[1]王光羽,杨斌,魏添翼,等.采用高光谱技术的川西矿区周边土壤铬含量反演模型[J].华侨大学学报(自然科学版),2025,46(4):462-469.[doi:10.11830/ISSN.1000-5013.202503024]
　WANG Guangyu,YANG Bin,WEI Tianyi,et al.Inversion Model of Soil Cr Content Around Western Sichuan Mining Area Using Hyperspectral Technology[J].Journal of Huaqiao University(Natural Science),2025,46(4):462-469.[doi:10.11830/ISSN.1000-5013.202503024]
点击复制

采用高光谱技术的川西矿区周边土壤铬含量反演模型()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第46卷
期数:
2025年第4期
页码:
462-469
栏目:
出版日期:
2025-07-16

文章信息/Info

Title:
Inversion Model of Soil Cr Content Around Western Sichuan Mining Area Using Hyperspectral Technology
文章编号:
1000-5013(2025)04-0462-08
作者:
王光羽1;  杨斌1; 2; 3;  魏添翼1;  卓思杰1;  陈卓尔1;  沙英超1
1. 西南科技大学 环境与资源学院, 四川 绵阳 621010;2. 西南科技大学 国家遥感中心绵阳科技城分部, 四川 绵阳 621010;3. 西南科技大学 四川天府新区创新研究院, 四川 成都 610299
Author(s):
WANG Guangyu1;  YANG Bin1; 2; 3;  WEI Tianyi1;  ZHUO Sijie1;  CHEN Zhuoer1;  SHA Yingchao1
1. School of Environment and Resource, Southwest University of Science and Technology, Mianyang 621010, China; 2. Mianyang Science and Technology City Division, National Remote Sensing Center of China, Southwest University of Science and Technology, Mianyang 621010, China; 3. Sichuan Tianfu New Area Innovation Research Institute, Southwest University of Science and Technology, Chengdu 610299, China
关键词:
土壤;  川西矿区;  铬含量;  光谱分析;  高光谱反演;  分数阶微分
Keywords:
soil;  western Sichuan mining area;  Cr content;  spectroscopy analysis;  hyperspectral inversion;  fractional-order differentiation
分类号:
X53(271)
DOI:
10.11830/ISSN.1000-5013.202503024
文献标志码:
A
摘要:
为快速检测出矿产资源开采及运输过程中对周边土壤的重金属的污染,以川西铜矿周边的土壤为研究对象,对原始光谱反射率进行0~1阶分数阶微分(阶数间隔0.2);通过最小绝对收缩和选择算子(LASSO)算法对变换后的光谱进行特征波段筛选,并利用岭回归、支持向量机回归、自适应提升算法、反向传播神经网络、门控循环单元(GRU)算法构建铬元素含量(质量比)的反演模型。研究结果表明:与原始光谱相比,经0.2阶、0.4阶微分后最大相关系数提升了5%和9%,筛选出的特征波段集中在近红外光谱区;预测效果最好的模型为0.4-GRU,其决定系数、均方根误差、相对分析误差分别为0.799 2、4.875 0、2.300;该模型能较准确地预测出土壤铬含量。
Abstract:
To rapidly detect heavy metals pollution in the soil around caused by mineral resource exploitation and transportation, the soil around the copper mine in western Sichuan was taken as the research object. The original spectral reflectance was processed by fractional-order differentiation from 0 to 1(an interval of 0.2), and the minimum absolute shrinkage and selection operator(LASSO)algorithm was used to screen the characteristic bands of the transformed spectrum. Inversion models of Cr content(mass ratio)were constructed using ridge regression, support vector regression, adaptive boosting algorithm, back propagation neural net-work, and gated recurrent unit(GRU)algorithms. The research results showed that, compared to the original spectra, the maximum correlation coefficient increased by 5% and 9% respectively after 0.2-order and 0.4-order differentiation, and the selected feature bands were concentrated in the near-infrared spectral region. The best prediction model was 0.4 GRU with determination coefficients of 0.799 2, root mean squared error of 4.875 0, and residual predictive deviation of 2.300. This model could accurately predict soil Cr content.

参考文献/References:

[1] ANIKWE M,IFE K.The role of soil ecosystem services in the circular bioeconomy[J].Frontiers in Soil Science,2023,3:1209100.DOI:10.3389/fsoil.2023.1209100.
[2] ZHANG Yangxi,WEI Lifei,LU Qikai,et al.Mapping soil available copper content in the mine tailings pond with combined simulated annealing deep neural network and UAV hyperspectral images[J].Environmental Pollution,2023,320:120962.DOI:10.1016/j.envpol.2022.120962.
[3] JIANG Xiawei,LIU Wenhong,XU Hao,et al.Characterizations of heavy metal contamination, microbial community, and resistance genes in a tailing of the largest copper mine in China[J].Environmental Pollution,2021,280:116947.DOI:10.1016/j.envpol.2021.116947.
[4] MAUS V,WERNER T.Impacts for half of the world’s mining areas are undocumented[J].Nature,2024,625(7993):26-29.DOI:10.1038/d41586-023-04090-3.
[5] 张霞,孙友鑫,尚坤,等.基于有机质特征谱段的土壤Cd含量高光谱遥感反演[J].农业机械学报,2024,55(1):186-195.DOI:10.6041/j.issn.1000-1298.2024.01.017.
[6] 李武耀,买买提·沙吾提,买合木提·巴拉提.基于分数阶微分的土壤有机质含量高光谱反演研究[J].激光与光电子学进展,2023,60(7):404-411.DOI:10.3788/LOP220715.
[7] 丁启东,王怡婧,张俊华,等.基于高光谱信息的宁夏引黄灌区中低产田土壤水分和有机质含量估算[J].应用生态学报,2023,34(11):3011-3020.DOI:10.13287/j.1001-9332.202311.013.
[8] ZHANG Zihao,GUO Fei,XU Zhen,et al.On retrieving the chromium and zinc concentrations in the arable soil by the hyperspectral reflectance based on the deep forest[J].Ecological Indicators,2022,144:109440.DOI:10.1016/j.ecolind.2022.109440.
[9] YE Miao,ZHU Lin,LI Xiaojuan,et al.Estimation of the soil arsenic concentration using a geographically weighted XGBoost model based on hyperspectral data[J].Science of the Total Environment,2023,858:159798.DOI:10.1016/j.scitotenv.2022.159798.
[10] 陈晓杰,何政伟,薛东剑.基于模糊综合评价的土壤环境质量研究: 以九龙县里伍铜矿区为例[J].水土保持研究,2012,19(1):130-133.
[11] CHEN Lihan,LAI Jian,TAN Kun,et al.Development of a soil heavy metal estimation method based on a spectral index: Combining fractional-order derivative pretreatment and the absorption mechanism[J].Science of the Total Environment,2022,813:151882.DOI:10.1016/j.scitotenv.2021.151882.
[12] WANG Xi,AN Shi,XU Yaqing,et al.A back propagation neural network model optimized by mind evolutionary algorithm for estimating Cd, Cr, and Pb concentrations in soils using Vis-NIR diffuse reflectance spectroscopy[J].Applied Sciences,2019,10(1):51.DOI:10.3390/app10010051.
[13] 杨林婧,杨莎,张圣杨,等.农田土壤有机碳高光谱特征及定量监测研究[J].激光生物学报,2024,33(4):316-325.DOI:10.3969/j.issn.1007-7146.2024.04.004.
[14] 赵启东,葛翔宇,丁建丽,等.结合分数阶微分技术与机器学习算法的土壤有机碳含量光谱估测[J].激光与光电子学进展,2020,57(15):253-261.DOI:10.3788/LOP57.153001.
[15] 丁松滔,张霞,尚坤,等.基于分数阶微分的土壤重金属高光谱遥感图像反演[J].遥感学报,2023,27(9):2191-2205.DOI:10.11834/jrs.20232513.
[16] 郭立笑,陈志超,马彦鹏,等.基于无人机多光谱和多波段组合纹理的马铃薯LAI估算[J].光谱学与光谱分析,2024,44(12):3443-3454.DOI:10.3964/j.issn.l000-0593(2024)l2-3443-l2.
[17] 王梦迪,何莉,刘潜,等.基于小麦冠层无人机高光谱影像的农田土壤含水率估算[J].农业工程学报,2023,39(6):120-129.DOI:10.11975/j.issn.1002-6819.202207170.
[18] LIN Nan,JIANG Ranzhe,LI Genjun,et al.Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning[J].Ecological Indicators,2022,143:109330.DOI:10.1016/j.ecolind.2022.109330.
[19] ZHAN Dexi,MU Yongqi,DUAN Wenxu,et al.Spatial prediction and mapping of soil water content by TPE-GBDT model in Chinese coastal delta farmland with sentinel-2 remote sensing data[J].Agriculture,2023,13(5):1088.DOI:10.3390/agriculture13051088.
[20] 毛继华,赵恒谦,金倩,等.河北铅锌尾矿库区土壤重金属含量高光谱反演方法对比[J].农业工程学报,2023,39(22):144-156.DOI:10.11975/j.issn.1002-6819.202307092.
[21] 郭云开,刘宁,刘磊,等.土壤Cu含量高光谱反演的BP神经网络模型[J].测绘科学,2018,43(1):135-139,152.DOI:10.16251/j.cnki.1009-2307.2018.01.023.
[22] YUAN Quan,WANG Jiajun,ZHENG Mingwei,et al.Hybrid 1D-CNN and attention-based Bi-GRU neural networks for predicting moisture content of sand gravel using NIR spectroscopy[J].Construction and Building Materials,2022,350:128799.DOI:10.1016/j.conbuildmat.2022.128799.
[23] GHOLAMI H,MOHAMMADIFAR A,GOLZARI S,et al.Interpretability of simple RNN and GRU deep learning models used to map land susceptibility to gully erosion[J].Science of the Total Environment,2023,904:166960.DOI:10.1016/j.scitotenv.2023.166960.
[24] WU Xijun,ZHAO Zhilei,TIAN Ruiling,et al.Total synchronous fluorescence spectroscopy coupled with deep learning to rapidly identify the authenticity of sesame oil[J].Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy,2021,244:118841.DOI:10.1016/j.saa.2020.118841.
[25] 张霞,王一博,孙伟超,等.基于铁氧化物特征光谱和改进遗传算法反演土壤Pb含量[J].农业工程学报,2020,36(16):103-109.DOI:10.11975/j.issn.1002-6819.2020.16.013.
[26] SAEYS W,MOUAZEN A M,RAMON H.Potential for onsite and online analysis of pig manure using visible and near infrared reflectance spectroscopy[J].Biosystems Engineering,2005,91(4):393-402.DOI:10.1016/j.biosystemseng.2005.05.001.
[27] 胡圆园,张一澜,王英英,等.四川攀西地区典型金属采选与冶炼企业周边农用地重金属污染评价及来源解析[J].四川环境,2024,43(2):72-78.DOI:10.14034/j.cnki.schj.2024.02.010.
[28] 刘茂生.全国金属采矿业矿区周边土壤重金属污染评价及潜在污染区域识别[D].赣州:江西理工大学,2023.DOI:10.27176/d.cnki.gnfyc.2023.000930.
[29] 尹翠景.青海省湟中区甘河工业园区土壤重金属污染反演研究[D].西安:长安大学,2022.DOI:10.26976/d.cnki.gchau.2022.000639.
[30] 杨晗.三江源区土壤重金属含量高光谱反演研究[D].重庆:重庆交通大学,2020.DOI:10.27671/d.cnki.gcjtc.2020.000859.

备注/Memo

备注/Memo:
收稿日期: 2025-03-02
通信作者: 杨斌(1979-),男,教授,博士后,博士生导师,主要从事遥感科学与技术在地学领域中综合应用的研究。E-mail:xjgis@126.com。
基金项目: 国家自然科学基金资助项目(41201541); 四川省军民融合研究院项目联合资助项目(39000005)https://hdxb.hqu.edu.cn/
更新日期/Last Update: 2025-07-20