Estimating cropland soil organic carbon stock in Erhai Lake basin: Contribution of temporal-spatial-spectral information
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; Le, Weipeng2,3,4; Fan, Dong2,3,4 |
| 刊名 | SOIL & TILLAGE RESEARCH
 |
| 出版日期 | 2025-12-01 |
| 卷号 | 254页码:106747 |
| 关键词 | Soil organic carbon Plateau lake basin Cropland Multi-source remote sensing data Soil-pedogenic model Multi-method fusion |
| ISSN号 | 0167-1987 |
| DOI | 10.1016/j.still.2025.106747 |
| 产权排序 | 4 |
| 文献子类 | Article |
| 英文摘要 | Traditional soil organic carbon (SOC) prediction methods exhibit significant uncertainty when applied to croplands in plateau lake basins, which are characterized by complex terrain, fragmented plots, and diverse cropping structures. In this study, we endeavored to overcome the limitations of traditional methods in predicting SOC content in the ecologically fragile and agriculturally vital plateau lake basins. This study effectively integrates dispersed soil data, spatial features, and temporal-spatial variations into seven categories of soil-forming factors by combining multi-source remote sensing data and a soil-pedogenic model. Furthermore, to extract the temporal-spatial-spectral (TSS) features of soil-forming factors and calculate the weights of input variables by integrating the convolutional neural networks, long short-term memory networks, and attention mechanism (CNN-LSTM_A), thereby enhancing the predictive accuracy and interpretability of SOC content. Finally, based on two periods of measured topsoil (0-20 cm) sample data, we constructed a precise estimation framework for interannual variations in cropland SOC stocks in the plateau lake basin. The results showed that CNN-LSTM_A outperformed six comparison models in both prediction accuracy and temporal transferability: reducing the RMSEmean and MAE(mean) by 1.6796-1.9558 g kg(-1) and 0.7835-1.2400 g kg(-1), increasing the R-mean(2), RPIQ(mean), and CCCmean by 0.0970-0.1273, 0.3863-0.5778, and 0.0773-0.1100, respectively. Additionally, the results confirmed that long-term crop growth information indirectly reflects the SOC accumulation process, contributing to improved prediction accuracy. From 2007-2016, the spatial heterogeneity of cropland SOC content in the Erhai Lake basin was jointly driven by vegetation and topography, with vegetation being the more influential factor. Higher SOC content was observed in regions on the western and northern sides of Erhai Lake, exhibiting certain temporal dynamics. During this period, cropland SOC content exhibited an overall increasing trend, with significant increases concentrated in the northern basin. However, due to a reduction in cropland area, total SOC stocks showed a decreasing trend (4.366 Tg C and 4.136 Tg C). Specifically, 0.475 Tg C was indirectly lost due to land use changes, while areas of unchanged cropland directly contributed a gain of 0.245 Tg C due to increasing SOC content. This research not only provides critical data support for ecological management and sustainable agricultural development in the Erhai Lake basin but also offers scientific backing for ecological protection and broader-scale carbon cycling studies in other ecologically fragile areas. |
| URL标识 | 查看原文 |
| WOS关键词 | TERRESTRIAL ECOSYSTEMS ; CHINA ; PREDICTION ; SEQUESTRATION ; TEMPERATURE ; REGRESSION ; DYNAMICS ; DATASET ; STORAGE ; FOREST |
| WOS研究方向 | Agriculture |
| 语种 | 英语 |
| WOS记录号 | WOS:001530977700001 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/215319]  |
| 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.Kunming Univ Sci & Technol, Fac Land Resources Engn, Kunming 650093, Peoples R China; 3.Yunnan Key Lab Quantitat Remote Sensing, Kunming 650093, Peoples R China; 4.Yunnan Int Joint Lab Integrated Sky Ground Intelli, Kunming 650093, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Ji, Xinran,Tang, Bo-Hui,Huang, Liang,et al. Estimating cropland soil organic carbon stock in Erhai Lake basin: Contribution of temporal-spatial-spectral information[J]. SOIL & TILLAGE RESEARCH,2025,254:106747. |
| APA | Ji, Xinran,Tang, Bo-Hui,Huang, Liang,Chen, Guokun,Le, Weipeng,&Fan, Dong.(2025).Estimating cropland soil organic carbon stock in Erhai Lake basin: Contribution of temporal-spatial-spectral information.SOIL & TILLAGE RESEARCH,254,106747. |
| MLA | Ji, Xinran,et al."Estimating cropland soil organic carbon stock in Erhai Lake basin: Contribution of temporal-spatial-spectral information".SOIL & TILLAGE RESEARCH 254(2025):106747. |
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。