabuk Juan Pablo Rivera-Caicedo Matthias Wocher Matej Mojses Katarina Gerhátová Giulia Tagliabue Miguel Morata Dolz Ana Belen Pascual Venteo Jochem Verrelst
author_sort	Katja Berger
title	Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery
title_short	Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery
title_full	Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery
title_fullStr	Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery
title_full_unstemmed	Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery
title_sort	assessing non-photosynthetic cropland biomass from spaceborne hyperspectral imagery
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b67b72b2c2b04aa3b26cbc5ac254af74
work_keys_str_mv	AT katjaberger assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT tobiashank assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT andrejhalabuk assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT juanpabloriveracaicedo assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT matthiaswocher assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT matejmojses assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT katarinagerhatova assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT giuliatagliabue assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT miguelmoratadolz assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT anabelenpascualventeo assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery AT jochemverrelst assessingnonphotosyntheticcroplandbiomassfromspacebornehyperspectralimagery
_version_	1718410548248313856

Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery

Ejemplares similares