Please wait a minute...
img

官方微信

遥感技术与应用  0, Vol. Issue (): 0-0    DOI: 10.11873/j.issn.1004-0323.2021.3605.0781
    
吐鲁番盆地葡萄园土壤重金属铅含量高光谱估算
阿依努尔·麦提努日,麦麦提吐尔逊·艾则孜
新疆师范大学
Hyperspectral Estimation of Heavy Metal Pb Concentration in Vineyard Soil in Turpan Basin
 全文: PDF(928 KB)  
摘要: 为探讨运用土壤光谱估算葡萄园土壤重金属铅(Pb)含量的可行性,以新疆吐鲁番盆地葡萄园土壤Pb元素为研究对象,分析土壤原始光谱在内的15种光谱变换下的土壤光谱反射率数据与土壤Pb含量的相关性,构建基于高光谱的葡萄园土壤Pb含量偏最小二乘回归(PLSR)模型。结果表明:土壤原始光谱率的二阶微分、平方根一阶微分、平方根二阶微分、倒数二阶微分、对数二阶微分与倒对数二阶微分变换能有效增强葡萄园土壤Pb元素的光谱特征。对土壤原始光谱率的平方根二阶微分和倒数二阶微分变换后的PLSR模型的决定系数(R2)最大,均为0.36,均方根误差(RMSE)最小,分别为2.21与2.20。从模型稳定性和精确性来看,Pb元素含量在平方根二阶微分变换后的PLSR模型拟合精度高,估算能力最优。对光谱数据的预处理后,采用PLSR模型可有效提高估算葡萄园土壤Pb含量的精度。
关键词: 土壤铅元素高光谱光谱变换吐鲁番盆地    
Abstract: In order to explore the feasibility of using soil spectrum to estimate the concentration of heavy metal lead (Pb) in vineyard soil, taking Pb concentration of vineyard soil in the Turpan Basin, Xinjiang, as the research object, the correlation between soil spectral reflectance data and soil Pb concentration under 15 spectral transformations including original soil spectra was analyzed, and a partial least squares regression (PLSR) model based on hyperspectral data was established. The results showed that the spectral characteristics of Pb in vineyard soil could be effectively enhanced by the second-order differential, first-order square root differential, second-order reciprocal differential, logarithmic second-order differential and reciprocal logarithmic second-order differential transformation of soil original spectral rate. The coefficient of determination (R2) of PLSR model transformed by square root second-order differential and reciprocal second-order differential transformation of soil original spectral rate was 0.36, and the root mean square error (RMSE) was 2.21 and 2.20, respectively. From the stability and accuracy of the model, the PLSR model of Pb concentration after square root second-order differential transformation has high fitting accuracy and the best estimation ability. After preprocessing the soil spectral data, PLSR model can effectively improve the accuracy of estimation of Pb concentration in vineyard soil.
Key words: soil    heavy metal Pb    hyperspectral    spectral transformation    Turpan Basin
收稿日期: 2020-08-09 出版日期: 2020-11-26
ZTFLH:  TP79  
基金资助: 国家自然科学基金项目
通讯作者: 阿依努尔·麦提努日   
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
阿依努尔·麦提努日
麦麦提吐尔逊·艾则孜

引用本文:

阿依努尔·麦提努日 麦麦提吐尔逊·艾则孜. 吐鲁番盆地葡萄园土壤重金属铅含量高光谱估算[J]. 遥感技术与应用, 0, (): 0-0.

链接本文:

http://www.rsta.ac.cn/CN/Y0/V/I/0

[1] 姜亚楠,张春雷,张欣,徐权威,张舒涛,周锐. 利用提升树模型综合Gabor和LPQ特征进行遥感地物识别[J]. 遥感技术与应用, 2022, 37(2): 515-523.
[2] 尹芳,封凯,吴朦朦,拜得珍,王蕊,周园园,尹春涛,尹翠景,刘磊. 一种基于分段偏最小二乘模型的土壤重金属遥感反演方法[J]. 遥感技术与应用, 2021, 36(6): 1321-1328.
[3] 姜玉峰,齐建国,陈博伟,闫敏,黄龙吉,张丽. 基于无人机高光谱影像和机器学习的红树林树种精细分类[J]. 遥感技术与应用, 2021, 36(6): 1416-1424.
[4] 徐宏根,刘慧泽,吴柯,占燕婷,林忠. 基于SAM-SCP组合方法的热红外高光谱影像岩性分类[J]. 遥感技术与应用, 2021, 36(6): 1398-1407.
[5] 王皓,郝莹,袁松,陈光舟,靳莉莉. SMAP土壤水分产品在淮河流域的适用性评估[J]. 遥感技术与应用, 2021, 36(5): 1009-1021.
[6] 肖窈,曾超,沈焕锋. 结合参量统计与时空融合的土壤水分降尺度方法[J]. 遥感技术与应用, 2021, 36(5): 1033-1043.
[7] 杨欣源,白晓静. 基于Sentinel-1和MODIS数据反演农田地表土壤水分—以REMEDHUS地区为例[J]. 遥感技术与应用, 2021, 36(5): 973-982.
[8] 杨奥莉,郑东海,文军,陆宣承,杨越,符晴. 青藏高原L波段微波辐射观测与土壤水分反演研究进展[J]. 遥感技术与应用, 2021, 36(5): 983-996.
[9] 彭书艳,赵龙,李婷婷,韩旭军,马明国,杨帅,杨跃程. 基于宇宙射线观测的喀斯特槽谷区典型流域土壤水分反演研究[J]. 遥感技术与应用, 2021, 36(5): 997-1008.
[10] 姜涛,郑兴明,李晓洁,李晓峰,赵凯. 闪电河流域L波段地基微波辐射计RFI检测与电磁环境分析[J]. 遥感技术与应用, 2021, 36(5): 1022-1032.
[11] 吴颉,陈楚群,刘叶取. 珠海一号欧比特高光谱数据交叉辐射定标初探[J]. 遥感技术与应用, 2021, 36(4): 791-802.
[12] 段金亮,张瑞,李奎,庞家泰. 一种基于噪声水平估计的扩展线性光谱分解算法[J]. 遥感技术与应用, 2021, 36(4): 820-826.
[13] 胡宜娜,安如,艾泽天,都伟冰. 基于无人机高光谱影像的三江源草种精细识别研究[J]. 遥感技术与应用, 2021, 36(4): 926-935.
[14] 刘鹤,顾玲嘉,任瑞治. 基于无人机遥感技术的森林参数获取研究进展[J]. 遥感技术与应用, 2021, 36(3): 489-501.
[15] 李宝芸,范玉刚,杨明莉. 基于LFDA和GA-ELM的高光谱图像地物识别方法研究[J]. 遥感技术与应用, 2021, 36(3): 587-593.