date: 2021-01-17T11:41:50Z
pdf:PDFVersion: 1.7
pdf:docinfo:title: Exploring the Suitability of UAS-Based Multispectral Images for Estimating Soil Organic Carbon: Comparison with Proximal Soil Sensing and Spaceborne Imagery
xmp:CreatorTool: LaTeX with hyperref
Keywords: soil organic carbon; proximal soil sensing; remote sensing multispectral sensors; agricultural soil; spectral indices
access_permission:modify_annotations: true
access_permission:can_print_degraded: true
subject: Soil organic carbon (SOC) is a variable of vital environmental significance in terms of soil quality and function, global food security, and climate change mitigation. Estimation of its content and prediction accuracy on a broader scale remain crucial. Although, spectroscopy under proximal sensing remains one of the best approaches to accurately predict SOC, however, spectroscopy limitation to estimate SOC on a larger spatial scale remains a concern. Therefore, for an efficient quantification of SOC content, faster and less costly techniques are needed, recent studies have suggested the use of remote sensing approaches. The primary aim of this research was to evaluate and compare the capabilities of small Unmanned Aircraft Systems (UAS) for monitoring and estimation of SOC with those obtained from spaceborne (Sentinel-2) and proximal soil sensing (field spectroscopy measurements) on an agricultural field low in SOC content. Nine calculated spectral indices were added to the remote sensing approaches (UAS and Sentinel-2) to enhance their predictive accuracy. Modeling was carried out using various bands/wavelength (UAS (6), Sentinel-2 (9)) and the calculated spectral indices were used as independent variables to generate soil prediction models using five-fold cross-validation built using random forest (RF) and support vector machine regression (SVMR). The correlation regarding SOC and the selected indices and bands/wavelengths was determined prior to the prediction. Our results revealed that the selected spectral indices slightly influenced the output of UAS compared to Sentinel-2 dataset as the latter had only one index correlated with SOC. For prediction, the models built on UAS data had a better accuracy with RF than the two other data used. However, using SVMR, the field spectral prediction models achieved a better overall result for the entire study (log(1/R), RPD = 1.40; R2CV = 0.48; RPIQ = 1.65; RMSEPCV = 0.24), followed by UAS and then Sentinel-2, respectively. This study has shown that UAS imagery can be exploited efficiently using spectral indices.
dc:creator: James Kobina Mensah Biney, Mohammadmehdi Saberioon, Lubo? Bor?vka, Jakub Hou?ka, Radim Va?át, Prince Chapman Agyeman, João Augusto Coblinski and Ale? Klement
dcterms:created: 2021-01-17T11:32:16Z
Last-Modified: 2021-01-17T11:41:50Z
dcterms:modified: 2021-01-17T11:41:50Z
dc:format: application/pdf; version=1.7
title: Exploring the Suitability of UAS-Based Multispectral Images for Estimating Soil Organic Carbon: Comparison with Proximal Soil Sensing and Spaceborne Imagery
Last-Save-Date: 2021-01-17T11:41:50Z
pdf:docinfo:creator_tool: LaTeX with hyperref
access_permission:fill_in_form: true
pdf:docinfo:keywords: soil organic carbon; proximal soil sensing; remote sensing multispectral sensors; agricultural soil; spectral indices
pdf:docinfo:modified: 2021-01-17T11:41:50Z
meta:save-date: 2021-01-17T11:41:50Z
pdf:encrypted: false
dc:title: Exploring the Suitability of UAS-Based Multispectral Images for Estimating Soil Organic Carbon: Comparison with Proximal Soil Sensing and Spaceborne Imagery
modified: 2021-01-17T11:41:50Z
cp:subject: Soil organic carbon (SOC) is a variable of vital environmental significance in terms of soil quality and function, global food security, and climate change mitigation. Estimation of its content and prediction accuracy on a broader scale remain crucial. Although, spectroscopy under proximal sensing remains one of the best approaches to accurately predict SOC, however, spectroscopy limitation to estimate SOC on a larger spatial scale remains a concern. Therefore, for an efficient quantification of SOC content, faster and less costly techniques are needed, recent studies have suggested the use of remote sensing approaches. The primary aim of this research was to evaluate and compare the capabilities of small Unmanned Aircraft Systems (UAS) for monitoring and estimation of SOC with those obtained from spaceborne (Sentinel-2) and proximal soil sensing (field spectroscopy measurements) on an agricultural field low in SOC content. Nine calculated spectral indices were added to the remote sensing approaches (UAS and Sentinel-2) to enhance their predictive accuracy. Modeling was carried out using various bands/wavelength (UAS (6), Sentinel-2 (9)) and the calculated spectral indices were used as independent variables to generate soil prediction models using five-fold cross-validation built using random forest (RF) and support vector machine regression (SVMR). The correlation regarding SOC and the selected indices and bands/wavelengths was determined prior to the prediction. Our results revealed that the selected spectral indices slightly influenced the output of UAS compared to Sentinel-2 dataset as the latter had only one index correlated with SOC. For prediction, the models built on UAS data had a better accuracy with RF than the two other data used. However, using SVMR, the field spectral prediction models achieved a better overall result for the entire study (log(1/R), RPD = 1.40; R2CV = 0.48; RPIQ = 1.65; RMSEPCV = 0.24), followed by UAS and then Sentinel-2, respectively. This study has shown that UAS imagery can be exploited efficiently using spectral indices.
pdf:docinfo:subject: Soil organic carbon (SOC) is a variable of vital environmental significance in terms of soil quality and function, global food security, and climate change mitigation. Estimation of its content and prediction accuracy on a broader scale remain crucial. Although, spectroscopy under proximal sensing remains one of the best approaches to accurately predict SOC, however, spectroscopy limitation to estimate SOC on a larger spatial scale remains a concern. Therefore, for an efficient quantification of SOC content, faster and less costly techniques are needed, recent studies have suggested the use of remote sensing approaches. The primary aim of this research was to evaluate and compare the capabilities of small Unmanned Aircraft Systems (UAS) for monitoring and estimation of SOC with those obtained from spaceborne (Sentinel-2) and proximal soil sensing (field spectroscopy measurements) on an agricultural field low in SOC content. Nine calculated spectral indices were added to the remote sensing approaches (UAS and Sentinel-2) to enhance their predictive accuracy. Modeling was carried out using various bands/wavelength (UAS (6), Sentinel-2 (9)) and the calculated spectral indices were used as independent variables to generate soil prediction models using five-fold cross-validation built using random forest (RF) and support vector machine regression (SVMR). The correlation regarding SOC and the selected indices and bands/wavelengths was determined prior to the prediction. Our results revealed that the selected spectral indices slightly influenced the output of UAS compared to Sentinel-2 dataset as the latter had only one index correlated with SOC. For prediction, the models built on UAS data had a better accuracy with RF than the two other data used. However, using SVMR, the field spectral prediction models achieved a better overall result for the entire study (log(1/R), RPD = 1.40; R2CV = 0.48; RPIQ = 1.65; RMSEPCV = 0.24), followed by UAS and then Sentinel-2, respectively. This study has shown that UAS imagery can be exploited efficiently using spectral indices.
Content-Type: application/pdf
pdf:docinfo:creator: James Kobina Mensah Biney, Mohammadmehdi Saberioon, Lubo? Bor?vka, Jakub Hou?ka, Radim Va?át, Prince Chapman Agyeman, João Augusto Coblinski and Ale? Klement
X-Parsed-By: org.apache.tika.parser.DefaultParser
creator: James Kobina Mensah Biney, Mohammadmehdi Saberioon, Lubo? Bor?vka, Jakub Hou?ka, Radim Va?át, Prince Chapman Agyeman, João Augusto Coblinski and Ale? Klement
meta:author: James Kobina Mensah Biney, Mohammadmehdi Saberioon, Lubo? Bor?vka, Jakub Hou?ka, Radim Va?át, Prince Chapman Agyeman, João Augusto Coblinski and Ale? Klement
dc:subject: soil organic carbon; proximal soil sensing; remote sensing multispectral sensors; agricultural soil; spectral indices
meta:creation-date: 2021-01-17T11:32:16Z
created: Sun Jan 17 12:32:16 CET 2021
access_permission:extract_for_accessibility: true
access_permission:assemble_document: true
xmpTPg:NPages: 19
Creation-Date: 2021-01-17T11:32:16Z
access_permission:extract_content: true
access_permission:can_print: true
meta:keyword: soil organic carbon; proximal soil sensing; remote sensing multispectral sensors; agricultural soil; spectral indices
Author: James Kobina Mensah Biney, Mohammadmehdi Saberioon, Lubo? Bor?vka, Jakub Hou?ka, Radim Va?át, Prince Chapman Agyeman, João Augusto Coblinski and Ale? Klement
producer: pdfTeX-1.40.21
access_permission:can_modify: true
pdf:docinfo:producer: pdfTeX-1.40.21
pdf:docinfo:created: 2021-01-17T11:32:16Z