Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation

Soils serve as critical carbon reservoirs, playing an essential role in climate change mitigation and agricultural sustainability. Accurate soil property determination relies on soil spectral reflectance data from Earth observation (EO), but current vegetation models often oversimplify soil conditio...

Full description

Saved in:
Bibliographic Details
Main Authors: Asmaa Abdelbaki, Robert Milewski, Mohammadmehdi Saberioon, Katja Berger, José A. M. Demattê, Sabine Chabrillat
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/14/2355
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850072139064934400
author Asmaa Abdelbaki
Robert Milewski
Mohammadmehdi Saberioon
Katja Berger
José A. M. Demattê
Sabine Chabrillat
author_facet Asmaa Abdelbaki
Robert Milewski
Mohammadmehdi Saberioon
Katja Berger
José A. M. Demattê
Sabine Chabrillat
author_sort Asmaa Abdelbaki
collection DOAJ
description Soils serve as critical carbon reservoirs, playing an essential role in climate change mitigation and agricultural sustainability. Accurate soil property determination relies on soil spectral reflectance data from Earth observation (EO), but current vegetation models often oversimplify soil conditions. This study introduces a novel approach that combines radiative transfer models (RTMs) with open-access soil spectral libraries to address this challenge. Focusing on conditions of low soil moisture content (SMC), photosynthetic vegetation (PV), and non-photosynthetic vegetation (NPV), the coupled Marmit–Leaf–Canopy (MLC) model is used to simulate early crop growth stages. The MLC model, which integrates MARMIT and PRO4SAIL2, enables the generation of mixed soil–vegetation scenarios. A simulated EO disturbed soil spectral library (DSSL) was created, significantly expanding the EU LUCAS cropland soil spectral library. A 1D convolutional neural network (1D-CNN) was trained on this database to predict Soil Organic Carbon (SOC) content. The results demonstrated relatively high SOC prediction accuracy compared to previous approaches that rely only on RTMs and/or machine learning approaches. Incorporating soil moisture content significantly improved performance over bare soil alone, yielding an R<sup>2</sup> of 0.86 and RMSE of 4.05 g/kg, compared to R<sup>2</sup> = 0.71 and RMSE = 6.01 g/kg for bare soil. Adding PV slightly reduced accuracy (R<sup>2</sup> = 0.71, RMSE = 6.31 g/kg), while the inclusion of NPV alongside moisture led to modest improvement (R<sup>2</sup> = 0.74, RMSE = 5.84 g/kg). The most comprehensive model, incorporating bare soil, SMC, PV, and NPV, achieved a balanced performance (R<sup>2</sup> = 0.76, RMSE = 5.49 g/kg), highlighting the importance of accounting for all surface components in SOC estimation. While further validation with additional scenarios and SOC prediction methods is needed, these findings demonstrate, for the first time, using radiative-transfer simulations of mixed vegetation-soil-water environments, that an EO-DSSL approach enhances machine learning-based SOC modeling from EO data, improving SOC mapping accuracy. This innovative framework could significantly improve global-scale SOC predictions, supporting the design of next-generation EO products for more accurate carbon monitoring.
format Article
id doaj-art-c8ec02b13ded461995474a620352a415
institution DOAJ
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-c8ec02b13ded461995474a620352a4152025-08-20T02:47:09ZengMDPI AGRemote Sensing2072-42922025-07-011714235510.3390/rs17142355Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon EstimationAsmaa Abdelbaki0Robert Milewski1Mohammadmehdi Saberioon2Katja Berger3José A. M. Demattê4Sabine Chabrillat5GFZ Helmholtz Centre for Geosciences, Telegrafenberg, 14473 Potsdam, GermanyGFZ Helmholtz Centre for Geosciences, Telegrafenberg, 14473 Potsdam, GermanyGFZ Helmholtz Centre for Geosciences, Telegrafenberg, 14473 Potsdam, GermanyGFZ Helmholtz Centre for Geosciences, Telegrafenberg, 14473 Potsdam, GermanyDepartment of Soil Science, Luiz de Queiroz College of Agriculture, University of São Paulo (ESALQ/USP), Av. Pádua Dias 11, CP9, Piracicaba 13418-900, SP, BrazilGFZ Helmholtz Centre for Geosciences, Telegrafenberg, 14473 Potsdam, GermanySoils serve as critical carbon reservoirs, playing an essential role in climate change mitigation and agricultural sustainability. Accurate soil property determination relies on soil spectral reflectance data from Earth observation (EO), but current vegetation models often oversimplify soil conditions. This study introduces a novel approach that combines radiative transfer models (RTMs) with open-access soil spectral libraries to address this challenge. Focusing on conditions of low soil moisture content (SMC), photosynthetic vegetation (PV), and non-photosynthetic vegetation (NPV), the coupled Marmit–Leaf–Canopy (MLC) model is used to simulate early crop growth stages. The MLC model, which integrates MARMIT and PRO4SAIL2, enables the generation of mixed soil–vegetation scenarios. A simulated EO disturbed soil spectral library (DSSL) was created, significantly expanding the EU LUCAS cropland soil spectral library. A 1D convolutional neural network (1D-CNN) was trained on this database to predict Soil Organic Carbon (SOC) content. The results demonstrated relatively high SOC prediction accuracy compared to previous approaches that rely only on RTMs and/or machine learning approaches. Incorporating soil moisture content significantly improved performance over bare soil alone, yielding an R<sup>2</sup> of 0.86 and RMSE of 4.05 g/kg, compared to R<sup>2</sup> = 0.71 and RMSE = 6.01 g/kg for bare soil. Adding PV slightly reduced accuracy (R<sup>2</sup> = 0.71, RMSE = 6.31 g/kg), while the inclusion of NPV alongside moisture led to modest improvement (R<sup>2</sup> = 0.74, RMSE = 5.84 g/kg). The most comprehensive model, incorporating bare soil, SMC, PV, and NPV, achieved a balanced performance (R<sup>2</sup> = 0.76, RMSE = 5.49 g/kg), highlighting the importance of accounting for all surface components in SOC estimation. While further validation with additional scenarios and SOC prediction methods is needed, these findings demonstrate, for the first time, using radiative-transfer simulations of mixed vegetation-soil-water environments, that an EO-DSSL approach enhances machine learning-based SOC modeling from EO data, improving SOC mapping accuracy. This innovative framework could significantly improve global-scale SOC predictions, supporting the design of next-generation EO products for more accurate carbon monitoring.https://www.mdpi.com/2072-4292/17/14/2355soil spectroscopyMARMITPROSPECT4SAIL2convolutional neural network (CNN)hybrid inversion modelLUCAS-SSL data
spellingShingle Asmaa Abdelbaki
Robert Milewski
Mohammadmehdi Saberioon
Katja Berger
José A. M. Demattê
Sabine Chabrillat
Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation
Remote Sensing
soil spectroscopy
MARMIT
PROSPECT4SAIL2
convolutional neural network (CNN)
hybrid inversion model
LUCAS-SSL data
title Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation
title_full Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation
title_fullStr Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation
title_full_unstemmed Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation
title_short Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation
title_sort radiative transfer model integrated approach for hyperspectral simulation of mixed soil vegetation scenarios and soil organic carbon estimation
topic soil spectroscopy
MARMIT
PROSPECT4SAIL2
convolutional neural network (CNN)
hybrid inversion model
LUCAS-SSL data
url https://www.mdpi.com/2072-4292/17/14/2355
work_keys_str_mv AT asmaaabdelbaki radiativetransfermodelintegratedapproachforhyperspectralsimulationofmixedsoilvegetationscenariosandsoilorganiccarbonestimation
AT robertmilewski radiativetransfermodelintegratedapproachforhyperspectralsimulationofmixedsoilvegetationscenariosandsoilorganiccarbonestimation
AT mohammadmehdisaberioon radiativetransfermodelintegratedapproachforhyperspectralsimulationofmixedsoilvegetationscenariosandsoilorganiccarbonestimation
AT katjaberger radiativetransfermodelintegratedapproachforhyperspectralsimulationofmixedsoilvegetationscenariosandsoilorganiccarbonestimation
AT joseamdematte radiativetransfermodelintegratedapproachforhyperspectralsimulationofmixedsoilvegetationscenariosandsoilorganiccarbonestimation
AT sabinechabrillat radiativetransfermodelintegratedapproachforhyperspectralsimulationofmixedsoilvegetationscenariosandsoilorganiccarbonestimation