中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
Assessing Potential of Multisource Satellite Data and Machine Learning Models for Cropland Soil Organic Carbon Prediction in Plateau Lake Basin

文献类型：期刊论文

作者Ji, Xinran2,3,4; Tang, Bo-Hui1,2,3,4; Huang, Liang2,3,4; Chen, Guokun2,3,4; Zhu, Xinming2,3,4; Fan, Dong2,3,4; Chen, Junyi2,3,4
刊名IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
出版日期2025
卷号63页码:4418119
关键词Lakes Biological system modeling Predictive models Soil properties Remote sensing Monitoring Long short term memory Data models Vegetation mapping Satellites Cropland machine learning (ML) plateau lake basin remote sensing (RS) soil organic carbon (SOC) soil-pedogenic model vegetation phenology
ISSN号0196-2892
DOI10.1109/TGRS.2025.3610513
产权排序4
文献子类Article
英文摘要Accurate spatial quantification of cropland soil organic carbon (SOC) in plateau lake basins is crucial for assessing the carbon sequestration potential in ecologically fragile regions. This study developed a machine learning (ML) frame-work that integrates multisource satellite-derived environmental covariates (ECs, topography, climate, vegetation, soil properties, and parent materials) to estimate SOC distribution in the Erhai Lake basin. Using 432 topsoil samples (0-20 cm), we systematically compared 15 models, including conventional ML approaches [e.g., random forest (RF), support vector machine, and light gradient boosting machine (LightGBM)] and deep learning (DL) models [e.g., long short-term memory (LSTM), recurrent neural network (RNN), and multilayer perceptron (MLP)]. The results showed that DL models achieved higher predictive accuracy than conventional ML models, reducing root-mean-square error (RMSE) by 0.1680 g kg(1) and increasing R2, ratio of performance to inter-quartile distance (RPIQ), and concordance correlation coefficient (CCC) by averages of 0.0225, 0.1143, and 0.0253, respectively, although conventional ML models exhibited greater robustness. Elevation and tem-perature were identified as dominant factors controlling SOC spatial patterns, with higher concentrations clustered in the western and northern subbasins. Greater prediction uncertainty in the northwestern and eastern margins was associated with complex terrain heterogeneity. Spatially explicit SOC mapping derived from the integration of multisource satellite data and ML models offers innovative approaches for carbon management in ecologically fragile lacustrine agroecosystems.
URL标识查看原文
WOS关键词TEMPERATURE ; REGRESSION ; STOCKS ; ERHAI
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001579061900035
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://ir.igsnrr.ac.cn/handle/311030/217479]  
专题资源与环境信息系统国家重点实验室_外文论文
通讯作者Tang, Bo-Hui
作者单位1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
2.Yunnan Int Joint Lab Integrated Sky Ground Intelli, Kunming 650093, Peoples R China;
3.Yunnan Key Lab Quantitat Remote Sensing, Kunming 650093, Peoples R China;
4.Kunming Univ Sci & Technol, Fac Land Resources Engn, Kunming 650093, Peoples R China;
推荐引用方式
GB/T 7714		 Ji, Xinran,Tang, Bo-Hui,Huang, Liang,et al. Assessing Potential of Multisource Satellite Data and Machine Learning Models for Cropland Soil Organic Carbon Prediction in Plateau Lake Basin[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:4418119.
APA Ji, Xinran.,Tang, Bo-Hui.,Huang, Liang.,Chen, Guokun.,Zhu, Xinming.,...&Chen, Junyi.(2025).Assessing Potential of Multisource Satellite Data and Machine Learning Models for Cropland Soil Organic Carbon Prediction in Plateau Lake Basin.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,4418119.
MLA Ji, Xinran,et al."Assessing Potential of Multisource Satellite Data and Machine Learning Models for Cropland Soil Organic Carbon Prediction in Plateau Lake Basin".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):4418119.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。