Multi-source spectral data and machine learning algorithm-based inversion of organic carbon in soil ：taking northeastern Inner Mongolia Autonomous Region， China as an example

REN Guanyao; QIN Jing; QIAN Xiaojiang; ZHANG Ke; YAN Weiyue; FENG Zi'ang; GUO Long

doi:10.13300/j.cnki.hnlkxb.2026.02.014

您当前的位置：

首页 >

文章列表页 >

Multi-source spectral data and machine learning algorithm-based inversion of organic carbon in soil ：taking northeastern Inner Mongolia Autonomous Region， China as an example

Resources and environment | 更新时间：2026-11-05

- Multi-source spectral data and machine learning algorithm-based inversion of organic carbon in soil ：taking northeastern Inner Mongolia Autonomous Region， China as an example
- Journal of Huazhong Agricultural University Vol. 45, Issue 2, Pages: 137-145(2026)
- 作者机构：
  
  1.内蒙古自治区测绘地理信息中心，呼和浩特010010
  2.湖北省国土测绘院，武汉430014
  3.国标（北京）检验认证有限公司，北京100010
  4.华中农业大学资源与环境学院，武汉430070
- 作者简介：
- 基金信息：
- DOI：10.13300/j.cnki.hnlkxb.2026.02.014
  CLC： TP181;S153.6
- Received：16 July 2025，
  
  Published：15 March 2026
- 稿件说明：
移动端阅览
任冠尧，秦婧，钱小将，等.基于多源光谱数据和机器学习算法的土壤有机碳反演研究：以内蒙古自治区东北部为例［J］.华中农业大学学报，2026，45（2）：137‐145.

REN Guanyao,QIN Jing,QIAN Xiaojiang,et al.Multi-source spectral data and machine learning algorithm-based inversion of organic carbon in soil ：taking northeastern Inner Mongolia Autonomous Region， China as an example[J].Journal of Huazhong Agricultural University,2026,45(02):137-145.
任冠尧，秦婧，钱小将，等.基于多源光谱数据和机器学习算法的土壤有机碳反演研究：以内蒙古自治区东北部为例［J］.华中农业大学学报，2026，45（2）：137‐145. DOI： 10.13300/j.cnki.hnlkxb.2026.02.014.

REN Guanyao,QIN Jing,QIAN Xiaojiang,et al.Multi-source spectral data and machine learning algorithm-based inversion of organic carbon in soil ：taking northeastern Inner Mongolia Autonomous Region， China as an example[J].Journal of Huazhong Agricultural University,2026,45(02):137-145. DOI： 10.13300/j.cnki.hnlkxb.2026.02.014.

摘要

为探究外界环境因素（光照、大气条件）和传感器参数（光谱与空间分辨率）对不同来源光谱数据反演土壤有机碳（SOC）精度的影响机制，以内蒙古自治区东北部为研究区，采集160个表层土壤（0~20 cm）SOC样品，并同步获取近端高光谱（室内人造光源与室外太阳光源）以及星载多光谱（Landsat-8、Sentinel-2）与高光谱（ZY1-02D）数据，使用随机森林（RF）与支持向量机（SVM）算法，分别构建SOC反演模型，通过系统比较不同数据源的模型性能，分析环境因素与传感器参数对SOC反演精度的影响。结果显示：室内人造光源因光谱信号稳定、可控性强，其反演精度略优于室外太阳光源，但二者差异较小，表明自然光照波动对SOC反演的影响有限；近地高光谱数据反演精度显著高于卫星多光谱与高光谱数据，主要因卫星数据受大气散射、水汽吸收及混合像元等问题干扰；在卫星数据中，高光谱卫星ZY1-02D的反演精度高于多光谱卫星，而Sentinel-2较Landsat-8的空间分辨率提升（10 m vs 30 m）对模型性能改善有限，说明光谱分辨率对SOC精度的贡献大于空间分辨率。

Abstract

Northeastern Inner Mongolia Autonomous Region， China was used to study the mechanism of external environmental factors including illumination and atmospheric conditions and sensor parameters including spectral and spatial resolutions affecting the accuracy of inverting the organic carbon in soil （SOC） from different sources of spectral data. SOC samples from 160 surface soils（0-20 cm） were collected and proximal hyperspectral data acquired under indoor artificial lighting and outdoor natural sunlight and spaceborne multispectral（Landsat-8 and Sentinel-2） and hyperspectral（ZY1-02D） data were synchronously obtained. Random forest（RF） and support vector machine（SVM） algorithms were used to construct the inversion models of SOC. The effects of environmental factors and sensor parameters on the accuracy of inverting SOC were analyzed by systematically comparing the performance of model across different sources of data. The results showed that proximal data acquired under indoor artificial lighting sources had slightly better accuracy of inversion than that under outdoor sunlight sources due to stable and controllable spectral signals. However， the difference between the two was small， indicating that the effect of natural illumination fluctuations on the inversion of SOC is limited. The inversion accuracy of proximal hyperspectral data was significantly higher than that of spaceborne multispectral and hyperspectral data， mainly due to the interference from atmospheric scattering， water vapor absorption， and mixed pixels in satellite data. Among the spaceborne datasets， the inversion accuracy of hyperspectral satellite ZY1-02D was higher than that of multispectral sensors， while the improvement in spatial resolution of Sentinel-2 had limited effect on the performance of model compared to that of Landsat-8（10 m vs 30 m）， indicating that spectral resolution contributes more to the accuracy of inverting SOC than spatial resolution.

关键词

Keywords

references

余玉洋，李晶，曾莉.中国南北过渡带生态系统固碳服务及价值量空间格局［J］.陕西师范大学学报（自然科学版），2020，48（1）：11-20.YU Y Y，LI J，ZENG L.Spatial pattern of carbon sequestration services and value of ecosystems of the North-South transitional zone in China［J］.Journal of Shaanxi Normal University（natural science edition），2020，48（1）：11-20 （in Chinese with English abstract） .

辛琨，颜葵，李真，等.海南岛红树林湿地土壤有机碳分布规律及影响因素研究［J］.土壤学报，2014，51（5）：1078-1086.XIN K，YAN K，LI Z，et al.Distribution of soil organic carbon in mangrove wetlands of Hainan Island and its influencing factors［J］.Acta pedologica sinica，2014，51（5）：1078-1086 （in Chinese） .

杨玉盛，谢锦升，盛浩，等.中亚热带山区土地利用变化对土壤有机碳储量和质量的影响［J］.地理学报，2007，62（11）： 1123-1131.YANG Y S，XIE J S，SHENG H，et al.The impact of land use/cover change on soil organic carbon stocks and quality in mid-subtropical mountainous area of southern China［J］.Acta geographica sinica，2007，62（11）：1123-1131 （in Chinese with English abstract） .

杨长明，欧阳竹，杨林章，等.农业土地利用方式对华北平原土壤有机碳组分和团聚体稳定性的影响［J］.生态学报，2006，26（12）：4148-4155.YANG C M，OUYANG Z，YANG L Z，et al.Organic carbon fractions and aggregate stability in an aquatic soil as influenced by agricultural land uses in the Northern China Plain［J］.Acta ecologica sinica，2006，26（12）：4148-4155 （in Chinese with English abstract） .

曹新光，岳伟鹏，邓洁.北亚热带山地不同海拔土壤有机碳分布特征：以鄂东龟峰山为例［J］.广西师范大学学报（自然科学版），2021，39（6）：174-182.CAO X G，YUE W P，DENG J.Soil organic carbon distribution characteristics along an altitudinal gradient in the northern subtropical region：a case study in Guifeng Mountains of eastern Hubei，China［J］.Journal of Guangxi Normal University（natural science edition），2021，39（6）：174-182 （in Chinese with English abstract） .

刘满强，胡锋，陈小云.土壤有机碳稳定机制研究进展［J］.生态学报，2007（6）：2642-2650.LIU M Q，HU F，CHEN X Y.A review on mechanisms of soil organic carbon stabilization［J］.Acta ecologica sinica，2007（6）：2642-2650 （in Chinese with English abstract） .

MA Y Q，WOOLF D，FAN M S，et al.Global crop production increase by soil organic carbon［J］.Nature geoscience，2023，16（12）：1159-1165.

温云杰，张建诚，杨娜，等.长期秸秆还田配施有机肥对土壤有机碳组分和孔隙结构的影响［J］.农业工程学报，2024，40（21）：74-81.WEN Y J，ZHANG J C，YANG N，et al.Effects of the long-term application of organic fertilization and straw returning on the components of soil organic carbon and pores［J］.Transactions of the CSAE，2024，40（21）：74-81 （in Chinese with English abstract） .

LIU C Z，HAN X Z，LU X C，et al.Response of soil enzymatic activity to pore structure under inversion tillage with organic materials incorporation in a Haplic Chernozem［J/OL］.Journal of environmental management，2024，370：122421［2025-07-16］.https：//doi.org/10.1016/j.jenvman.2024.122421.

包青岭，丁建丽，王敬哲，等.基于随机森林算法的土壤有机质含量高光谱检测［J］.干旱区地理，2019，42（6）：1404-1414.BAO Q L，DING J L，WANG J Z，et al.Hyperspectral detection of soil organic matter content based on random forest algorithm［J］.Arid land geography，2019，42（6）：1404-1414 （in Chinese with English abstract） .

周磊，何秀芹，贾德伟，等.基于CWT-CARS的黄土高原东部陕州区农田表层有机碳含量高光谱反演［J］.遥感技术与应用，2025，40（1）：60-68.ZHOU L，HE X Q，JIA D W，et al.Hyperspectral retrieval of organic carbon content in farmland surface in Shanzhou District of eastern Loess Plateau based on CWT-CARS［J］.Remote sensing technology and application，2025，40（1）：60-68 （in Chinese with English abstract） .

STENBERG B，VISCARRA ROSSEL R A，MOUAZEN A M，et al.Visible and near infrared spectroscopy in soil science ［J］.Advances in agronomy，2010，107：163-215.

VOHLAND M，BESOLD J，HILL J，et al.Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy［J］.Geoderma，2011，166（1）：198-205.

甄诚，王海燕，雷相东，等.基于随机森林模型的旺业甸实验林场土壤全氮数字制图［J］.华中农业大学学报，2024，43（3）：249-257.ZHEN C，WANG H Y，LEI X D，et al.Digital mapping of soil total nitrogen in Wangyedian experimental forest farm based on random forest model［J］.Journal of Huazhong Agricultural University，2024，43（3）：249-257 （in Chinese with English abstract） .

邹霞，钱海燕，周杨明，等.季节性淹水湿地表层土壤有机碳含量遥感预测及空间分布特征［J］.华中农业大学学报，2024，43（3）：111-120.ZOU X，QIAN H Y，ZHOU Y M，et al.Remote sensing prediction and spatial distribution characteristics of content of organic carbon in surface soil of seasonal flooded wetlands in Poyang Lake［J］.Journal of Huazhong Agricultural University，2024，43（3）：111-120 （in Chinese with English abstract） .

MINASNY B，MCBRATNEY A B，MALONE B P，et al.Digital mapping of soil carbon［J］.Advances in agronomy，2013，118：1-47.

VISCARRA ROSSEL R A，BEHRENS T，BEN-DOR E，et al.A global spectral library to characterize the world’s soil［J］.Earth-science reviews，2016，155：198-230.

刘艳芳，宋玉玲，郭龙，等.结合高光谱信息的土壤有机碳密度地统计模型［J］.农业工程学报，2017，33（2）：183-191.LIU Y F，SONG Y L，GUO L，et al.Geostatistical models of soil organic carbon density prediction based on soil hyperspectral reflectance［J］.Transactions of the CSAE，2017，33（2）：183-191 （in Chinese with English abstract） .

颜祥照，姚艳敏，张霄羽.土壤有机质遥感制图研究进展与展望［J］.中国农业信息，2019，31（3）：13-26.YAN X Z，YAO Y M，ZHANG X Y.The progress and prospect of soil organic matter mapping based on remote sensing technology［J］.China agricultural information，2019，31（3）：13-26 （in Chinese） .

宋玉婷，高小红，宋奇，等.基于Sentinel-2 MSI与Sentinel-1 SAR影像相结合的区域农田土壤有机碳估算：以青海湟水流域黄土丘陵区为例［J］.土壤通报，2025，56（3）：755-766.SONG Y T，GAO X H，SONG Q，et al.The combination of sentinel-2 MSI and sentinel-1SAR to estimate and map soil organic carbon content in farmland：a case study of the typical area of loess hilly area in the Huangshui watershed of Qinghai Province［J］.Chinese journal of soil science，2025，56（3）：755-766 （in Chinese with English abstract） .

王迪，曾妍，田甜，等.基于卫星遥感的耕地质量监测与评价研究进展［J］.中国农业资源与区划，2025，46（12）：203-218.WANG D，ZENG Y，TIAN T，et al.Research progress on cultivated land quality monitoring and assessment by remote sensing［J］.Chinese journal of agricultural resources and regional planning，2025，46（12）：203-218 （in Chinese with English abstract） .

李泽鑫，高爽，胡登辉，等.天基载荷特性光谱分辨率与信噪比对黑土地有机质定量反演影响分析［J］.遥感技术与应用，2024，39（4）：917-926.LI Z X，GAO S，HU D H，et al.Sensitivity of black soil organic matter content prediction to the spectral resolution and signal-to-noise ratio of space-based remote sensing loads［J］.Remote sensing technology and application ，2024，39（4）：917-926 （in Chinese with English abstract） .

王倩，毕研盟，杨忠东.气溶胶对大气CO 2 短波红外遥感探测影响的模拟分析［J］.物理学报，2018，67（3）：301-313.WANG Q，BI Y M，YANG Z D.Simulation analysis of aerosol effect on shortwave infrared remote sensing detection of atmospheric CO 2 ［J］.Acta physica sinica，2018，67（3）：301-313 （in Chinese with English abstract） .

CORTES C，VAPNIK V.Support-vector networks［J］.Machine learning，1995，20（3）：273-297.

BREIMAN L.Random forests［J］.Machine learning，2001，45（1）：5-32.

王雨雪，杨柯，高秉博，等.基于两点机器学习方法的土壤有机质空间分布预测［J］.农业工程学报，2022，38（12）：65-73.WANG Y X，YANG K，GAO B B，et al.Prediction of the spatial distribution of soil organic matter based on two-point machine learning method［J］.Transactions of the CSAE，2022，38（12）：65-73 （in Chinese with English abstract） .

袁玉琦，陈瀚阅，张黎明，等.基于多变量与RF算法的耕地土壤有机碳空间预测研究：以福建亚热带复杂地貌区为例［J］.土壤学报，2021，58（4）：887-899.YUAN Y Q，CHEN H Y，ZHANG L M，et al.Prediction of spatial distribution of soil organic carbon in farmland based on multi-variables and random forest algorithm-a case study of a subtropical complex geomorphic region in Fujian as an example［J］.Acta pedologica sinica，2021，58（4）：887-899 （in Chinese with English abstract） .

聂明鹏.基于排序差异和算法对光谱变量选择与定性分析的研究［D］.温州：温州大学，20 19.NIE M P.Study on the variable selection and qualitative analysis of spectrum based on sum of ranking differences algorithm［D］.Wenzhou：Wenzhou University，2019 （in Chinese with English abstract） .

HONG Y S，CHEN Y Y，CHEN S C，et al.Bridging the gap between laboratory VNIR-SWIR spectra and Landsat-8 bare soil composite image for soil organic carbon prediction ［J/OL］.Remote sensing of environment，2025，328：114874［2025-07-16］.https：//doi.org/10.1016/j.rse.2025.114874.

施建成.MODIS亚像元积雪覆盖反演算法研究：纪念杰出的地理学家、冰川学家施雅风先生逝世一周年［J］.第四纪研究，2012，32（1）：6-15.SHI J C.An automatic algorithm on estimating sub-pixel snow cover from modis［J］.Quaternary sciences，2012，32（1）：6-15 （in Chinese with English abstract） .

祝元丽，王冬艳，张鹤，等.采用无人机载高分辨率光谱仪反演土壤有机碳含量［J］.农业工程学报，2021，37（6）：66-72.ZHU Y L，WANG D Y，ZHANG H，et al.Soil organic carbon content retrieved by UAV-borne high resolution spectrometer［J］.Transactions of the CSAE，2021，37（6）：66-72 （in Chinese with English abstract） .

尹成卓，高小红，宋奇，等.基于Sentinel-2影像的农田土壤有机碳含量估算：以湟水流域典型区域为例［J］.激光与光电子学进展，2025，62（12）：294-305.YIN C Z，GAO X H，SONG Q，et al.Estimation of soil organic carbon content in farmland based on Sentinel-2 imagery：case study of a typical area in the Huangshui River Basin［J］.Laser & optoelectronics progress，2025，62（12）：294-305 （in Chinese with English abstract） .

张益玮.基于SAR与光学遥感影像的玉米秸秆覆盖度反研究［D］.鞍山：辽宁科技大学，2023.ZHAN G Y W.Inverse study on corn stalk coverage based on SAR and optical remote sensing images［D］.Anshan：University of Science and Technology Liaoning，2023 （in Chinese with English abstract） .

POULADI N，GHOLIZADEH A，KHOSRAVI V，et al.Digital mapping of soil organic carbon using remote sensing data：a systematic review［J/OL］.CATENA，2023，232：107409［2025-07-16］.https：//doi.org/10.1016/j.catena.2023.107409.

BROEG T，DON A，WIESMEIER M，et al.Spatiotemporal monitoring of cropland soil organic carbon changes from space［J/OL］.Global change biology，2024，30（12）：e17608［2025-07-16］.https：//doi.org/10.1111%2Fgcb.17608.

LI Y J，LUO L Y，GUO F，et al.Quality control and improvement of GNSS-IR soil moisture robust inversion model［J］.Advances in space research，2025，75（1）：91-107.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research progress on mechanisms of traditional Chinese medicine for preventing and treating porcine epidemic diarrhea

Development of an indirect ELISA for detecting Photobacterium damselae using polyclonal antibodies against two outer membrane proteins

Optimization of multi-stage hydraulic cylinder arrangement points in articulated steering mechanisms based on NSGA-Ⅱ algorithm

农业生物质增值化利用技术与装备团队

Design of an IoT-based monitoring system for small-scale rural biogas projects

Related Author

No data

Related Institution

No data

AI问答

⁰