Assessment of important soil properties related to Chinese Soil Taxonomy based on vis-NIR reflectance spectroscopy
文献类型: 外文期刊
第一作者: Xu, Dongyun
作者: Xu, Dongyun;Jiang, Qingsong;He, Kang;Shi, Zhou;Ma, Wanzhu;Chen, Songchao;Chen, Songchao;Jiang, Qingsong
作者机构:
关键词: vis-NIR spectroscopy;Soil properties;Chinese Soil Taxonomy;PLSR;Selectivity ratio
期刊名称:COMPUTERS AND ELECTRONICS IN AGRICULTURE ( 影响因子:5.565; 五年影响因子:5.494 )
ISSN: 0168-1699
年卷期: 2018 年 144 卷
页码:
收录情况: SCI
摘要: As a rapid, inexpensive and accurate analysis technique, vis-NIR spectra has shown great advantages for determining a wide variety of soil properties, such as soil organic matter content, mineral composition, water content, particle size and color. Thus, this technique is becoming increasingly popular in soil science. We aim to assess the applicability of using vis-NIR spectra to estimate eighteen different soil properties that are important for Chinese Soil Taxonomy (CST). In this study, vis-NIR reflectance spectra were measured under laboratory conditions. First, partial least-squares regression (PLSR) was used to predict the following soil properties related to soil classification: coarse crumb, sand, silt, and clay contents, bulk density (BD), pH (H2O), pH (KCl), soil organic matter (SOM), total nitrogen (TN), total potassium (TIC), and total phosphorus (TP) contents, cation exchange capacity (CEC), free iron (Fe2O3), soluble salts (salt), available phosphorus (AP), exchangeable aluminum (ExAl), aluminum saturation (AS) and base saturation (BS). Then, the important bands for modeling these soil properties were selected based on the selectivity ratio (SR). Finally, the spectral chromophores of the soil and the correlations of soil properties were analyzed. The results showed that (1) the prediction accuracy based on the PLSR algorithm was good for pH, SOM, TN, Fe2O3, salt, AS and BS (RPD > 2.0, R-2 between 0.70 and 0.90). For sand, silt, clay, BD, TP, TK, CEC, AP and ExAl, the PLSR model could achieve acceptable estimates (1.4 < RPD < 2.0, R-2 between 0.56 and 0.72), while for coarse crumb, the PLSR model was unable to make reliable predictions (RPD < 1.4, R2 below 0.50). (2) As chromophore properties, SOM, TN, Fe2O3, clay and salt are and can be predicted by spectroscopy. Besides, BD, pH, TK, TP, CEC, AP, ExAl, AS and BS have significant correlations with chromophore properties and can also be predicted by vis-NIR spectroscopy. Therefore, except for coarse crumb, the soil properties important to CST can be quantitatively predicted by PLSR based on vis-NIR reflectance spectroscopy. This study is significant to CST, and it provides a fast and efficient method for soil classification.
分类号:
- 相关文献
作者其他论文 更多>>
-
Spatiotemporal patterns and driving factors of gross primary productivity over the Mongolian Plateau steppe in the past 20 years
作者:Ding, Lei;Shi, Zhou;Chang, Jinfeng;Li, Zhenwang;Li, Zhenwang;Ding, Lei;Wang, Xu;Shen, Beibei;Shao, Changliang;Xiao, Liujun;Dong, Gang;Yu, Lu;Yu, Lu;Nandintsetseg, Banzragch;Nandintsetseg, Banzragch
关键词:Gross primary productivity; Mongolian Plateau; Grassland; Climatic factors; Human activity
-
Improvement of Winter Wheat Aboveground Biomass Estimation Using Digital Surface Model Information Extracted from Unmanned-Aerial-Vehicle-Based Multispectral Images
作者:Guo, Yan;He, Jia;Zhang, Huifang;Wei, Panpan;Jing, Yuhang;Yang, Xiuzhong;Zhang, Yan;Wang, Laigang;Zheng, Guoqing;Guo, Yan;He, Jia;Zhang, Huifang;Wei, Panpan;Jing, Yuhang;Yang, Xiuzhong;Zhang, Yan;Zheng, Guoqing;Guo, Yan;Yang, Xiuzhong;Zhang, Yan;Zheng, Guoqing;Shi, Zhou;Wang, Laigang
关键词:aboveground biomass; UAV; height; transferability; BP neural network; machine learning
-
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
-
Using process-oriented model output to enhance machine learning-based soil organic carbon prediction in space and time
作者:Zhang, Lei;Yang, Lin;Zhang, Lei;Heuvelink, Gerard B. M.;Mulder, Vera L.;Heuvelink, Gerard B. M.;Chen, Songchao;Deng, Xunfei;Yang, Lin
关键词:Hybrid modelling; Mechanistic knowledge-guided machine; learning; RothC; Random forest; Digital soil mapping; Soil carbon dynamics
-
A water stress factor based on normalized difference water index substantially improved the accuracy of light use efficiency model for arid and semi-arid grasslands
作者:Ding, Lei;Shi, Zhou;Guo, Kaiwen;Chang, Jinfeng;Li, Zhenwang;Li, Zhenwang;Xu, Kang;Huang, Mengtian;Ding, Lei;Shen, Beibei;Hou, Lulu;Wang, Xu;Xin, Xiaoping;Xiao, Liujun;Liang, Shefang;Yang, Yuanyuan
关键词:gross primary productivity; grassland; light use efficiency model; water stress; fraction of absorbed photosynthetically active; radiation; aridity gradient
-
A refined edge-aware convolutional neural networks for agricultural parcel delineation
作者:Lu, Rui;Zhang, Yingfan;Shi, Zhou;Ye, Su;Huang, Qiting;Ye, Su
关键词:Agricultural parcels; Convolutional neural networks; Edge detection; Deep supervision; Boundary refinement
-
Improving model performance in mapping cropland soil organic matter using time-series remote sensing data
作者:Zhang, Xianglin;Chen, Songchao;Wang, Zheng;Chen, Xueyao;Xiao, Yi;Shi, Zhou;Xue, Jie;Chen, Songchao;Zhuo, Zhiqing;Shi, Zhou
关键词:cropland; soil organic matter; digital soil mapping; machine learning; feature selection; model averaging