Optimization of Soil Particle Size Mapping Incorporating Spatial Autocorrelation and Attribute Similarity
文献类型：期刊论文
| 作者 | Qin, Liya2; Wang, Zong2,3; Zhang, Xiaoyuan1; Liang, Boyi2; Wang, Jia2 |
| 刊名 | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
 |
| 出版日期 | 2025 |
| 卷号 | 18页码:21044-21064 |
| 关键词 | Soil Predictive models Biological system modeling Accuracy Vegetation mapping Reflectivity Indexes Random forests Forestry Erosion Random forest (RF) soil particle size spatial distribution two-point machine learning (TPML) model uncertainty assessment |
| ISSN号 | 1939-1404 |
| DOI | 10.1109/JSTARS.2025.3597914 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Soil particle size fractions (PSFs) are vital for understanding soil functions and are widely used in environmental and land surface modeling. Accurate spatial mapping of PSFs is crucial and relies on robust prediction methods. This study, conducted in the typical loess plateau, integrates multidimensional auxiliary data-including remote sensing bands, topography, vegetation indices, socioeconomic indicators, and soil properties-to enhance prediction accuracy. We employ a two-point machine learning (TPML) model that incorporates spatial autocorrelation and attribute similarity into a unified framework for predicting PSF distribution. TPML enhances local predictions and overcomes the curse of dimensionality, ensuring robust performance with limited training samples. The TPML model is evaluated against random forest (RF), random forest regression kriging (RFRK), inverse distance weighting, and ordinary kriging under various sample sizes. Accuracy is assessed using mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R-2). TPML consistently outperforms other models across sample sizes (50-200), with optimal results at 150 samples (e.g., silt: MAE 4.21, RMSE 7.61, R-2 0.62). Its performance improves with larger training data, particularly for silt and sand, where R-2 increased from 0.59 to 0.69 and 0.63 to 0.73, respectively. Key environmental variables-latitude, precipitation, valley depth, vegetation type, and SAVI-strongly influenced spatial PSF patterns, showing a gradient from coarse textures in the north to fine textures in the south. The results demonstrate the effectiveness of TPML in enhancing PSF mapping by integrating spatial and attribute-based similarities within a high-dimensional prediction framework. |
| URL标识 | 查看原文 |
| WOS关键词 | LOESS PLATEAU ; GRAIN-SIZE ; PREDICTION ; SEDIMENTATION ; CONSERVATION ; FRACTIONS |
| WOS研究方向 | Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001564254800006 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/216030]  |
| 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 | Wang, Zong |
| 作者单位 | 1.Beijing Technol & Business Univ, Business Sch, Beijing 100048, Peoples R China 2.Beijing Forestry Univ, Coll Forestry, Precis Forestry Key Lab Beijing, Beijing 100083, Peoples R China; 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Qin, Liya,Wang, Zong,Zhang, Xiaoyuan,et al. Optimization of Soil Particle Size Mapping Incorporating Spatial Autocorrelation and Attribute Similarity[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2025,18:21044-21064. |
| APA | Qin, Liya,Wang, Zong,Zhang, Xiaoyuan,Liang, Boyi,&Wang, Jia.(2025).Optimization of Soil Particle Size Mapping Incorporating Spatial Autocorrelation and Attribute Similarity.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,18,21044-21064. |
| MLA | Qin, Liya,et al."Optimization of Soil Particle Size Mapping Incorporating Spatial Autocorrelation and Attribute Similarity".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 18(2025):21044-21064. |
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。