文献类型： 外文期刊

作者： Hong, Yongsheng ¹ ; Sanderman, Jonathan ³ ; Hengl, Tomislav ⁴ ; Chen, Songchao ⁵ ; Wang, Nan ⁶ ; Xue, Jie ⁶ ; Zhuo, Zhiqing ⁷ ; Peng, Jie ⁸ ; Li, Shuo ⁹ ; Chen, Yiyun ¹⁰ ; Liu, Yaolin ¹⁰ ; Mouazen, Abdul Mounem ¹¹ ; Shi, Zhou ⁶ ;

作者机构： 1.Chinese Acad Sci, Inst Soil Sci, State Key Lab Soil & Sustainable Agr, Nanjing 210008, Peoples R China

2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China

3.Woodwell Climate Res Ctr, Falmouth, MA 02540 USA

4.OpenGeoHub Fdn, Agro Business Pk 10, NL-6708 PW Wageningen, Netherlands

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

6.Zhejiang Univ, Inst Agr Remote Sensing & Informat Technol Applica, Coll Environm & Resource Sci, Hangzhou 310058, Peoples R China

7.Zhejiang Acad Agr Sci, Inst Digital Agr, Hangzhou 310021, Peoples R China

8.Tarim Univ, Coll Plant Sci, Alaer 843300, Peoples R China

9.Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Peoples R China

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

11.Univ Ghent, Dept Environm, Coupure Links 653, B-9000 Ghent, Belgium

12.Vytautas Magnus Univ, Fac Engn, Dept Agr Engn & Safety, Kaunas, Lithuania

关键词： Soil monitoring; Mid-infrared spectroscopy; Soil spectral library; Fractional-order derivative; Deep learning

期刊名称：CATENA （ 影响因子：6.2； 五年影响因子：6.4 ）

ISSN： 0341-8162

年卷期： 2024 年 235 卷

页码：

收录情况： SCI

摘要： Accurate monitoring of soil organic carbon (SOC) is critical for sustainable management of soil for improving its quality, function, and carbon sequestration. As a nondestructive, efficient, and low-cost technique, mid-infrared (MIR) spectroscopy has shown a great potential in rapid estimation of SOC, despite limited studies of the global scale. The objective of this work was to use a globally distributed topsoil MIR spectral library with 33,039 samples to predict SOC using different modeling methods. Effects of nine fractional-order derivatives (FODs) on the predicted accuracy of SOC were evaluated using four regression algorithms (i.e., ratio index-based linear regression, RI-LR; partial least squares regression, PLSR; Cubist; convolutional neural network, CNN). Squareroot transformation to SOC data was performed to minimize the skewness and non-linearity. Results indicated FOD to capture the subtle spectral details related to SOC, leading to improved predictions that may not be possible by the raw absorbance and common integer-order derivatives. Concerning the RI-LR models, the optimal validation result for SOC was obtained by 0.75-order derivative, with the ratio of performance to inter-quartile distance (RPIQ) of 1.85. Regarding the full-spectrum modeling for SOC, the CNN outperformed PLSR and Cubist models, irrespective of raw absorbance or eight FODs; the best-performing CNN model was achieved by 1.25order derivative (validation RPIQ = 6.33). It can be concluded that accurate estimation of SOC using large and diverse MIR spectral library at the global scale combined with deep-learning CNN model is feasible. This global-scale database is extremely valuable for us to deal with the shortage of soil data and to monitor the soils at different geographical scales.