文献类型： 外文期刊

作者： Zhou, Tao ¹ ; Lv, Wenhao ¹ ; Geng, Yajun ¹ ; Xiao, Shancai ⁴ ; Chen, Jie ⁵ ; Xu, Xiangrui ⁶ ; Pan, Jianjun ⁷ ; Si, Bingcheng ¹ ; Lausch, Angela ² ;

作者机构： 1.Ludong Univ, Sch Resources & Environm Engn, Middle Hongqi Rd 186, Yantai 264025, Peoples R China

2.Humboldt Univ, Dept Geog, Unter Linden 6, D-10099 Berlin, Germany

3.Helmholtz Ctr Environm Res, Dept Comp Landscape Ecol, Permoserstr 15, D-04318 Leipzig, Germany

4.Peking Univ, Coll Urban & Environm Sci, Yiheyuan Rd 5, Beijing 100871, Peoples R China

5.Hunan Acad Agr Sci, Yuanda 2nd Rd 560, Changsha 410125, Peoples R China

6.Zhejiang Univ City Coll, Sch Spatial Planning & Design, Huzhou St 51, Hangzhou, Peoples R China

7.Nanjing Agr Univ, Coll Resources & Environm Sci, Weigang 1, Nanjing 210095, Peoples R China

8.Univ Saskatchewan, Dept Soil Sci, Saskatoon, SK S7N 5A8, Canada

关键词： Digital soil mapping; Cloud computing; Soil properties; Sentinel-1; Sentinel-2

期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.3； 五年影响因子：8.3 ）

ISSN： 0168-1699

年卷期： 2023 年 210 卷

页码：

收录情况： SCI

摘要： Modeling accurate and detailed soil spatial information is essential for environmental modeling, precision soil management and decision-making. In this study, we integrated long-term optical (Sentinel-2) and radar (Sentinel-1) satellite observations via the Google Earth Engine (GEE) platform for high-resolution national-scale digital mapping of soil organic carbon (SOC) and total soil nitrogen (TSN) in Austria. Our soil predictive models based on boosted regression tree (BRT) and regression kriging (RK) methods were constructed from 449 soil samples (0-20 cm) covering the study area in the LUCAS soil database and Sentinel observations synthesized with different time intervals. The different input predictors of these soil predictive models resulted in seven modeling scenarios, and their prediction performance was evaluated by a cross-validation technique. Comparative analysis indicated that satellite sensors, modeling techniques, and SAR data acquisition configurations greatly affected the model outputs. Cross-polarization and co-polarization had similar performance in TSN and SOC predictions, and their combination improved the prediction accuracy. Predictive models based on Sentinel-1 with the "ASCENDING" orbits outperformed the models involving the "DESCENDING" orbits; the prediction accuracy of the former was comparable to models involving two orbital data. The models built by Sentinel-1 and Sentinel-2 performed similarly in predicting SOC (R2 = 0.51 vs. R2 = 0.52, respectively) and TSN (their R2 were both 0.42); their synergistic utilization improved the prediction results. Models involving more years of Sentinel observations on the GEE platform provided more accurate modeling results. The best soil predictive models explained 55% and 45% of soil variability for SOC and TSN, respectively, both constructed from long-term Sentinel-1/2 observations using the RK method. The overall trends of the mapping results of the models constructed by Sentinel-1 and Sentinel-2 and their combinations were consistent. The predicted digital soil maps displayed high spatial heterogeneity: SOC and TSN-shared similar spatial patterns-were greater in highaltitude central and western regions than other regions. This study provides valuable information for revealing the effects of satellite sensors, modeling techniques and SAR configurations on mapping SOC and TSN.