中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > Improving model performance in mapping cropland soil organic matter using time-series remote sensing data 农业科学学报 (英文) 2024,23 (8)
Position: Home > Articles > Improving model performance in mapping cropland soil organic matter using time-series remote sensing data Journal of Integrative Agriculture 2024,23 (8)

Improving model performance in mapping cropland soil organic matter using time-series remote sensing data

作  者：
Zhang, Xianglin;Xue, Jie;Chen, Songchao;Zhuo, Zhiqing;Wang, Zheng;Chen, Xueyao;Xiao, Yi;Shi, Zhou
单  位：
Minist Agr & Rural Affairs, Key Lab Spect Sensing, Hangzhou 310058, Peoples R China;Zhejiang Acad Agr Sci, Inst Digital Agr, Hangzhou 310021, Peoples R China;Zhejiang Univ, Inst Appl Remote Sensing & Informat Technol, Coll Environm & Resource Sci, Hangzhou 310058, Peoples R China;Zhejiang Univ, ZJU Hangzhou Global Sci & Technol Innovat Ctr, Hangzhou 311215, Peoples R China;Zhejiang Univ, Dept Land Management, Hangzhou 310058, Peoples R China
关键词：
cropland;soil organic matter;digital soil mapping;machine learning;feature selection;model averaging
摘  要：
Faced with increasing global soil degradation, spatially explicit data on cropland soil organic matter (SOM) provides crucial data for soil carbon pool accounting, cropland quality assessment and the formulation of effective management policies. As a spatial information prediction technique, digital soil mapping (DSM) has been widely used to spatially map soil information at different scales. However, the accuracy of digital SOM maps for cropland is typically lower than for other land cover types due to the inherent difficulty in precisely quantifying human disturbance. To overcome this limitation, this study systematically assessed a framework of "information extraction-feature selection-model averaging" for improving model performance in mapping cropland SOM using 462 cropland soil samples collected in Guangzhou, China in 2021. The results showed that using the framework of dynamic information extraction, feature selection and model averaging could efficiently improve the accuracy of the final predictions (R-2 : 0.48 to 0.53) without having obviously negative impacts on uncertainty. Quantifying the dynamic information of the environment was an efficient way to generate covariates that are linearly and nonlinearly related to SOM, which improved the R-2 of random forest from 0.44 to 0.48 and the R-2 of extreme gradient boosting from 0.37 to 0.43. Forward recursive feature selection (FRFS) is recommended when there are relatively few environmental covariates (<200), whereas Boruta is recommended when there are many environmental covariates (>500). The Granger-Ramanathan model averaging approach could improve the prediction accuracy and average uncertainty. When the structures of initial prediction models are similar, increasing in the number of averaging models did not have significantly positive effects on the final predictions. Given the advantages of these selected strategies over information extraction, feature selection and model averaging have a great potential for high-accuracy soil mapping at any scales, so this approach can provide more reliable references for soil conservation policy-making.

相似文章

PDF下载 PDF预览
导出引用
计量
文章访问数: 11
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46