Improving model parsimony and accuracy by modified greedy feature selection in digital soil mapping
文献类型: 外文期刊
作者: Zhang, Xianglin 1 ; Chen, Songchao 1 ; Xue, Jie 3 ; Wang, Nan 2 ; Xiao, Yi 2 ; Chen, Qianqian 2 ; Hong, Yongsheng 2 ; Zhou, Yin 4 ; Teng, Hongfen 5 ; Hu, Bifeng 6 ; Zhuo, Zhiqing 7 ; Ji, Wenjun 8 ; Huang, Yuanfang 8 ; Gou, Yuxuan 8 ; Richer-de-Forges, Anne C. 9 ; Arrouays, Dominique 9 ; Shi, Zhou 2 ;
作者机构: 1.ZJU Hangzhou Global Sci & Technol Innovat Ctr, Hangzhou 311200, Peoples R China
2.Zhejiang Univ, Inst Appl Remote Sensing & Informat Technol, 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, Inst Land & Urban Rural Dev, Hangzhou 310018, Peoples R China
5.Wuhan Inst Technol, Sch Environm Ecol & Biol Engn, Wuhan 430205, Peoples R China
6.Jiangxi Univ Finance & Econ, Sch Tourism & Urban Management, Dept Land Resource Management, Nanchang 330013, Peoples R China
7.Zhejiang Acad Agr Sci, Inst Digital Agr, Hangzhou 310021, Peoples R China
8.China Agr Univ, Coll Land Sci & Technol, Beijing 100193, Peoples R China
9.INRAE, Unite InfoSol, F-45075 Orleans, France
关键词: Digital soil mapping; Variable selection; Quantile regression forests; Computation efficiency; Northeast and North China
期刊名称:GEODERMA ( 影响因子:6.1; 五年影响因子:7.0 )
ISSN: 0016-7061
年卷期: 2023 年 432 卷
页码:
收录情况: SCI
摘要: In the context of increasing soil degradation worldwide, spatially explicit soil information is urgently needed to support decision-making for sustaining limited soil resources. Digital soil mapping (DSM) has been proven as an efficient way to deliver soil information from local to global scales. The number of environmental covariates used for DSM has rapidly increased due to the growing volume of remote sensing data, therefore variable selection is necessary to deal with multicollinearity and improve model parsimony. Compared with Boruta, recursive feature elimination (RFE), and variance inflation factor (VIF) analysis, we proposed the use of modified greedy feature selection (MGFS), for DSM regression. For this purpose, using quantile regression forest, 402 soil samples and 392 environmental covariates were used to map the spatial distribution of soil organic carbon density (SOCD) in Northeast and North China. The result showed that MGFS selected the most parsimonious model with only 9 covariates (e.g., brightness index, mean annual temperature), much lower than RFE (22 covariates), VIF (30 covariates), and Boruta (76 covariates). The repeated validation (50 times) showed that the MGFS derived model performed better (R2 of 0.60, LCCC of 0.74, RMSE of 13.80 t ha -1) than these using full covariates, Boruta, RFE and VIF (R2 of 0.48-0.57, LCCC of 0.64-0.72, RMSE of 14.24-15.79 t ha -1). Despite the similar performance of the uncertainty estimate (PICP), the model using MGFS and RFE had the lowest global uncertainty (0.86) as indicated by the uncertainty index. In addition, MGFS had the best computation efficiency when considering the steps of variable selection and map prediction. Given these advantages over Boruta, RFE and VIF, MGFS has a high potential in fine-resolution soil mapping practices, especially for these studies at a broad scale involving heavy computation on millions or billions of pixels.
- 相关文献
作者其他论文 更多>>
-
Potential of globally distributed topsoil mid-infrared spectral library for organic carbon estimation
作者:Hong, Yongsheng;Hong, Yongsheng;Sanderman, Jonathan;Hengl, Tomislav;Chen, Songchao;Wang, Nan;Xue, Jie;Shi, Zhou;Zhuo, Zhiqing;Peng, Jie;Li, Shuo;Chen, Yiyun;Liu, Yaolin;Mouazen, Abdul Mounem;Mouazen, Abdul Mounem
关键词:Soil monitoring; Mid-infrared spectroscopy; Soil spectral library; Fractional-order derivative; Deep learning
-
Preparation and activity evaluation of angiotensin-I converting enzyme inhibitory peptides from protein hydrolysate of mulberry leaf
作者:Chen, Yu;Jiao, Yingchun;Chen, Yu;Zhang, Yu;Qi, Qianhui;Liang, Feng;Li, Xue;Sun, Suling;Wang, Xinquan;Wang, Wei;Zhang, Yu;Li, Xue;Zhang, Yu;Li, Xue;Liang, Feng;Wang, Nan;Chen, Qihe;Bai, Kaiwen;Wang, Wei
关键词:mulberry leaf protein; hydrolysate; angiotensin-I converting enzyme (ACE); inhibitory peptides; molecular docking
-
Spectral fusion modeling for soil organic carbon by a parallel input-convolutional neural network
作者:Hong, Yongsheng;Wang, Nan;Xue, Jie;Shi, Zhou;Chen, Songchao;Hu, Bifeng;Zhuo, Zhiqing;Yang, Yuanyuan;Chen, Yiyun;Liu, Yaolin;Peng, Jie;Mouazen, Abdul Mounem;Mouazen, Abdul Mounem
关键词:Soil analysis; Visible-to-near-infrared spectroscopy; Mid-infrared spectroscopy; Data fusion; Deep learning
-
Effects of in vitro fermentation of Atractylodes chinensis (DC.) Koidz. polysaccharide on fecal microbiota and metabolites in patients with type 2 diabetes mellitus
作者:Zhang, Xin;Ma, Qian;Jia, Lina;He, Hongpeng;Zhang, Tongcun;Qi, Wei;Wang, Nan;Zhang, Xin;Ma, Qian;Jia, Lina;He, Hongpeng;Zhang, Tongcun;Qi, Wei;Wang, Nan;Jia, Weiguo;Zhu, Liying
关键词:Type 2 diabetes mellitus; Fecal microbiota; Metabolites; Atractylodes chinensis (DC.) Koidz.
-
Fine Resolution Mapping of Soil Organic Carbon in Croplands with Feature Selection and Machine Learning in Northeast Plain China
作者:Zhang, Xianglin;Zhuo, Zhiqing;Zhang, Xianglin;Wang, Nan;Xie, Tieli;Xiao, Yi;Chen, Xueyao;Shi, Zhou;Xue, Jie;Chen, Songchao;Shi, Zhou;Huang, Yuanfang
关键词:soil organic carbon; digital soil mapping; quantile Regression Forest; feature selection
-
Scale-Location Dependence Relationship between Soil Organic Matter and Environmental Factors by Anisotropy Analysis and Multiple Wavelet Coherence
作者:Gou, Yuxuan;Liu, Dong;Liu, Xiangjun;Shen, Chongyang;Liu, Yunjia;Huang, Yuangfang;Zhuo, Zhiqing;Cao, Meng
关键词:soil organic matter; anisotropy analysis; multiple wavelet coherence; multiple environmental factors
-
Significant loss of soil inorganic carbon at the continental scale
作者:Song, Xiao-Dong;Yang, Fei;Wu, Hua-Yong;Zhang, Jing;Li, De-Cheng;Liu, Feng;Zhao, Yu-Guo;Yang, Jin-Ling;Ju, Bing;Huang, Biao;Zhang, Gan-Lin;Zhang, Jing;Zhao, Yu-Guo;Yang, Jin-Ling;Zhang, Gan-Lin;Cai, Chong-Fa;Chen, Jia-Ying;Wang, Tian-Wei;Long, Huai-Yu;Chen, Yin-Jun;Lu, Ying;Sui, Yue-Yu;Wang, Qiu-Bing;Han, Chun-Lan;Sun, Fu-Jun;Wu, Ke-Ning;Zhang, Feng-Rong;Zhang, Ming-Kui;Shi, Zhou;Ma, Wan-Zhu;Xin, Gang;Qi, Zhi-Ping;Wang, Deng-Feng;Chang, Qing-Rui;Ci, En;Yuan, Da-Gang;Zhang, Yang-Zhu;Zhou, Qing;Bai, Jun-Ping;Chen, Jie;Dong, Yun-Zhong;Li, Ling;Liu, Li-Ming;Pan, Jian-Jun;Song, Fu-Peng;Wei, Xiang-Hua;Wu, Hong-Qi;Zhao, Xia;Zhang, Gan-Lin
关键词:China; soil inorganic carbon stocks; global change; carbonate; soil acidification