Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 Data

Based on multi-source data, including synthetic aperture radar (Sentinel-1, S1) and optical satellite images (Sentinel-2, S2), topographic data, and climate data, this study explored the performance and feasibility of different variable combinations in predicting SOC using three machine learning mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Haoming Li, Jingyao Xia, Yadi Yang, Yansu Bo, Xiaoyan Li
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/15/1640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239729063591936
author Haoming Li
Jingyao Xia
Yadi Yang
Yansu Bo
Xiaoyan Li
author_facet Haoming Li
Jingyao Xia
Yadi Yang
Yansu Bo
Xiaoyan Li
author_sort Haoming Li
collection DOAJ
description Based on multi-source data, including synthetic aperture radar (Sentinel-1, S1) and optical satellite images (Sentinel-2, S2), topographic data, and climate data, this study explored the performance and feasibility of different variable combinations in predicting SOC using three machine learning models. We designed the three models based on 244 samples from the study area, using 70% of the samples for the training set and 30% for the testing set. Nine experiments were conducted under three variable scenarios to select the optimal model. We used this optimal model to achieve high-precision predictions of SOC content. Our results indicated that both S1 and S2 data are significant for SOC prediction, and the use of multi-sensor data yielded more accurate results than single-sensor data. The RF model based on the integration of S1, S2, topography, and climate data achieved the highest prediction accuracy. In terms of variable importance, the S2 data exhibited the highest contribution to SOC prediction (31.03%). The SOC contents within the study region varied between 4.16 g/kg and 29.19 g/kg, showing a clear spatial trend of higher concentrations in the east than in the west. Overall, the proposed model showed strong performance in estimating grassland SOC and offered valuable scientific guidance for grassland conservation in the western Songnen Plain.
format Article
id doaj-art-8dfc3f0d6cdc48e894c92a4a65e84af7
institution Kabale University
issn 2077-0472
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-8dfc3f0d6cdc48e894c92a4a65e84af72025-08-20T04:00:51ZengMDPI AGAgriculture2077-04722025-07-011515164010.3390/agriculture15151640Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 DataHaoming Li0Jingyao Xia1Yadi Yang2Yansu Bo3Xiaoyan Li4College of Earth Sciences, Jilin University, Changchun 130061, ChinaCollege of Earth Sciences, Jilin University, Changchun 130061, ChinaCollege of Earth Sciences, Jilin University, Changchun 130061, ChinaCollege of Earth Sciences, Jilin University, Changchun 130061, ChinaCollege of Earth Sciences, Jilin University, Changchun 130061, ChinaBased on multi-source data, including synthetic aperture radar (Sentinel-1, S1) and optical satellite images (Sentinel-2, S2), topographic data, and climate data, this study explored the performance and feasibility of different variable combinations in predicting SOC using three machine learning models. We designed the three models based on 244 samples from the study area, using 70% of the samples for the training set and 30% for the testing set. Nine experiments were conducted under three variable scenarios to select the optimal model. We used this optimal model to achieve high-precision predictions of SOC content. Our results indicated that both S1 and S2 data are significant for SOC prediction, and the use of multi-sensor data yielded more accurate results than single-sensor data. The RF model based on the integration of S1, S2, topography, and climate data achieved the highest prediction accuracy. In terms of variable importance, the S2 data exhibited the highest contribution to SOC prediction (31.03%). The SOC contents within the study region varied between 4.16 g/kg and 29.19 g/kg, showing a clear spatial trend of higher concentrations in the east than in the west. Overall, the proposed model showed strong performance in estimating grassland SOC and offered valuable scientific guidance for grassland conservation in the western Songnen Plain.https://www.mdpi.com/2077-0472/15/15/1640machine learningSentinel-1/2soil organic carbongrasslandWest Songnen Plain
spellingShingle Haoming Li
Jingyao Xia
Yadi Yang
Yansu Bo
Xiaoyan Li
Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 Data
Agriculture
machine learning
Sentinel-1/2
soil organic carbon
grassland
West Songnen Plain
title Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 Data
title_full Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 Data
title_fullStr Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 Data
title_full_unstemmed Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 Data
title_short Estimation of Soil Organic Carbon Content of Grassland in West Songnen Plain Using Machine Learning Algorithms and Sentinel-1/2 Data
title_sort estimation of soil organic carbon content of grassland in west songnen plain using machine learning algorithms and sentinel 1 2 data
topic machine learning
Sentinel-1/2
soil organic carbon
grassland
West Songnen Plain
url https://www.mdpi.com/2077-0472/15/15/1640
work_keys_str_mv AT haomingli estimationofsoilorganiccarboncontentofgrasslandinwestsongnenplainusingmachinelearningalgorithmsandsentinel12data
AT jingyaoxia estimationofsoilorganiccarboncontentofgrasslandinwestsongnenplainusingmachinelearningalgorithmsandsentinel12data
AT yadiyang estimationofsoilorganiccarboncontentofgrasslandinwestsongnenplainusingmachinelearningalgorithmsandsentinel12data
AT yansubo estimationofsoilorganiccarboncontentofgrasslandinwestsongnenplainusingmachinelearningalgorithmsandsentinel12data
AT xiaoyanli estimationofsoilorganiccarboncontentofgrasslandinwestsongnenplainusingmachinelearningalgorithmsandsentinel12data