微分光谱变换方法对土壤重金属含量反演精度的影响研究

doi:10.3964/j.issn.1000-0593(2024)05-1449-08

摘要
参考文献
相关文章 (15)

全文: PDF (5156 KB)
输出: BibTeX | EndNote (RIS)

摘要：随着我国工农业的日益发展，土壤中以镍（Ni）、铁（Fe）、铜（Cu）、铬（Cr）、铅（Pb）等为代表的重金属污染对人类生活产生了严重影响。高光谱遥感技术具有实时、无损、快速等优点，为高效准确地获取土壤重金属含量提供了科学手段。而在利用高光谱数据反演土壤重金属含量时，微分光谱变换方法的选择对遥感反演土壤重金属含量的精度有显著影响。为明确二者关系，基于研究区采集的60个土壤样品，测定其Ni、Fe、Cr、Cu、Pb等含量以及350～2 500 nm波段范围的光谱反射率。在相关系数（CC）分析法的基础上通过改进离散粒子群算法（MDBPSO）优选遥感探测土壤重金属含量的特征波段。最终以优选出的特征波段作为自变量利用随机森林（RF）算法构建了Ni、Fe、Cr、Cu、Pb等重金属含量的估测模型。在对原始反射率数据进行高斯平滑的基础上，对比分析了一阶微分（R′）、对数倒数的一阶微分（1/lgR）′、倒数的一阶微分（1/R）′、指数的一阶微分（e^R）′四种微分光谱变换方法对土壤重金属反演精度的影响。结果表明，在CC分析法的基础上，MDBPSO算法可以有效地降低光谱数据的冗余度，提高模型的运行效率。其中R′、（1/lgR）′、（1/R）′、（e^R）′中对Ni、Fe、Cr、Cu、Pb敏感的特征波段个数分别至少减少了154、363、135、744和889个。（1/lgR）′、R′、R′、（1/R）′、R′光谱变换方法分别应用到Ni、Fe、Cr、Cu、Pb特征波段的组合运算中，得到的估测模型的精度优于其他微分变换方法；模型检验集的决定系数分别为0.913、0.906、0.872、0.912、0.876，均方根误差分别为0.743、0.095、2.588、1.541、1.453。本研究为利用遥感数据反演土壤重金属含量微分光谱变换方法的选择提供了科学的参考，为进一步实现土壤重金属含量的大面积高精度遥感监测提供新的思路。

关键词：遥感；高光谱；土壤；光谱变换方法；重金属；改进离散粒子群；随机森林

Abstract：With the increasing development of industry and agriculture in China, heavy metal pollution in soil represented by nickel (Ni), iron (Fe), copper (Cu), chromium (Cr), lead (Pb), etc., has a serious impact on human life. Hyperspectral technology has advantages such as being real-time, non-destructive, and fast, which provides scientific means to obtain information on soil heavy metal content efficiently and accurately. At the same time, the spectral transformation method significantly impacts the inversion accuracy of soil heavy metal content. To clarify the relationship between the spectral transformation method and the inversion accuracy, 60 soil samples were collected in the study area to determine the Ni, Fe, Cr, Cu, and Pb heavy metals content and the corresponding spectral reflectance between 350～2 500 nm. Based on the correlation coefficient (CC) analysis, the feature bands for remote sensing detection of soil heavy metals were selected by the modified discrete binary particle swarm optimization (MDBPSO) method. Finally, the inverse models of Ni, Fe, Cr, Cu and Pb contents were constructed by the random forest (RF) algorithm with the feature bands as independent variables. In this study, based on Gaussian smoothing of the original reflectance, the effects of four differential spectral transformation methods, including first-order differential (R′), first-order differential of logarithmic inverse (1/lgR)′, first-order differential of inverse (1/R)′, and first-order differential of exponential (e^R)′, on the accuracy of soil heavy metal inversion were compared and analyzed. The results show that based on the CC analysis method, the MDBPSO algorithm can effectively reduce the redundancy of spectral data and improve the efficiency of the model operation. The number of feature bands sensitive to Ni, Fe, Cr, Cu and Pb in R′, (1/lgR)′, (1/R)′, (e^R)′, has been reduced by at least 154, 363, 135, 744 and 889, respectively. (1/lgR)′, R′, R′, (1/R)′, and R′ spectral transformation methods were applied to the combined operation of Ni, Fe, Cr, Cu, and Pb feature bands, respectively. The accuracy of the estimated models was better than other differential transformation methods, where the coefficients of determination of the model test set were 0.913, 0.906, 0.872, 0.912, and 0.876. The root mean square errors were 0.743, 0.095, 2.588, 1.541, and 1.453, respectively. This study provides a scientific reference for selecting of differential spectral transformation methods when using remote sensing data to retrieve soil heavy metal content. It provides new ideas for further realizing large-area high-precision remote sensing monitoring of soil heavy metal content.

Key words：Remote sensing; Hyperspectral; Soil; Spectral transformation method; Heavy metals; Modified discrete binary particle swarm optimization; Random forests

收稿日期: 2022-04-02 修订日期: 2023-08-31

中图分类号:

TP79

基金资助: 国家科技重大专项（04-H30G01-9001-20/22），国家自然科学基金项目（211035210511）资助

通讯作者: 韩玲 E-mail: hanling@chd.edu.cn

作者简介: 白宗璠，女，1995年生，长安大学土地工程学院博士研究生 e-mail: bzf1529@163.com

引用本文:

白宗璠，韩玲，姜旭海，武春林. 微分光谱变换方法对土壤重金属含量反演精度的影响研究[J]. 光谱学与光谱分析, 2024, 44(05): 1449-1456.
BAI Zong-fan, HAN Ling, JIANG Xu-hai, WU Chun-lin. Effect of Differential Spectral Transformation on Soil Heavy Metal Content Inversion Accuracy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1449-1456.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2024)05-1449-08 或 https://www.gpxygpfx.com/CN/Y2024/V44/I05/1449

[1] QIAN Jia-wei, LIU Xiao-qing, ZHANG Jing-jing, et al（钱家炜, 刘晓青, 张静静, 等）. Acta Agriculturae Zhejiangensis（浙江农业学报）, 2020, 32(8): 1437.
[2] LIU Yan-ping, LUO Qing, CHENG He-fa（刘彦平, 罗晴, 程和发）. Journal of Agro-Environment Science（农业环境科学学报）, 2020, 39(12): 2699.
[3] Liu K, Zhao D, Fang J Y, et al. Journal of the Indian Society of Remote Sensing, 2017, 45(5): 805.
[4] MA Chi（马驰）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2020, 36(20): 164.
[5] Han L, Chen R, Zhu H, et al. Sustainability, 2020, 12(4), 1476.
[6] Liu Z, Lu Y, Peng Y, et al. Remote Sensing, 2019, 11(12), 1464.
[7] GUO Yun-kai, ZHANG Qiong, QIAN Jia, et al（郭云开, 章琼, 钱佳, 等）. Engineering of Surveying and Mapping（测绘工程）, 2020, 29(6): 56.
[8] Tan K, Ma W, Chen L, et al. Journal of Hazardous Materials, 2021, 401: 123288.
[9] Tian S Q, Wang S J, Bai X Y, et al. Chinese Journal of Geochemistry, 2020, 39(3): 423.
[10] WANG Yu-na, LI Fen-ling, WANG Wei-dong, et al（王玉娜, 李粉玲, 王伟东, 等）. Journal of Triticeae Crops（麦类作物学报）, 2020, 40(11): 1389.
[11] ZHOU Ding-hao, XUE Li-hong, LI Ying, et al（周鼎浩, 薛利红, 李颖, 等）. Soils（土壤）, 2014, 46(1): 47.
[12] ZHANG Dong-hui, ZHAO Ying-jun, QIN Kai, et al（张东辉, 赵英俊, 秦凯, 等）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2018, 34(20): 141.
[13] XU Kai-jian, TIAN Qing-jiu, XU Nian-xu, et al（徐凯健, 田庆久, 徐念旭, 等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2019, 39(12): 3794.
[14] Yang C, Tan Y L, Bruzzone L, et al. Remote Sensing, 2017, 9: 782.
[15] Zhang X, Yang G, Yang Y, et al. Proc SPIE, 2016, 10156: 1015605.
[16] ZHANG Jue, TIAN Hai-qing, ZHAO Zhi-yu, et al（张珏, 田海清, 赵志宇, 等）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2019, 35(1): 285.
[17] DING Hai-ning, CHEN Yu, CHEN Yun-zhi（丁海宁, 陈玉, 陈芸芝）. Remote Sensing Technology and Application（遥感技术与应用）, 2019, 34(2): 275.
[18] TONG Qing-xi, ZHANG Bing, ZHENG Lan-fen（童庆禧, 张兵, 郑兰芬）. Hyperspectral Remote Sensing-Principles, Techniques and Applications（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）, 2015.
[19] PU Rui-liang, GONG Peng（浦瑞良, 宫鹏）. Hyperspectral Remote Sensing and Its Applications（高光谱遥感及应用）, Beijing: Higher Education Press（北京：高等教育出版社）, 2003.
[20] Kennedy J, Eberhart R. A Discrete Binary Version of the Particle Swarm Algorithm. International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, 1997, 5: 4104.
[21] CAO Yin, YE Yun-tao, ZHAO Hong-li, et al（曹引, 冶运涛, 赵红莉, 等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报）, 2018, 49(1): 173.
[22] BAI Zong-fan, JING Xia, ZHANG Teng, et al（白宗璠, 竞霞, 张腾, 等）. Acta Agronomica Sinica（作物学报）, 2020, 46(8): 1248.
[23] Wang L, Zhou X D, Zhu X K, et al. The Crop Journal, 2016, 4(3): 212.
[24] YAO Xiong, YU Kun-yong, YANG Yu-jie, et al（姚雄, 余坤勇, 杨玉洁, 等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报）, 2017, 48(5): 159.
[25] Breiman L. Machine Learning, 2001, 45(1): 5.
[26] Rodriguez-Galiano V, Mendes M P, Garcia-Soldado M J, et al. Science of the Total Environment, 2014, 476-477: 189.
[27] WANG Li-ai, MA Chang, ZHOU Xu-dong, et al（王丽爱, 马昌, 周旭东, 等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报）, 2015, 46(1): 259.
[28] XIE Xian-li, SUN Bo, HAO Hong-tao（解宪丽, 孙波, 郝红涛）. Acta Pedologica Sinica（土壤学报）, 2007, 44(6): 982.
[29] ZHANG Hui-juan, ZHANG Da-min, YAN Wei, et al（张绘娟, 张达敏, 闫威, 等）. Computer Science（计算机科学）, 2019, 46(10): 109.
[30] Cao Y, Ye Y T, Zhao H L, et al. Ecological Informatics, 2018, 44: 21.