A dynamic soil endmember spectrum selection approach for soil and crop residue linear spectral unmixing analysis
文献类型： 外文期刊
作者： Yue, Jibo 1 ; Tian, Qingjiu 1 ; Tang, Shaofei 1 ; Xu, Kaijian 1 ; Zhou, Chengquan 3 ;
作者机构： 1.Nanjing Univ, Int Inst Earth Syst Sci, Nanjing 210023, Jiangsu, Peoples R China
2.Nanjing Univ, Jiangsu Prov Key Lab Geog Informat Sci & Technol, Nanjing 210023, Jiangsu, Peoples R China
3.Minist Agr China, Beijing Res Ctr Informat Technol Agr, Key Lab Quantitat Remote Sensing Agr, Beijing 100097, Peoples R China
关键词： Crop residue; Soil endmember; Soil moisture; Linear spectral unmixing analysis; Remote sensing
期刊名称：INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION （ 影响因子：5.933； 五年影响因子：6.225 ）
ISSN： 0303-2434
年卷期： 2019 年 78 卷
页码：
收录情况： SCI
摘要： Crop residue deposited on the soil surface helps protect against water and wind erosion, improve soil quality and increase soil organic matter and soil carbon storage. Linear spectral mixture analysis (LSMA) is an important technique in field crop residue estimation. Traditionally, only one single or fixed standard crop residue and soil endmember spectrum is performed for each of the presented endmember classes or field. Because the variation in soil endmember spectrum signatures significantly changes with soil moisture (SM), spectral unmixing with fixed endmember spectra can lead to poor accuracy of the abundance of the spectral constituents of pure crop residue. Herein, this paper presents a dynamic soil endmember spectrum selection approach for improving the performance of soil and rice residue spectral unmixing analysis in rice residue cover (RRC) estimation. This new approach uses SM and soil spectral reflectance model to modify soil endmember spectra in each spectral unmixing analysis. Two validation datasets computed results have verified the feasibility and correctness of the dynamic soil endmember method. Results indicated that the distribution of SM in farmland was crucial for RRC estimation. Compared with traditional fixed min and fixed mean soil endmember spectrum methods, the results of the method developed herein showed this method significantly improved RRC estimation accuracy for an SM content lower than 20% (volumetric water content) over the traditional methods tested. Therefore, our proposed approach can be used to improve RRC estimation accuracy in harvest field.
- 相关文献
作者其他论文 更多>>
-
Estimation of Peanut Southern Blight Severity in Hyperspectral Data Using the Synthetic Minority Oversampling Technique and Fractional-Order Differentiation
作者：Sun, Heguang;Shu, Meiyan;Yue, Jibo;Guo, Wei;Sun, Heguang;Zhang, Jie;Feng, Ziheng;Feng, Haikuan;Song, Xiaoyu;Zhou, Lin
关键词：peanut southern blight; SMOTE; hyperspectral reflectance; machine learning; FOD
-
Analyzing winter-wheat biochemical traits using hyperspectral remote sensing and deep learning
作者：Yue, Jibo;Wang, Jian;Guo, Wei;Ma, Xinming;Qiao, Hongbo;Yang, Guijun;Liu, Yang;Feng, Haikuan;Yue, Jibo;Yang, Guijun;Li, Changchun;Niu, Qinglin;Feng, Haikuan
关键词：Unmanned aerial vehicle; Transfer learning; Deep learning; Hyperspectral
-
Estimation of potato yield using a semi-mechanistic model developed by proximal remote sensing and environmental variables
作者：Fan, Yiguang;Liu, Yang;Chen, Riqiang;Bian, Mingbo;Ma, Yanpeng;Yang, Guijun;Feng, Haikuan;Fan, Yiguang;Yue, Jibo;Jin, Xiuliang;Feng, Haikuan
关键词：Potato; Yield; Remote sensing; Environmental variables
-
Estimating potato above-ground biomass based on vegetation indices and texture features constructed from sensitive bands of UAV hyperspectral imagery
作者：Liu, Yang;Fan, Yiguang;Feng, Haikuan;Chen, Riqiang;Bian, Mingbo;Ma, Yanpeng;Yang, Guijun;Liu, Yang;Yue, Jibo
关键词：UAV; Potato; AGB; Hyperspectral images; RF
-
Improving potato AGB estimation to mitigate phenological stage impacts through depth features from hyperspectral data
作者：Liu, Yang;Feng, Haikuan;Fan, Yiguang;Chen, Riqiang;Bian, Mingbo;Ma, Yanpeng;Li, Jingbo;Xu, Bo;Yang, Guijun;Liu, Yang;Liu, Yang;Feng, Haikuan;Yue, Jibo;Jin, Xiuliang
关键词：AGB; Hyperspectral features; Deep features; SPA; LSTM; PLSR
-
Pretrained Deep Learning Networks and Multispectral Imagery Enhance Maize LCC, FVC, and Maturity Estimation
作者：Hu, Jingyu;Feng, Hao;Shen, Jianing;Wang, Jian;Guo, Wei;Qiao, Hongbo;Yue, Jibo;Wang, Qilei;Liu, Yang;Liu, Yang;Feng, Haikuan;Yang, Hao;Niu, Qinglin;Niu, Qinglin
关键词：unmanned aerial vehicle; crop leaf chlorophyll content; fractional vegetation cover; maturity; deep learning; ensemble learning; maize
-
Improving potato above ground biomass estimation combining hyperspectral data and harmonic decomposition techniques
作者：Liu, Yang;Feng, Haikuan;Fan, Yiguang;Chen, Riqiang;Ma, Yanpeng;Bian, Mingbo;Yang, Guijun;Liu, Yang;Liu, Yang;Feng, Haikuan;Yue, Jibo
关键词：AGB; ASD; UHD185; Harmonic components; PLSR
