|
|
|
|
|
|
Plant Litter Effect of the Soil Organic Carbon Estimation and Unmixing Method Based on the Visible-Near Infrared Spectra |
ZHAO Wei1, BAO Ni-sha1,2*, LIU Shan-jun1,2, MAO Ya-chun1,2, XIAO Dong2,3 |
1. College of Resources and Civil Engineering, Northeastern University, Shenyang 110819, China
2. Smart Mine Research Center, Northeastern University, Shenyang 110819, China
3. College of Information Science and Engineering, Northeastern University, Shenyang 110819, China |
|
|
Abstract In terms of the application of spectroscopy in-situ for soil quality monitoring from grassland, this paper takes the soil spectrum of Hulunbeier’s typical grassland as the research object. Verification by indoor simulated spectroscopy experiment and field spectrum measurement, and reveal the influence of plant litter on soil spectrum by analyzing the characteristics of mixed spectra. The blind source separation (BSS) independent component analysis (ICA) algorithm is used to separate the mixed spectra. Furthermore, spectral similarity value (SSV) is calculated to optimize BSS- ICA for unmixing soil spectra. The accuracy of the SOC prediction model before and after unmixing is compared to valid applicability of BSS-ICA algorithm. The results show that, (1) the cellulose absorption index (CAI) based on the characteristics of mixed spectra could effectively detect the extent of plant litter cover in the mixed spectra. CAI index would increase with the increasing of plant litter cover in quadratic regression; (2) It is found that a steep slope occurs at the transition band of 700 nm and weak lignin absorption characteristics in 1 680 and 1 754 nm, strong cellulose absorption occurs at 2 100 nm from mixed spectra; The SOC would be overestimated by about 11.94% using SVM prediction model once soil surface covered by only 5% plant litter. (3) The unmixing method of BSS-ICA can reduce the spectral characteristic from plant litter effect, and using partial least squares (PLSR), support vector machine (SVM) and random forest (RF) to model the prediction of organic carbon before and after unmixing. SVM has the highest accuracy among the three methods. The accuracy of SOC prediction was improved from R2 of 0.71 before unmixing to 0.75 after unmixing, RMSE of 4.82 g·kg-1 before unmixing to 4.50 g·kg-1 after unmixing. The optimized BSS-ICA algorithm can effectively separate soil from mixed spectra with litter and might improve the accuracy of SOC estimation by field spectra. This experimental study of reducing the external factors on soil spectra provides a theoretical basis for SOC prediction based on in-situ measurement of soil spectra.
|
Received: 2019-06-26
Accepted: 2019-10-08
|
|
Corresponding Authors:
BAO Ni-sha
E-mail: baonisha@hotmail.com
|
|
[1] HONG Yong-sheng, ZHU Ya-xing, SU Xue-ping,et al(洪永胜, 朱亚星, 苏学平,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017,37(11).
[2] Yin Z, Hartemink A E, Zhou S, et al. Science of The Total Environment, 2019, 647: 1230.
[3] Bao N, Wu L, Ye B, et al. Geoderma, 2017, 288: 47.
[4] SHI Zhou, XU Dong-yun, TENG Hong-fen,et al(史 舟, 徐冬云, 滕洪芬,等). Progress in Geography(地理科学进展), 2018,37(1):79.
[5] Rodionov A, Patzold S, Welp G, et al. Soil and Tillage Research,2016,163: 89.
[6] LIU Shan-jun, ZHUO Jian-ying, WU Li-xin,et al(刘善军, 卓建英, 吴立新,等). Science & Technology Review, 2011, 29(35): 24.
[7] TONG Qing-xi, ZHANG Bing, ZHENG Lan-fen(童庆禧, 张 兵, 郑兰芬). Hyperspectral Remote Sensing: Technology and Application(高光谱遥感: 原理, 技术与应用). Beijing: Higher Education Press(北京: 高等教育出版社), 2006.
[8] Ouerghemmi W, Gomez C, Naceur S, et al. Geoderma, 2011, 163(3/4): 227.
[9] LIU Ya, PAN Xian-zhang, SHI Rong-jie, et al(刘 娅, 潘贤章, 石荣杰,等). Acta Pedologica Sinica(土壤学报), 2016, 53(2):322.
[10] SHI Zhou(史 舟). Principle and Method of Soil Surface Hyperspectral Remote Sensing(土壤地面高光谱遥感原理与方法). Beijing: China Science Publishing & Media Ltd.(北京: 中国科技出版传媒股份有限公司), 2014.
[11] ZHAO Chun-hui, TIAN Ming-hua, LI Jia-wei,et al(赵春晖, 田明华, 李佳伟,等). Journal of Harbin Engineering University(哈尔滨工程大学学报), 2017, 38(8): 1179.
[12] Nagler P L, Daughtry C S T, Goward S N. Remote Sensing of Environment, 2000, 71(2): 207.
[13] Rodionov A, Welp G, Damerow L, et al. Soil and Tillage Research, 2015, 145: 93.
[14] WANG He-xin, LI Gen-zhu, YU Dong-mei, et al(王贺新,李根柱,于冬梅,等). Chinese Journal of Ecology(生态学杂志),2008,27(1):83. |
[1] |
XU Tian1, 2, LI Jing1, 2, LIU Zhen-hua1, 2*. Remote Sensing Inversion of Soil Manganese in Nanchuan District, Chongqing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 69-75. |
[2] |
LI Hu1, ZHONG Yun1, 2, FENG Ya-ting1, LIN Zhen1, ZHU Shi-jiang1, 2*. Multi-Vegetation Index Soil Moisture Inversion Model Based on UAV
Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 207-214. |
[3] |
HAN Xue1, 2, LIU Hai1, 2, LIU Jia-wei3, WU Ming-kai1, 2*. Rapid Identification of Inorganic Elements in Understory Soils in
Different Regions of Guizhou Province by X-Ray
Fluorescence Spectrometry[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 225-229. |
[4] |
CHENG Hui-zhu1, 2, YANG Wan-qi1, 2, LI Fu-sheng1, 2*, MA Qian1, 2, ZHAO Yan-chun1, 2. Genetic Algorithm Optimized BP Neural Network for Quantitative
Analysis of Soil Heavy Metals in XRF[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3742-3746. |
[5] |
MENG Shan1, 2, LI Xin-guo1, 2*. Estimation of Surface Soil Organic Carbon Content in Lakeside Oasis Based on Hyperspectral Wavelet Energy Feature Vector[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3853-3861. |
[6] |
LI Qi-chen1, 2, LI Min-zan1, 2*, YANG Wei2, 3, SUN Hong2, 3, ZHANG Yao1, 3. Quantitative Analysis of Water-Soluble Phosphorous Based on Raman
Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3871-3876. |
[7] |
XIE Peng, WANG Zheng-hai*, XIAO Bei, CAO Hai-ling, HUANG Yi, SU Wen-lin. Hyperspectral Quantitative Inversion of Soil Selenium Content Based on sCARS-PSO-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3599-3606. |
[8] |
HUANG Zhao-di1, CHEN Zai-liang2, WANG Chen3, TIAN Peng2, ZHANG Hai-liang2, XIE Chao-yong2*, LIU Xue-mei4*. Comparing Different Multivariate Calibration Methods Analyses for Measurement of Soil Properties Using Visible and Short Wave-Near
Infrared Spectroscopy Combined With Machine Learning Algorithms[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3535-3540. |
[9] |
AN Bai-song1, 2, WANG Xue-mei1, 2*, HUANG Xiao-yu1, 2, KAWUQIATI Bai-shan1, 2. Hyperspectral Estimation of Soil Lead Content Based on Random Frog Band Selection Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3302-3309. |
[10] |
DENG Yun1, 2, NIU Zhao-wen1, 2, FENG Qi-yao1, 2, WANG Yu1, 2*. A Novel Hyperspectral Prediction Model of Organic Matter in Red Soil Based on Improved Temporal Convolutional Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2942-2951. |
[11] |
WANG Jin-hua, DAI Jia-le*, LI Meng-qian, LIU Wei, MIAO Ruo-fan. Blind Separation Algorithm of Mixed Minerals Hyperspectral Base on NMF Mode[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2458-2466. |
[12] |
CAI Hai-hui1, ZHOU Ling2, SHI Zhou3, JI Wen-jun4, LUO De-fang1, PENG Jie1, FENG Chun-hui5*. Hyperspectral Inversion of Soil Organic Matter in Jujube Orchard
in Southern Xinjiang Using CARS-BPNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2568-2573. |
[13] |
XIA Chen-zhen1, 2, 3, JIANG Yan-yan4, ZHANG Xing-yu1, 2, 3, SHA Ye5, CUI Shuai1, 2, 3, MI Guo-hua5, GAO Qiang1, 2, 3, ZHANG Yue1, 2, 3*. Estimation of Soil Organic Matter in Maize Field of Black Soil Area Based on UAV Hyperspectral Image[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2617-2626. |
[14] |
ZHANG Zi-hao1, GUO Fei3, 4, WU Kun-ze1, YANG Xin-yu2, XU Zhen1*. Performance Evaluation of the Deep Forest 2021 (DF21) Model in
Retrieving Soil Cadmium Concentration Using Hyperspectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2638-2643. |
[15] |
ZHANG Xia1, WANG Wei-hao1, 2*, SUN Wei-chao1, DING Song-tao1, 2, WANG Yi-bo1, 2. Soil Zn Content Inversion by Hyperspectral Remote Sensing Data and Considering Soil Types[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2019-2026. |
|
|
|
|