文献类型： 外文期刊

作者： Li, Shuo ¹ ; Shen, Xinru ¹ ; Shen, Xue ¹ ; Cheng, Jun ⁴ ; Xu, Dongyun ⁵ ; Makar, Randa S. ⁶ ; Guo, Yan ² ; Hu, Bifeng ⁸ ; Chen, Songchao ⁹ ; Hong, Yongsheng ¹¹ ; Peng, Jie ¹² ; Shi, Zhou ⁹ ;

作者机构： 1.Cent China Normal Univ, Coll Urban & Environm Sci, Key Lab Geog Proc Anal & Simulat Hubei Prov, Wuhan 430079, Peoples R China

2.Minist Agr & Rural Affairs, Key Lab Huang Huai Hai Smart Agr Technol, Zhengzhou 450002, Peoples R China

3.Northwest A&F Univ, State Key Lab Soil Eros & Dryland Farming Loess Pl, Yangling 712100, Peoples R China

4.Kean Univ, Dept Environm & Sustainabil Sci, Union, NJ 07083 USA

5.Shandong Agr Univ, Coll Resources & Environm, Tai An 271018, Peoples R China

6.Natl Res Ctr, Agr & Biol Res Inst, Soils & Water Use Dept, Cairo 12622, Egypt

7.Henan Acad Agr Sci, Inst Agr Informat Technol, Zhengzhou 450002, Peoples R China

8.Jiangxi Univ Finance & Econ, Sch Publ Adm, Dept Land Resource Management, Nanchang 330013, Peoples R China

9.Zhejiang Univ, Inst Appl Remote Sensing & Informat Technol, Coll Environm & Resource Sci, Hangzhou 310058, Peoples R China

10.ZJU Hangzhou Global Sci & Technol Innovat Ctr, Hangzhou 311200, Peoples R China

11.Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China

12.Tarim Univ, Coll Agr, Alar 843300, Peoples R China

关键词： spectroscopy; proximal sensing; random forest; partial least-squares discriminant analysis (PLSDA); outer product analysis (OPA)

期刊名称：REMOTE SENSING （ 影响因子：4.1； 五年影响因子：4.8 ）

ISSN：

年卷期： 2025 年 17 卷 9 期

页码：

收录情况： SCI

摘要： Soil spectroscopy offers a rapid, cost-effective alternative to traditional soil analyses for characterization and classification. Previous studies have mainly focused on predicting soil categories using single sensors, particularly visible-near-infrared (vis-NIR) or mid-infrared (MIR) spectroscopy. In this study, we evaluated the performance of vis-NIR, MIR, and their combined spectra for soil classification by partial least-squares discriminant analysis (PLSDA) and random forest (RF). Utilizing 60 typical soil profiles' data of four soil classes from the global soil spectral library (GSSL), our results demonstrated that in PLSDA models, direct combination (optimal overall accuracy: 70.6%, kappa coefficient: 0.60) and outer product analysis (OPA) fused spectra (optimal overall accuracy: 68.1%, kappa coefficient: 0.57) outperformed vis-NIR (optimal overall accuracy: 62.2%, kappa coefficient: 0.49) but underperformed compared to MIR (optimal overall accuracy: 71.4%, kappa coefficient: 0.62). In RF models, classification accuracy using fused spectra was inferior to single spectral ranges, with MIR achieving the highest classification accuracy (optimal overall accuracy: 89.1%, kappa coefficient: 0.85). Therefore, MIR alone remains the most effective spectral range for accurate soil class discrimination. Our findings highlight the potential of MIR spectroscopy for enhancing global soil classification accuracy and efficiency, with important implications for soil resource management and agricultural planning across diverse environments.