date: 2024-03-29T13:57:38Z
pdf:PDFVersion: 1.7
pdf:docinfo:title: Gaussian Process Regression Hybrid Models for the Top-of-Atmosphere Retrieval of Vegetation Traits Applied to PRISMA and EnMAP Imagery
xmp:CreatorTool: LaTeX with hyperref
Keywords: top-of-atmosphere; atmospheric correction; machine learning models; Gaussian processes; radiative transfer model; SCOPE; PRISMA; EnMAp
access_permission:modify_annotations: true
access_permission:can_print_degraded: true
subject: The continuous monitoring of the terrestrial Earth system by a growing number of optical satellite missions provides valuable insights into vegetation and cropland characteristics. Satellite missions typically provide different levels of data, such as level 1 top-of-atmosphere (TOA) radiance and level 2 bottom-of-atmosphere (BOA) reflectance products. Exploiting TOA radiance data directly offers the advantage of bypassing the complex atmospheric correction step, where errors can propagate and compromise the subsequent retrieval process. Therefore, the objective of our study was to develop models capable of retrieving vegetation traits directly from TOA radiance data from imaging spectroscopy satellite missions. To achieve this, we constructed hybrid models based on radiative transfer model (RTM) simulated data, thereby employing the vegetation SCOPE RTM coupled with the atmosphere LibRadtran RTM in conjunction with Gaussian process regression (GPR). The retrieval evaluation focused on vegetation canopy traits, including the leaf area index (LAI), canopy chlorophyll content (CCC), canopy water content (CWC), the fraction of absorbed photosynthetically active radiation (FAPAR), and the fraction of vegetation cover (FVC). Employing band settings from the upcoming Copernicus Hyperspectral Imaging Mission (CHIME), two types of hybrid GPR models were assessed: (1) one trained at level 1 (L1) using TOA radiance data and (2) one trained at level 2 (L2) using BOA reflectance data. Both the TOA- and BOA-based GPR models were validated against in situ data with corresponding hyperspectral data obtained from field campaigns. The TOA-based hybrid GPR models revealed a range of performance from moderate to optimal results, thus reaching R2 = 0.92 (LAI), R2 = 0.72 (CCC) and 0.68 (CWC), R2 = 0.94 (FAPAR), and R2 = 0.95 (FVC). To demonstrate the models' applicability, the TOA- and BOA-based GPR models were subsequently applied to imagery from the scientific precursor missions PRISMA and EnMAP. The resulting trait maps showed sufficient consistency between the TOA- and BOA-based models, with relative errors between 4% and 16% (R2 between 0.68 and 0.97). Altogether, these findings illuminate the path for the development and enhancement of machine learning hybrid models for the estimation of vegetation traits directly tailored at the TOA level. 
dc:creator: Ana B. Pascual-Venteo, Jose L. Garcia, Katja Berger, José Estévez, Jorge Vicent, Adrián Pérez-Suay, Shari Van Wittenberghe and Jochem Verrelst
dcterms:created: 2024-03-29T13:46:59Z
Last-Modified: 2024-03-29T13:57:38Z
dcterms:modified: 2024-03-29T13:57:38Z
dc:format: application/pdf; version=1.7
title: Gaussian Process Regression Hybrid Models for the Top-of-Atmosphere Retrieval of Vegetation Traits Applied to PRISMA and EnMAP Imagery
Last-Save-Date: 2024-03-29T13:57:38Z
pdf:docinfo:creator_tool: LaTeX with hyperref
access_permission:fill_in_form: true
pdf:docinfo:keywords: top-of-atmosphere; atmospheric correction; machine learning models; Gaussian processes; radiative transfer model; SCOPE; PRISMA; EnMAp
pdf:docinfo:modified: 2024-03-29T13:57:38Z
meta:save-date: 2024-03-29T13:57:38Z
pdf:encrypted: false
dc:title: Gaussian Process Regression Hybrid Models for the Top-of-Atmosphere Retrieval of Vegetation Traits Applied to PRISMA and EnMAP Imagery
modified: 2024-03-29T13:57:38Z
cp:subject: The continuous monitoring of the terrestrial Earth system by a growing number of optical satellite missions provides valuable insights into vegetation and cropland characteristics. Satellite missions typically provide different levels of data, such as level 1 top-of-atmosphere (TOA) radiance and level 2 bottom-of-atmosphere (BOA) reflectance products. Exploiting TOA radiance data directly offers the advantage of bypassing the complex atmospheric correction step, where errors can propagate and compromise the subsequent retrieval process. Therefore, the objective of our study was to develop models capable of retrieving vegetation traits directly from TOA radiance data from imaging spectroscopy satellite missions. To achieve this, we constructed hybrid models based on radiative transfer model (RTM) simulated data, thereby employing the vegetation SCOPE RTM coupled with the atmosphere LibRadtran RTM in conjunction with Gaussian process regression (GPR). The retrieval evaluation focused on vegetation canopy traits, including the leaf area index (LAI), canopy chlorophyll content (CCC), canopy water content (CWC), the fraction of absorbed photosynthetically active radiation (FAPAR), and the fraction of vegetation cover (FVC). Employing band settings from the upcoming Copernicus Hyperspectral Imaging Mission (CHIME), two types of hybrid GPR models were assessed: (1) one trained at level 1 (L1) using TOA radiance data and (2) one trained at level 2 (L2) using BOA reflectance data. Both the TOA- and BOA-based GPR models were validated against in situ data with corresponding hyperspectral data obtained from field campaigns. The TOA-based hybrid GPR models revealed a range of performance from moderate to optimal results, thus reaching R2 = 0.92 (LAI), R2 = 0.72 (CCC) and 0.68 (CWC), R2 = 0.94 (FAPAR), and R2 = 0.95 (FVC). To demonstrate the models' applicability, the TOA- and BOA-based GPR models were subsequently applied to imagery from the scientific precursor missions PRISMA and EnMAP. The resulting trait maps showed sufficient consistency between the TOA- and BOA-based models, with relative errors between 4% and 16% (R2 between 0.68 and 0.97). Altogether, these findings illuminate the path for the development and enhancement of machine learning hybrid models for the estimation of vegetation traits directly tailored at the TOA level. 
pdf:docinfo:subject: The continuous monitoring of the terrestrial Earth system by a growing number of optical satellite missions provides valuable insights into vegetation and cropland characteristics. Satellite missions typically provide different levels of data, such as level 1 top-of-atmosphere (TOA) radiance and level 2 bottom-of-atmosphere (BOA) reflectance products. Exploiting TOA radiance data directly offers the advantage of bypassing the complex atmospheric correction step, where errors can propagate and compromise the subsequent retrieval process. Therefore, the objective of our study was to develop models capable of retrieving vegetation traits directly from TOA radiance data from imaging spectroscopy satellite missions. To achieve this, we constructed hybrid models based on radiative transfer model (RTM) simulated data, thereby employing the vegetation SCOPE RTM coupled with the atmosphere LibRadtran RTM in conjunction with Gaussian process regression (GPR). The retrieval evaluation focused on vegetation canopy traits, including the leaf area index (LAI), canopy chlorophyll content (CCC), canopy water content (CWC), the fraction of absorbed photosynthetically active radiation (FAPAR), and the fraction of vegetation cover (FVC). Employing band settings from the upcoming Copernicus Hyperspectral Imaging Mission (CHIME), two types of hybrid GPR models were assessed: (1) one trained at level 1 (L1) using TOA radiance data and (2) one trained at level 2 (L2) using BOA reflectance data. Both the TOA- and BOA-based GPR models were validated against in situ data with corresponding hyperspectral data obtained from field campaigns. The TOA-based hybrid GPR models revealed a range of performance from moderate to optimal results, thus reaching R2 = 0.92 (LAI), R2 = 0.72 (CCC) and 0.68 (CWC), R2 = 0.94 (FAPAR), and R2 = 0.95 (FVC). To demonstrate the models' applicability, the TOA- and BOA-based GPR models were subsequently applied to imagery from the scientific precursor missions PRISMA and EnMAP. The resulting trait maps showed sufficient consistency between the TOA- and BOA-based models, with relative errors between 4% and 16% (R2 between 0.68 and 0.97). Altogether, these findings illuminate the path for the development and enhancement of machine learning hybrid models for the estimation of vegetation traits directly tailored at the TOA level. 
Content-Type: application/pdf
pdf:docinfo:creator: Ana B. Pascual-Venteo, Jose L. Garcia, Katja Berger, José Estévez, Jorge Vicent, Adrián Pérez-Suay, Shari Van Wittenberghe and Jochem Verrelst
X-Parsed-By: org.apache.tika.parser.DefaultParser
creator: Ana B. Pascual-Venteo, Jose L. Garcia, Katja Berger, José Estévez, Jorge Vicent, Adrián Pérez-Suay, Shari Van Wittenberghe and Jochem Verrelst
meta:author: Ana B. Pascual-Venteo, Jose L. Garcia, Katja Berger, José Estévez, Jorge Vicent, Adrián Pérez-Suay, Shari Van Wittenberghe and Jochem Verrelst
dc:subject: top-of-atmosphere; atmospheric correction; machine learning models; Gaussian processes; radiative transfer model; SCOPE; PRISMA; EnMAp
meta:creation-date: 2024-03-29T13:46:59Z
created: Fri Mar 29 14:46:59 CET 2024
access_permission:extract_for_accessibility: true
access_permission:assemble_document: true
xmpTPg:NPages: 27
Creation-Date: 2024-03-29T13:46:59Z
access_permission:extract_content: true
access_permission:can_print: true
meta:keyword: top-of-atmosphere; atmospheric correction; machine learning models; Gaussian processes; radiative transfer model; SCOPE; PRISMA; EnMAp
Author: Ana B. Pascual-Venteo, Jose L. Garcia, Katja Berger, José Estévez, Jorge Vicent, Adrián Pérez-Suay, Shari Van Wittenberghe and Jochem Verrelst
producer: pdfTeX-1.40.25
access_permission:can_modify: true
pdf:docinfo:producer: pdfTeX-1.40.25
pdf:docinfo:created: 2024-03-29T13:46:59Z