Estimation of Soil Organic Matter in Coastal Wetlands by SVM and BP Based on Hyperspectral Remote Sensing
ZHANG Sen1, LU Xia1*, NIE Ge-ge2, LI Yu-rong1, SHAO Ya-ting1, TIAN Yan-qin1, FAN Li-qiang1, ZHANG Yu-juan1
1. School of Geomatics and Marine Information, Jiangsu Ocean University, Lianyungang 222005, China
2. School of Resources and Environment, Henan University of Economics and Law, Zhengzhou 450046, China
Abstract：In recent years, although the nutrient content in the soil can be quickly obtained with the emergence of hyperspectral technology, but different soil types have great differences in the accuracy of estimation. The soil type of coastal wetland is greatly affected by the marine environment, and its hyperspectral reflectance and inland soil type will be different. This will reduce the precision in the same estimation model when inverting the nutrient content of coastal wetland soil types. With the development of marine resources and the ecological restoration of coastal wetlands in recent years, it is urgent to explore a suitable estimation model to quickly and accurately obtain nutrient content in soil. This study aimed to verify the use of visible-near infrared hyperspectral reflectivity to construct a nonlinear model so as to invert the feasibility of organic matter (SOM) in coastal wetland soils. The topsoil in the third core area of Dafeng Elk National Nature Reserve in Yancheng, Jiangsu province was taken as the investigated object. The sensitive bands corresponding to Soil Organic Matter (SOM) content were retrieved based on correlation coefficient after 5 point S-G filtering and four differential transformations of R′, (1/R)′, (1/R)″, (lgR)′ by spectral reflectance of soil samples. The estimation models of SOM by Support Vector Machine (SVM) and BP neural network were determined, and the prediction accuracy of the model was verified by using the decision coefficient R2 and the root mean square error RMSE. The research results indicated that the effective bands can be identified by S-G filtering, differential transformation and correlation coefficient method based on the original spectra of soil samples. The characteristic bands of SOM based on transformations (1/R)′ were 498~501, 1 180~1 182, 1 946, 1 947, 2 323～2 326 nm. Estimation accuracy of SVM was better than that of BP neural network for SOM in Yancheng coastal wetland. The estimation model of SOM by SVM based on (1/R)′ spectra had the highest precision, with the determination coefficients (R2) and root mean square error (RMSE) of 0.93 and 0.23. Therefore, it is suitable to use hyperspectral remote sensing to quickly estimate the nutrient contents of topsoil in coastal wetland.
Key words：Coastal wetland; S-G filtering; Support vector machine; BP neural network
张 森，卢 霞，聂格格，李昱蓉，邵亚婷，田燕芹，范礼强，张钰娟. SVM和BP检测滨海湿地土壤有机质[J]. 光谱学与光谱分析, 2020, 40(02): 556-561.
ZHANG Sen, LU Xia, NIE Ge-ge, LI Yu-rong, SHAO Ya-ting, TIAN Yan-qin, FAN Li-qiang, ZHANG Yu-juan. Estimation of Soil Organic Matter in Coastal Wetlands by SVM and BP Based on Hyperspectral Remote Sensing. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(02): 556-561.
[1] Gabriel Y K Moinet, John E Hunt, Miko U F Kirschbaum, et al. Soil Biology and Biochemistry, 2018, 116: 333.
[2] Vohland M, Emmerling C. Soil Science, 2011, 62(4): 598.
[3] Wu Di, Shi Hui, Wang Songjing, et al. Analytica Chimica Acta, 2012, 726(0): 57.
[4] Radim Vašát, Radka Kodešová, Aleš Klement, et al. Geoderma, 2017, 298: 46.
[5] JIANG Ye-lin, WANG Rang-hui, LI Yan, et al(蒋烨林，王让会，李 焱，等). Chinese Journal of Eco-Agriculture(中国生态农业学报)，2016，24(11)：1555.
[6] GAO Deng-zhou, ZENG Cong-sheng, ZHANG Wen-long, et al(高灯州, 曾从盛, 章文龙, 等). Chinese Journal of Ecology(生态学杂志), 2016, 35(4): 952.
[7] He Yong, Xiao Shupei, Nie Pengcheng, et al. Sensors, 2017, 17(9): 2045.
[8] ZOU Xiao-bo, ZHAO Jie-wen(邹小波, 赵杰文). Acta Optica Sinica(光学学报), 2007, 27(7): 1316.
[9] GAO Deng-zhou, CHEN Gui-xiang, ZHANG Wen-long, et al(高灯州, 陈桂香, 章文龙, 等). Research and Exploration in Laboratory(实验室研究与探索), 2014, 33(6): 19.
[10] Gerighausen H, Menz G, Kaufmann H, et al. Applied & Environmental Soil Science, 2012, 143: 487.
[11] Tian Yongchao, Zhang Juanjuan, YAO Xiao, et al. Geoderm, 2013, 202-203: 161.
[12] Kennedy Were, Dieu Tien Bui, ystein B Dick, et al. Ecological indicators, 2015, 52: 394.
[13] Bao Nisha, Wu Lixin, Ye Baoying, et al. Geoderma, 2017, 288: 47.
[14] Wang Xiaoping, Zhang Fei, Kung Hsiang-te, et al. Remote Sensing of Environment, 2018, 218(1): 104.
[15] LU Xia, LIN Ya-li, WU Ya-nan, et al(卢 霞, 林雅丽, 吴亚楠, 等). Transactions of Oceanology and Limnology(海洋湖沼通报), 2018, 4: 74.
[16] LIU Jin-gen, XUE Jian-hui, WANG Lei, et al(刘金根, 薛建辉, 王 磊, 等). Chinese Journal of Ecology(生态学杂志), 2011, 30(8): 1793.
[17] QIAO Juan-feng, XIONG Hei-gang, WANG Xiao-ping, et al(乔娟峰，熊黑纲，王小平，等). Agricultural Research in the Arid Areas(干旱地区农业研究)，2018，36(5)：207.
[18] DING Ning-ning, WANG Bao-song, LIANG Zhen-hai, et al(丁宁宁，王保松，梁珍海，等). Soils(土壤)，2011，43(3)：487.
[19] JIANG Lu-lu, ZHANG Yu, WANG Yan-yan, et al(蒋璐璐, 张 瑜, 王艳艳, 等). Journal of Zhejiang University(浙江大学学报), 2010, 36(4): 445.
[20] LIU Xue-mei(刘雪梅). Journal of Chinese Agricultural Mechanization(中国农机化学报), 2013, 34(2): 202.
