文献类型： 外文期刊

作者： Chen, Zhongxing ¹ ; Xue, Jie ³ ; Wang, Zheng ² ; Zhou, Yin ⁴ ; Deng, Xunfei ⁵ ; Liu, Feng ⁶ ; Song, Xiaodong ⁶ ; Zhang, Ganlin ⁶ ; Su, Yang ⁷ ; Zhu, Peng ⁹ ; Shi, Zhou ² ; Chen, Songchao ¹ ;

作者机构： 1.Zhejiang Univ, ZJU Hangzhou Global Sci & Technol Innovat Ctr, Hangzhou 311215, Peoples R China

2.Zhejiang Univ, Coll Environm & Resource Sci, Hangzhou 310058, Peoples R China

3.Zhejiang Univ, Dept Land Management, Hangzhou 310058, Peoples R China

4.Zhejiang Univ Finance & Econ, Sch Publ Adm, Hangzhou 310018, Peoples R China

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

6.Chinese Acad Sci, Inst Soil Sci, State Key Lab Soil & Sustainable Agr, Nanjing 210008, Peoples R China

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

8.Ecole Normale Super, Dept informat, PSL, F-75005 Paris, France

9.Univ Hong Kong, Dept Geog, Hong Kong 999077, Peoples R China

10.Univ Hong Kong, Inst Climate & Carbon Neutral, Hong Kong 999077, Peoples R China

关键词： Soil organic carbon stock; Variable selection; Machine learning; Land cover; National scale; Soil database

期刊名称：GEODERMA （ 影响因子：5.6； 五年影响因子：6.7 ）

ISSN： 0016-7061

年卷期： 2024 年 448 卷

页码：

收录情况： SCI

摘要： Understanding and managing soil organic carbon stocks (SOCS) are integral to ensuring environmental sustainability and the health of terrestrial ecosystems. The information of soil bulk density (BD) is important in accurately determining SOCS while it is often missing in the soil database. Using 3,504 soil profiles (14,170 soil samples) that represented diverse regions across China, we investigated the effectiveness of various pedotransfer functions (PTFs), including traditional PTFs, machine learning (ML), and ensemble model (EM), in predicting BD. The results showed that refitting the parameter(s) in traditional PTFs was essential for BD prediction (coefficient of determination (R 2 ) of 0.299 -0.432, root mean squared error (RMSE) of 0.156 -0.162 g cm-3 , Lin 's concordance coefficient (LCCC) of 0.428 -0.605). Compared to traditional PTFs, ML can greatly improve the model performance for BD prediction with R 2 of 0.425 -0.616, RMSE of 0.129 -0.158 g cm-3 and LCCC of 0.622 -0.765. Our results also showed that EM can further improve BD prediction by ensembling four ML models (R 2 = 0.630, RMSE = 0.126 g cm-3 , LCCC = 0.775). Using the EM model, we filled the missing BD (1207 soil profiles with 3,112 soil samples) in our database and built the SOC stock database (4,275 soil profiles with 17,282 soil samples). This study can be a good reference for gap-filling the missing BD depending on the data availability, thus contribute to a deeper understanding in soil C related climate change mitigation, ecological balance preservation and environmental sustainability promotion.