|
|
|
|
|
|
| The Effect of Spectral Pretreatment on the LSSVM Model of Nitrogen in Intertidal Sediments |
| LÜ Mei-rong1, REN Guo-xing1, 2, LI Xue-ying1, FAN Ping-ping1, LIU Jie1, SUN Zhong-liang1, HOU Guang-li1, LIU Yan1* |
1. Institute of Oceanographic Instrmentation，Qilu University of Technology (Shandong Academy of Sciences)，Shandong Provincial Key Laboratory of Marine Monitoring Instrument Equipment Technology，National Engineering and Technological Research Center of Marine Monitoring Equipment, Qingdao 266100, China
2. School of Information Science and Engineering, Ocean University of China, Qingdao 266100, China |
|
|
|
|
Abstract Spectral data transformation and feature wavelength extraction are two important spectral pretreatment methods, which play an important role in eliminating environmental interference. Previous literature mainly compared different spectral data transformation methods and there was less studyon the spectral feature wavelength extraction methods and the combination of the two methods. In order to obtain suitable spectral pretreatment method and improve the accuracy of LSSVM model of sediment nitrogen in the intertidal zone, the effect of 4 spectral transformation methods combined with 3 characteristic wavelength extraction methods on the accuracy of LSSVM model of sediment nitrogen is studied for accurate prediction of sediment nitrogen in the intertidal zone. The results showed that the spectral transformation methods of multivariate scattering correction (MSC) or normal distribution (SVN) increasedthe correlation between spectra and nitrogen content and the highest correlation reached 0.69 and 0.71 respectively. MSC and SVN improved the prediction accuracy of LSSVM model, and the prediction R2 and RPD are 0.88, 0.87 and 2.78, 2.69, respectively. The feature wavelength extraction method of uninformative variable elimination (UVE) also improved the prediction accuracy of LSSVM model, model test R2 and RPD were 0.89 and 2.70, respectively. However, not all of the characteristic wavelengths extracted by UVE have a high correlation with nitrogen content. In addition, the combination of UVE and MSC or SVN also improved the prediction accuracy of the model, but it is not better than UVE alone or MSC or SVN alone. The results of this paper can provide a technical reference for nitrogen estimation and spectral data preprocessing of intertidal sediments.
|
|
Received: 2019-07-08
Accepted: 2019-11-12
|
|
|
|
Corresponding Authors:
LIU Yan
E-mail: sdqdliuyan@126.com
|
|
[1] REN Hong-yan, SHI Xue-zheng, ZHUANG Da-fang, et al(任红艳, 史学正, 庄大方, 等). Remote Sensing Technology and Application(遥感技术与应用), 2012, 27: 372.
[2] NIE Jia-qin, WANG Dong-qi, CHEN Jie, et al(聂家琴, 王东启, 陈 杰, 等). Environmental Science(环境科学), 2018, 39: 4219.
[3] SHEN Zhang-quan, YE Ling-bin, SHAN Ying-jie(沈掌泉, 叶领宾, 单英杰). Acta Pedologica Sinica(土壤学报), 2014, 51: 1011.
[4] ZHANG Rui, LI Zhao-fu, PAN Jian-jun(张 锐, 李兆富, 潘剑君). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017, 33: 175.
[5] FAN Chang-sheng, LIU Ze-zhao, GUO Qiang, et al(范昌胜, 刘泽照, 郭 强, 等). Journal of Taiyuan University of Science and Technology(太原科技大学学报), 2019, 40: 159.
[6] SUN Biao, YANG Zhi-yan, ZHAO Sheng-nan, et al(孙 标，杨志岩，赵胜男，等). Soil and Fertilizer Sciences in China(中国土壤与肥料), 2019, (2)：194.
[7] CUI Xia, SONG Qing-jie, ZHANG Yao-yao, et al(崔 霞, 宋清洁, 张瑶瑶, 等). Acta Prataculturae Sinica(草业学报), 2017, 10: 20.
[8] ZHOU Qing, ZHOU Bin, ZHANG Yang-zhu, et al(周 清, 周 斌, 张杨珠, 等). Acta Pedologica Sinica(土壤学报), 2004, 41(6): 905.
[9] YANG Hong-fei, ZHENG Li-ming, HAO Zhong-yao, et al(杨红飞, 郑黎明, 郜中要, 等). Journal of Anhui Agricultural University(安徽农业大学学报), 2018, 45(1): 101.
[10] LIANG Meng-xing, DAI Jun, HAN Bang-xing, et al(梁梦醒, 戴 军, 韩邦兴, 等). Journal of West Anhui University(皖西学院学报), 2017, 33: 1. |
| [1] |
LI Xin-ting, ZHANG Feng, FENG Jie*. Convolutional Neural Network Combined With Improved Spectral
Processing Method for Potato Disease Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 215-224. |
| [2] |
LIU Yu-juan1, 2, 3 , LIU Yan-da1, 2, 3, SONG Ying1, 2, 3*, ZHU Yang1, 2, 3, MENG Zhao-ling1, 2, 3. Near Infrared Spectroscopic Quantitative Detection and Analysis Method of Methanol Gasoline[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1489-1494. |
| [3] |
CAI Yu1, 2, ZHAO Zhi-fang3, GUO Lian-bo4, CHEN Yun-zhong1, 2*, JIANG Qiong4, LIU Si-min1, 2, ZHANG Cong-zi4, KOU Wei-ping5, HU Xiu-juan5, DENG Fan6, HUANG Wei-hua7. Research on Origin Traceability of Rhizoma Dioscoreae Based on LIBS[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 138-144. |
| [4] |
XU Lu1, CHEN Yi-yun1, 2, 3*, HONG Yong-sheng1, WEI Yu1, GUO Long4, Marc Linderman5. Estimation of Soil Organic Carbon Content by Imaging Spectroscopy With Soil Roughness[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2788-2794. |
| [5] |
YANG Jie-kai1, GUO Zhi-qiang1, HUANG Yuan2, 3*, GAO Hong-sheng1, JIN Ke1, WU Xiang-shuai2, YANG Jie1. Early Classification and Detection of Melon Graft Healing State Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(07): 2218-2224. |
| [6] |
HE Nian, SHAN Peng*, HE Zhong-hai, WANG Qiao-yun, LI Zhi-gang, WU Zhui. Study on the Fractional Baseline Correction Method of ATR-FTIR
Spectral Signal in the Fermentation Process of Sodium Glutamate[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1848-1854. |
| [7] |
XU Bo1, XU Tong-yu1, 2*, YU Feng-hua1, 2, ZHANG Guo-sheng1, FENG Shuai1, GUO Zhong-hui1, ZHOU Chang-xian1. Inversion Method for Cellulose Content of Rice Stem in Northeast Cold Region Based on Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(06): 1775-1781. |
| [8] |
LI Qing-bo1, BI Zhi-qi1, SHI Dong-dong2. The Method of Fishmeal Origin Tracing Based on EDXRF Spectrometry Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(03): 745-749. |
| [9] |
LI Xin-xing1, LIANG Bu-wen1, BAI Xue-bing1, LI Na2*. Research Progress of Spectroscopy in the Detection of Soil Moisture Content[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(12): 3705-3710. |
| [10] |
LÜ Mei-rong1, REN Guo-xing1, 2, LI Xue-ying1, FAN Ping-ping1, SUN Zhong-liang1, HOU Guang-li1, LIU Yan1*. Prediction of Organic Carbon Content of Intertidal Sediments Based on Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(04): 1082-1086. |
| [11] |
LUO Long-qiang1, YAO Xin-li1, HE Sai-ling1, 2*. Study on the Method of Determining the Survival Rate of Rice Seeds Based on Visible-Near Infrared Multispectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(01): 221-226. |
| [12] |
HAO Yong1, SHANG Qing-yuan1, RAO Min2, HU Yuan2. Identification of Wood Species Based on Near Infrared Spectroscopy and Pattern Recognition Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(03): 705-710. |
| [13] |
MENG Fan-long1, PAN Jing-chang1*, YU Jing-jing1, WEI Peng2. An Automatic Detection and Classification Method of the Splicing Abnormality in the Stellar Spectra for LAMOST[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(07): 2250-2253. |
| [14] |
WANG Wei-wei1, 2, 3, WEI Wei-wei1, 2, 3, SONG Xiang-gang1, 2, 3, CHENG Ya-ting4, CHEN Chao1, 2, 3*, WANG Shu-mei1, 2, 3*, LIANG Sheng-wang1, 2, 3. Effects of Different Pretreatment Methods on the Phenylketonuria Screening Model by FTIR/ATR Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(05): 1218-1221. |
| [15] |
LEI Meng1, LI Ming1*, WU Nan2, LI Ying-na3, CHENG Yu-hu1 . Influence of Different Coal Particle Sizes on Near-Infrared Spectral Quantitative Analytical Models[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(01): 65-68. |
|
|
|
|
