文献类型： 外文期刊

作者： Xu, Xibo ¹ ; Chen, Yunhao ³ ; Yang, Shuting ⁴ ;

作者机构： 1.Beijing Normal Univ, Fac Geog Sci, Beijing Key Lab Environm Remote Sensing & Digital, Beijing 100875, Peoples R China

2.Qilu Normal Univ, Coll Geog & Tourism, Jinan 250200, Peoples R China

3.Beijing Normal Univ, Fac Geog Sci, State Key Lab Remote Sensing Sci, Beijing, Peoples R China

4.NingXia Acad Agr & Forestry Sci, Inst Agr Econ & Informat Technol, Yinchuan 750002, Peoples R China

关键词： Satellites; Soil; Soil measurements; Accuracy; Precipitation; Hyperspectral imaging; Data models; Area measurement; Transfer learning; Satellite images; Bare soil hyperspectral imagery; mapping model; satellite-simulated spectral sample; soil organic matter (SOM); transfer learning (TL)

期刊名称：IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING （ 影响因子：5.3； 五年影响因子：5.6 ）

ISSN： 1939-1404

年卷期： 2025 年 18 卷

页码：

收录情况： SCI

摘要： Calibrating an accurate soil organic matter (SOM) satellite mapping model requires a sufficient number of representative satellite samples (including actual ground-based SOM values and corresponding satellite spectral data). However, collecting these samples is challenging due to complex geological environments and inconvenient transportation conditions across large areas. To address this issue, a satellite sample simulation strategy was developed to transform ground-based local-area soil spectral samples into satellite-simulated spectral samples. Subsequently, a transfer learning (TL) approach was implemented to encode the spectra-SOM relationship learned from the satellite-simulated sample set into a basic neural network model. Finally, by fine-tuning this model with only a small number of satellite spectral samples, a robust SOM satellite mapping model was established. The results indicated that a total of 846 satellite-simulated spectral samples were generated, and the differences between the satellite-simulated spectral samples and the satellite spectral samples were minimized. The optimal TL-based SOM satellite mapping model (TL-half model) had an R-2 of 0.90 and RPIQ of 4.02, representing a 12.50% improvement over the traditional SOM mapping model (R-2 = 0.80; RPIQ = 3.10). The TL-based SOM satellite mapping method proposed in this study offers an effective technical approach for regional SOM monitoring and global carbon storage management.