Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer

The retrieval of sun-induced fluorescence (SIF) from hyperspectral radiance data grew to maturity with research activities around the FLuorescence EXplorer satellite mission FLEX, yet full-spectrum estimation methods such as the spectral fitting method (SFM) are computationally expensive. To bypass...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Miguel Morata, Bastian Siegmann, Pablo Morcillo-Pallarés, Juan Pablo Rivera-Caicedo, Jochem Verrelst
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	emulation machine learning sun-induced fluorescence sif spectral fitting method (sfm) principal component analysis Science Q
Acceso en línea:	https://doaj.org/article/605ddd76692a4eaba0afed9a6c56c5bf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:605ddd76692a4eaba0afed9a6c56c5bf
record_format	dspace
spelling	oai:doaj.org-article:605ddd76692a4eaba0afed9a6c56c5bf2021-11-11T18:54:50ZEmulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer10.3390/rs132143682072-4292https://doaj.org/article/605ddd76692a4eaba0afed9a6c56c5bf2021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4368https://doaj.org/toc/2072-4292The retrieval of sun-induced fluorescence (SIF) from hyperspectral radiance data grew to maturity with research activities around the FLuorescence EXplorer satellite mission FLEX, yet full-spectrum estimation methods such as the spectral fitting method (SFM) are computationally expensive. To bypass this computational load, this work aims to approximate the SFM-based SIF retrieval by means of statistical learning, i.e., <i>emulation</i>. While emulators emerged as fast surrogate models of simulators, the accuracy-speedup trade-offs are still to be analyzed when the emulation concept is applied to experimental data. We evaluated the possibility of approximating the SFM-like SIF output directly based on radiance data while minimizing the loss in precision as opposed to SFM-based SIF. To do so, we implemented a double principal component analysis (PCA) dimensionality reduction, i.e., in both input and output, to achieve emulation of multispectral SIF output based on hyperspectral radiance data. We then evaluated systematically: (1) multiple machine learning regression algorithms, (2) number of principal components, (3) number of training samples, and (4) quality of training samples. The best performing SIF emulator was then applied to a HyPlant flight line containing at sensor radiance information, and the results were compared to the SFM SIF map of the same flight line. The emulated SIF map was quasi-instantaneously generated, and a good agreement against the reference SFM map was obtained with a <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 0.88 and NRMSE of 3.77%. The SIF emulator was subsequently applied to 7 HyPlant flight lines to evaluate its robustness and portability, leading to a <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> between 0.68 and 0.95, and a NRMSE between 6.42% and 4.13%. Emulated SIF maps proved to be consistent while processing time was in the order of 3 min. In comparison, the original SFM needed approximately 78 min to complete the SIF processing. Our results suggest that emulation can be used to efficiently reduce computational loads of SIF retrieval methods.Miguel MorataBastian SiegmannPablo Morcillo-PallarésJuan Pablo Rivera-CaicedoJochem VerrelstMDPI AGarticleemulationmachine learningsun-induced fluorescencesifspectral fitting method (sfm)principal component analysisScienceQENRemote Sensing, Vol 13, Iss 4368, p 4368 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	emulation machine learning sun-induced fluorescence sif spectral fitting method (sfm) principal component analysis Science Q
spellingShingle	emulation machine learning sun-induced fluorescence sif spectral fitting method (sfm) principal component analysis Science Q Miguel Morata Bastian Siegmann Pablo Morcillo-Pallarés Juan Pablo Rivera-Caicedo Jochem Verrelst Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer
description	The retrieval of sun-induced fluorescence (SIF) from hyperspectral radiance data grew to maturity with research activities around the FLuorescence EXplorer satellite mission FLEX, yet full-spectrum estimation methods such as the spectral fitting method (SFM) are computationally expensive. To bypass this computational load, this work aims to approximate the SFM-based SIF retrieval by means of statistical learning, i.e., <i>emulation</i>. While emulators emerged as fast surrogate models of simulators, the accuracy-speedup trade-offs are still to be analyzed when the emulation concept is applied to experimental data. We evaluated the possibility of approximating the SFM-like SIF output directly based on radiance data while minimizing the loss in precision as opposed to SFM-based SIF. To do so, we implemented a double principal component analysis (PCA) dimensionality reduction, i.e., in both input and output, to achieve emulation of multispectral SIF output based on hyperspectral radiance data. We then evaluated systematically: (1) multiple machine learning regression algorithms, (2) number of principal components, (3) number of training samples, and (4) quality of training samples. The best performing SIF emulator was then applied to a HyPlant flight line containing at sensor radiance information, and the results were compared to the SFM SIF map of the same flight line. The emulated SIF map was quasi-instantaneously generated, and a good agreement against the reference SFM map was obtained with a <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 0.88 and NRMSE of 3.77%. The SIF emulator was subsequently applied to 7 HyPlant flight lines to evaluate its robustness and portability, leading to a <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> between 0.68 and 0.95, and a NRMSE between 6.42% and 4.13%. Emulated SIF maps proved to be consistent while processing time was in the order of 3 min. In comparison, the original SFM needed approximately 78 min to complete the SIF processing. Our results suggest that emulation can be used to efficiently reduce computational loads of SIF retrieval methods.
format	article
author	Miguel Morata Bastian Siegmann Pablo Morcillo-Pallarés Juan Pablo Rivera-Caicedo Jochem Verrelst
author_facet	Miguel Morata Bastian Siegmann Pablo Morcillo-Pallarés Juan Pablo Rivera-Caicedo Jochem Verrelst
author_sort	Miguel Morata
title	Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer
title_short	Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer
title_full	Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer
title_fullStr	Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer
title_full_unstemmed	Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer
title_sort	emulation of sun-induced fluorescence from radiance data recorded by the hyplant airborne imaging spectrometer
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/605ddd76692a4eaba0afed9a6c56c5bf
work_keys_str_mv	AT miguelmorata emulationofsuninducedfluorescencefromradiancedatarecordedbythehyplantairborneimagingspectrometer AT bastiansiegmann emulationofsuninducedfluorescencefromradiancedatarecordedbythehyplantairborneimagingspectrometer AT pablomorcillopallares emulationofsuninducedfluorescencefromradiancedatarecordedbythehyplantairborneimagingspectrometer AT juanpabloriveracaicedo emulationofsuninducedfluorescencefromradiancedatarecordedbythehyplantairborneimagingspectrometer AT jochemverrelst emulationofsuninducedfluorescencefromradiancedatarecordedbythehyplantairborneimagingspectrometer
_version_	1718431648054247424

Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer

Ejemplares similares