Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR Data

Soil organic carbon (SOC) is an essential component for plant growth and a pivotal factor in the global carbon cycle. <italic>Spartina alterniflora</italic> (<italic>S. alterniflora</italic>), an invasive species characterized by high primary productivity and rapid carbon seq...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiannan He, Yongbin Zhang, Mingyue Liu, Lin Chen, Weidong Man, Hua Fang, Xiang Li, Xuan Yin, Jianping Liang, Wenke Bai, Fuping Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10854657/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1823857170524930048
author Jiannan He
Yongbin Zhang
Mingyue Liu
Lin Chen
Weidong Man
Hua Fang
Xiang Li
Xuan Yin
Jianping Liang
Wenke Bai
Fuping Li
author_facet Jiannan He
Yongbin Zhang
Mingyue Liu
Lin Chen
Weidong Man
Hua Fang
Xiang Li
Xuan Yin
Jianping Liang
Wenke Bai
Fuping Li
author_sort Jiannan He
collection DOAJ
description Soil organic carbon (SOC) is an essential component for plant growth and a pivotal factor in the global carbon cycle. <italic>Spartina alterniflora</italic> (<italic>S. alterniflora</italic>), an invasive species characterized by high primary productivity and rapid carbon sequestration capabilities, exerts a substantial impact on SOC concentrations. The precise quantification of SOC content in <italic>S. alterniflora</italic> is extremely importance. Based on 73 measured samples, along with multispectral imagery and LiDAR data collected via unmanned aerial vehicles, machine learning techniques, including random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost), were employed to predict the SOC content of <italic>S. alterniflora</italic> and map its spatial distribution. We compared the predictive performance of these different machine learning algorithms to identify the most effective one. The results show that the following. 1) The prediction accuracy is improved by classifying the data into three types: unlodging <italic>S. alterniflora</italic> (ULSA), lodging <italic>S. alterniflora</italic> (LSA), and mudflats. 2) XGBoost outperformed RF and SVM in accurately predicting SOC content, with <italic>R</italic><sup>2</sup>; values of 0.743 for ULSA, 0.731 for LSA, and 0.705 for mudflats; 3) In the XGBoost models constructed for ULSA, LSA, and mudflats, spectral features contributed 75.7&#x0025;, 73.1&#x0025;, and 63.1&#x0025;, respectively, with the normalized difference vegetation index emerging as the most critical spectral feature. Slope aspect (AS) was identified as the most influential topographic feature. 4) The spatial distribution of SOC exhibited marked heterogeneity, with higher SOC content in ULSA and lower in mudflats, demonstrating a gradient of decreasing SOC content from land to sea. These results hold significant implications for the study of SOC content in <italic>S. alterniflora</italic>.
format Article
id doaj-art-edf9a4b01a064a56b23907cfa01bab84
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-edf9a4b01a064a56b23907cfa01bab842025-02-12T00:00:11ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184895490610.1109/JSTARS.2025.353423810854657Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR DataJiannan He0https://orcid.org/0009-0008-6197-6038Yongbin Zhang1Mingyue Liu2https://orcid.org/0000-0002-0503-3544Lin Chen3https://orcid.org/0000-0002-9270-1626Weidong Man4https://orcid.org/0000-0003-1960-1976Hua Fang5Xiang Li6Xuan Yin7Jianping Liang8Wenke Bai9https://orcid.org/0009-0007-8308-8843Fuping Li10College of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaCollege of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaCollege of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaZhejiang Provincial Key Laboratory of Urban Wetlands and Regional Change, Institute of Remote Sensing and Earth Sciences, Hangzhou Normal University, Hangzhou, ChinaCollege of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaCollege of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaCollege of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaCollege of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaSINOTECH LAND SPATIO CORP, Beijing, ChinaFifth Geological Brigade of Hebei Bureau of Geology and Mineral Resources, Tangshan, ChinaCollege of Mining Engineering, North China University of Science and Technology, Tangshan, ChinaSoil organic carbon (SOC) is an essential component for plant growth and a pivotal factor in the global carbon cycle. <italic>Spartina alterniflora</italic> (<italic>S. alterniflora</italic>), an invasive species characterized by high primary productivity and rapid carbon sequestration capabilities, exerts a substantial impact on SOC concentrations. The precise quantification of SOC content in <italic>S. alterniflora</italic> is extremely importance. Based on 73 measured samples, along with multispectral imagery and LiDAR data collected via unmanned aerial vehicles, machine learning techniques, including random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost), were employed to predict the SOC content of <italic>S. alterniflora</italic> and map its spatial distribution. We compared the predictive performance of these different machine learning algorithms to identify the most effective one. The results show that the following. 1) The prediction accuracy is improved by classifying the data into three types: unlodging <italic>S. alterniflora</italic> (ULSA), lodging <italic>S. alterniflora</italic> (LSA), and mudflats. 2) XGBoost outperformed RF and SVM in accurately predicting SOC content, with <italic>R</italic><sup>2</sup>; values of 0.743 for ULSA, 0.731 for LSA, and 0.705 for mudflats; 3) In the XGBoost models constructed for ULSA, LSA, and mudflats, spectral features contributed 75.7&#x0025;, 73.1&#x0025;, and 63.1&#x0025;, respectively, with the normalized difference vegetation index emerging as the most critical spectral feature. Slope aspect (AS) was identified as the most influential topographic feature. 4) The spatial distribution of SOC exhibited marked heterogeneity, with higher SOC content in ULSA and lower in mudflats, demonstrating a gradient of decreasing SOC content from land to sea. These results hold significant implications for the study of SOC content in <italic>S. alterniflora</italic>.https://ieeexplore.ieee.org/document/10854657/Extreme gradient boostingmachine learningrandom forest (RF)soil organic carbon content<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">Spartina alterniflora</italic>support vector machine (SVM)
spellingShingle Jiannan He
Yongbin Zhang
Mingyue Liu
Lin Chen
Weidong Man
Hua Fang
Xiang Li
Xuan Yin
Jianping Liang
Wenke Bai
Fuping Li
Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR Data
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Extreme gradient boosting
machine learning
random forest (RF)
soil organic carbon content
<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">Spartina alterniflora</italic>
support vector machine (SVM)
title Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR Data
title_full Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR Data
title_fullStr Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR Data
title_full_unstemmed Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR Data
title_short Prediction of Soil Organic Carbon Content in <italic>Spartina alterniflora</italic> by Using UAV Multispectral and LiDAR Data
title_sort prediction of soil organic carbon content in italic spartina alterniflora italic by using uav multispectral and lidar data
topic Extreme gradient boosting
machine learning
random forest (RF)
soil organic carbon content
<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">Spartina alterniflora</italic>
support vector machine (SVM)
url https://ieeexplore.ieee.org/document/10854657/
work_keys_str_mv AT jiannanhe predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT yongbinzhang predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT mingyueliu predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT linchen predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT weidongman predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT huafang predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT xiangli predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT xuanyin predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT jianpingliang predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT wenkebai predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata
AT fupingli predictionofsoilorganiccarboncontentinitalicspartinaalternifloraitalicbyusinguavmultispectralandlidardata