Estimating soil heavy metal from hyperspectral remote sensing images base on fractional order derivative

DING Songtao; ZHANG Xia; SHANG Kun; LI Ru; SUN Weichao

doi:10.11834/jrs.20232513

Models and Methods | Views : 0 下载量: 262 CSCD: 0 更多指标

R-PDF
PDF
Export
Share
Collection
Album

Estimating soil heavy metal from hyperspectral remote sensing images base on fractional order derivative
Vol. 27, Issue 9, Pages: 2191-2205(2023)
Published： 07 September 2023 ，
DOI： 10.11834/jrs.20232513

扫描看全文

丁松滔，张霞，尚坤，李儒，孙伟超.2023.基于分数阶微分的土壤重金属高光谱遥感图像反演.遥感学报，27（9）： 2191-2205

Ding S T，Zhang X，Shang K，Li R and Sun W C. 2023. Estimating soil heavy metal from hyperspectral remote sensing images base on fractional order derivative. National Remote Sensing Bulletin， 27（9）：2191-2205
丁松滔，张霞，尚坤，李儒，孙伟超.2023.基于分数阶微分的土壤重金属高光谱遥感图像反演.遥感学报，27（9）： 2191-2205 DOI： 10.11834/jrs.20232513.

Ding S T，Zhang X，Shang K，Li R and Sun W C. 2023. Estimating soil heavy metal from hyperspectral remote sensing images base on fractional order derivative. National Remote Sensing Bulletin， 27（9）：2191-2205 DOI： 10.11834/jrs.20232513.

摘要

高光谱成像技术在实现低成本大范围的土壤重金属快速监测方面独具潜力。针对高光谱图像反演中突出的小样本问题，本文基于分数阶微分FOD（Fractional Order Derivative）提出一种面向高光谱图像的土壤重金属反演方法。首先，利用土壤采样点的邻近像元进行样本扩充，增加样本的光谱差异性；其次，采用FOD突出光谱特征同时保留微分光谱的渐变信息；进而通过竞争自适应重加权采样CARS（Competitive Adaptive Reweighted Sampling）优选波段，采用偏最小二乘方法（PLSR）建立反演模型。以新疆维吾尔自治区哈密市黄山南矿区获取的72个土壤样本和航空高光谱图像为研究数据，对铅（Pb）、锌（Zn）、镍（Ni）3种重金属进行反演，结果表明：样本扩充不仅缓和了模型的过拟合现象，还提升了重金属反演精度；最佳阶数的分数阶微分能有效增强光谱特征，提高反演精度；CARS相对于相关系数法CC（Correlation Coefficient）、遗传算法GA（Genetic Algorithm）选出的波段组合反演精度更优，对研究区重金属Pb、Zn、Ni的反演精度

分别为0.7974、0.8690和0.8303，反演方法具有较好的鲁棒性。

Abstract

Hyperspectral imaging technology has the unique potential for the low-cost

large-scale

and rapid monitoring of soil heavy metals. For hyperspectral images

the number of soil image elements differs greatly from the number of soil samples

so the problem of small samples is prominent. In this paper

a soil heavy metal estimation method based on Fractional-Order Derivative (FOD) for hyperspectral images is proposed.

First

the neighboring pixels of soil samples were extracted to expand the samples and increase the spectral variability. Second

FOD was used to highlight the spectral features. Then

the bands were selected by Competitive Adaptive Reweighted Sampling (CARS)

and partial least squares (PLSR) was used to construct the model. Seventy-two soil samples and aerial hyperspectral images obtained from the Huangshan South mine in Hami

Xinjiang were used to estimate three heavy metals

namely

lead (Pb)

zinc (Zn)

and nickel (Ni).

After sample expansion

the estimation accuracy of the test set was improved for three heavy metals

the test set R2 improved from 0.6128 to 0.7974 for Pb

from 0.8178 to 0.8690 for Zn

and from 0.6969 to 0.8303 for Ni

while the R2 of the training set was above 0.8. The accuracy of estimation model for three heavy metals with the best fractional-order differentiation was better than that using integer-order differentiation. CARS+PLSR obtained higher estimation accuracy than the modeling approaches of GA+PLSR and CC+PLSR. The estimation accuracies R2 were 0.7974

0.8690

and 0.8303 for Pb

and Ni

respectively.

Sample expansion alleviated the overfitting phenomenon and improved the estimation accuracy. The FOD of the optimal order could effectively enhance the spectral features and improve the estimation accuracy. CARS was more accurate than CC and GA.

关键词

分数阶微分高光谱遥感图像CARS土壤重金属小样本可见近红外短波红外

Keywords

fractional order derivativehyperspectral remote sensing imagesCompetitive Adaptive Reweighted Sampling (CARS)soil heavy metalsmall sample sizevisible and near-infrared bandshort-ware infrared band

references

Bai H, Yang Y, Cui Q F, Jia P and Wang L X. 2022. Retrieval of heavy metal content in soil using GF-5 Satellite images based on GA-XGBoost model. Laser and Optoelectronics Progress, 59(12): 1230001

柏晗, 杨耘, 崔琴芳, 贾鹏, 王丽霞. 2022. 基于GA-XGBoost模型的GF-5卫星影像土壤重金属含量反演研究. 激光与光电子学进展, 59(12): 1230001 [DOI: 10.3788/LOP202259.1230001http://dx.doi.org/10.3788/LOP202259.1230001]

Chen L H, Lai J, Tan K, Wang X, Chen Y and Ding J W. 2022. Development of a soil heavy metal estimation method based on a spectral index: combining fractional-order derivative pretreatment and the absorption mechanism. Science of the Total Environment, 813: 151882 [DOI: 10.1016/j.scitotenv.2021.151882http://dx.doi.org/10.1016/j.scitotenv.2021.151882]

Cheng H, Wang J and Du Y K. 2021. Combining multivariate method and spectral variable selection for soil total nitrogen estimation by Vis-NIR spectroscopy. Archives of Agronomy and Soil Science, 67(12): 1665-1678 [DOI: 10.1080/03650340.2020.1802013http://dx.doi.org/10.1080/03650340.2020.1802013]

Covelo E F, Vega F A and Andrade M L. 2007. Simultaneous sorption and desorption of Cd, Cr, Cu, Ni, Pb, and Zn in acid soils: I. Selectivity sequences. Journal of Hazardous Materials, 147(3): 852-861 [DOI: 10.1016/j.jhazmat.2007.01.123http://dx.doi.org/10.1016/j.jhazmat.2007.01.123]

Ding S T, Zhang X, Sun W C, Shang K and Wang Y B. 2022. Estimation of soil lead content based on GF-5 hyperspectral images, considering the influence of soil environmental factors. Journal of Soils and Sediments, 22(5): 1431-1445 [DOI: 10.1007/s11368-022-03169-0http://dx.doi.org/10.1007/s11368-022-03169-0]

Guo X F, Cao Y, Jiao R C and Nan Y. 2020. Overview of Hyperspectral Remote Sensing Monitoring Method of Soil Heavy Metals. Urban Geology, 15(3): 320-326

郭学飞, 曹颖, 焦润成, 南赟. 2020. 土壤重金属污染高光谱遥感监测方法综述. 城市地质, 15(3): 320-326 [DOI: 10.3969/j.issn.1007-1903.2020.03.015http://dx.doi.org/10.3969/j.issn.1007-1903.2020.03.015]

Hong Y S, Chen Y Y, Yu L, Liu Y F, Liu Y L, Zhang Y, Liu Y and Cheng H. 2018. Combining fractional order derivative and spectral variable selection for organic matter estimation of homogeneous soil samples by VIS-NIR spectroscopy. Remote Sensing, 10(3): 479 [DOI: 10.3390/rs10030479http://dx.doi.org/10.3390/rs10030479]

Khosravi V, Ardejani F D, Yousefi S and Aryafar A. 2018. Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods. Geoderma, 318: 29-41 [DOI: 10.1016/j.geoderma.2017.12.025http://dx.doi.org/10.1016/j.geoderma.2017.12.025]

Kooistra L, Wanders J, Epema G F, Leuven R S E W, Wehrens R and Buydens L M C. 2003. The potential of field spectroscopy for the assessment of sediment properties in river floodplains. Analytica Chimica Acta, 484(2): 189-200 [DOI: 10.1016/s0003-2670(03)00331-3http://dx.doi.org/10.1016/s0003-2670(03)00331-3]

Leardi R and González A L. 1998. Genetic algorithms applied to feature selection in PLS regression: how and when to use them. Chemometrics and Intelligent Laboratory Systems, 41(2): 195-207 [DOI: 10.1016/s0169-7439(98)00051-3http://dx.doi.org/10.1016/s0169-7439(98)00051-3]

Li H D, Liang Y Z, Xu Q S and Cao D S. 2009. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Analytica Chimica Acta, 648(1): 77-84 [DOI: 10.1016/j.aca.2009.06.046http://dx.doi.org/10.1016/j.aca.2009.06.046]

Li L, Shao L M, Li Y W, Xu J and Zhang F W. 2020. Characteristics and risk assessment of heavy metal pollution in soil of a polymetallic mine in Xinjiang. Environment and Development, 32(8): 23-26

李玲, 邵龙美, 李永武, 徐娟, 张峰玮. 2020. 新疆某多金属矿土壤重金属污染特征及风险评价. 环境与发展, 32(8): 23-26 [DOI: 10.16647/j.cnki.cn15-1369/X.2020.08.012http://dx.doi.org/10.16647/j.cnki.cn15-1369/X.2020.08.012]

Li T C, Mu T H, Liu G W, Yang X G, Zhu G C and Shang C Q. 2022. A method of soil moisture content estimation at various soil organic matter conditions based on soil reflectance. Remote Sensing, 14(10): 2411 [DOI: 10.3390/rs14102411http://dx.doi.org/10.3390/rs14102411]

Meng X T, Bao Y L, Ye Q, Liu H J, Zhang X L, Tang H T and Zhang X H. 2021. Soil organic matter prediction model with satellite hyperspectral image based on optimized denoising method. Remote Sensing, 13(12): 2273 [DOI: 10.3390/rs13122273http://dx.doi.org/10.3390/rs13122273]

Pavez-Lazo B and Soto-Cartes J. 2011. A deterministic annular crossover genetic algorithm optimisation for the unit commitment problem. Expert Systems with Applications, 38(6): 6523-6529 [DOI: 10.1016/j.eswa.2010.11.089http://dx.doi.org/10.1016/j.eswa.2010.11.089]

Peng Z H and Jiang S F. 2018. Study on the ore dressing experiment of Huangshan south copper-nickel ore in Hami, Xinjiang. Hunan Nonferrous Metals, 34(5): 25-30

彭再华, 蒋素芳. 2018. 新疆哈密黄山南铜镍矿选矿试验研究. 湖南有色金属, 34(5): 25-30 [DOI: 10.3969/j.issn.1003-5540.2018.05.007http://dx.doi.org/10.3969/j.issn.1003-5540.2018.05.007]

Ramirez-Lopez L, Behrens T, Schmidt K, Rossel R A V, Demattê J A M and Scholten T. 2013. Distance and similarity-search metrics for use with soil vis-NIR spectra. Geoderma, 199: 43-53 [DOI: 10.1016/j.geoderma.2012.08.035http://dx.doi.org/10.1016/j.geoderma.2012.08.035]

Rathod P H, Rossiter D G, Noomen M F and van der Meer F D. 2013. Proximal spectral sensing to monitor phytoremediation of metal-contaminated soils. International Journal of Phytoremediation, 15(5): 405-426 [DOI: 10.1080/15226514.2012.702805http://dx.doi.org/10.1080/15226514.2012.702805]

Rossel R A V and Behrens T. 2010. Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma, 158(1/2): 46-54 [DOI: 10.1016/j.geoderma.2009.12.025http://dx.doi.org/10.1016/j.geoderma.2009.12.025]

Shen Q, Zhang S W, Ge C, Liu H L, Zhou Y, Chen Y P, Hu Q Q, Ye H C and Huang Y F. 2019. Hyperspectral inversion of heavy metal content in soils reconstituted by mining wasteland. Spectroscopy and Spectral Analysis, 39(4): 1214-1220

沈强, 张世文, 葛畅, 刘慧琳, 周妍, 陈元鹏, 胡青青, 叶回春, 黄元仿. 2019. 矿业废弃地重构土壤重金属含量高光谱反演. 光谱学与光谱分析, 39(4): 1214-1220 [DOI: 10.3964/j.issn.1000-0593(2019)04-1214-08http://dx.doi.org/10.3964/j.issn.1000-0593(2019)04-1214-08]

Sun W C, Liu S, Zhang X and Li Y. 2022. Estimation of soil organic matter content using selected spectral subset of hyperspectral data. Geoderma, 409: 115653 [DOI: 10.1016/j.geoderma.2021.115653http://dx.doi.org/10.1016/j.geoderma.2021.115653]

Sun W C and Zhang X. 2017. Estimating soil zinc concentrations using reflectance spectroscopy. International Journal of Applied Earth Observation and Geoinformation, 58: 126-133 [DOI: 10.1016/j.jag.2017.01.013http://dx.doi.org/10.1016/j.jag.2017.01.013]

Sun W C, Zhang X, Sun X J, Sun Y L and Cen Y. 2018. Predicting nickel concentration in soil using reflectance spectroscopy associated with organic matter and clay minerals. Geoderma, 327: 25-35 [DOI: 10.1016/j.geoderma.2018.04.019http://dx.doi.org/10.1016/j.geoderma.2018.04.019]

Tan K, Ma W B, Chen L H, Wang H M, Du Q, Du P J, Yan B K, Liu R Y and Li H D. 2021. Estimating the distribution trend of soil heavy metals in mining area from HyMap airborne hyperspectral imagery based on ensemble learning. Journal of Hazardous Materials, 401: 123288 [DOI: 10.1016/j.jhazmat.2020.123288http://dx.doi.org/10.1016/j.jhazmat.2020.123288]

Tan K, Wang H M, Chen L H, Du Q, Du P J and Pan C C. 2020. Estimation of the spatial distribution of heavy metal in agricultural soils using airborne hyperspectral imaging and random forest. Journal of Hazardous Materials, 382: 120987 [DOI: 10.1016/j.jhazmat.2019.120987http://dx.doi.org/10.1016/j.jhazmat.2019.120987]

Vohland M, Harbich M, Ludwig M, Emmerling C and Thiele-Bruhn S. 2016. Quantification of soil variables in a heterogeneous soil region with VIS-NIR-SWIR data using different statistical sampling and modeling strategies. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(9): 4011-4021 [DOI: 10.1109/jstars.2016.2572879http://dx.doi.org/10.1109/jstars.2016.2572879]

Vohland M, Ludwig M, Thiele-Bruhn S and Ludwig B. 2017. Quantification of soil properties with hyperspectral data: selecting spectral variables with different methods to improve accuracies and analyze prediction mechanisms. Remote Sensing, 9(11): 1103 [DOI: 10.3390/rs9111103http://dx.doi.org/10.3390/rs9111103]

Wang H Y, Han L, Xie D N, Hu H J, Liu Z H and Wang Z. 2022. Distribution characteristics of heavy metals in farmland soils around mining areas and pollution Assessment. Environmental Science, 43(4): 2104-2114

王海洋, 韩玲, 谢丹妮, 胡慧娟, 刘志恒, 王祯. 2022. 矿区周边农田土壤重金属分布特征及污染评价. 环境科学, 43(4): 2104-2114 [DOI: 10.13227/j.hjkx.202106218http://dx.doi.org/10.13227/j.hjkx.202106218]

Wang J J, Cui L J, Gao W X, Shi T Z, Chen Y Y and Gao Y. 2014. Prediction of low heavy metal concentrations in agricultural soils using visible and near-infrared reflectance spectroscopy. Geoderma, 216: 1-9 [DOI: 10.1016/j.geoderma.2013.10.024http://dx.doi.org/10.1016/j.geoderma.2013.10.024]

Wang J Z, Tiyip T, Ding J L, Zhang D, Liu W, Wang F and Tashpolat N. 2017. Desert soil clay content estimation using reflectance spectroscopy preprocessed by fractional derivative. PLoS ONE, 12(9): e0184836 [DOI: 10.1371/journal.pone.0184836http://dx.doi.org/10.1371/journal.pone.0184836]

Wang J B, Wang Y W and He Z J. 2006. Ore deposits as a guide to the tectonic evolution in the East Tianshan Mountains, NW China. Geology in China, 33(3): 461-469

王京彬, 王玉往, 何志军. 2006. 东天山大地构造演化的成矿示踪. 中国地质, 33(3): 461-469 [DOI: 10.3969/j.issn.1000-3657.2006.03.002http://dx.doi.org/10.3969/j.issn.1000-3657.2006.03.002]

Wang Y B, Zhang X, Sun W C, Wang J N, Ding S T and Liu S H. 2022. Effects of hyperspectral data with different spectral resolutions on the estimation of soil heavy metal content: from ground-based and airborne data to satellite-simulated data. Science of the Total Environment, 838: 156129 [DOI: 10.1016/j.scitotenv.2022.156129http://dx.doi.org/10.1016/j.scitotenv.2022.156129]

Wu Y Z, Chen J, Ji J F, Gong P, Liao Q L, Tian Q J and Ma H R. 2007. A mechanism study of reflectance spectroscopy for investigating heavy metals in soils. Soil Science Society of America Journal, 71(3): 918-926 [DOI: 10.2136/sssaj2006.0285http://dx.doi.org/10.2136/sssaj2006.0285]

Xu B B, Ji G S and Zhu Y H. 1991. A preliminary research of geographic regionalization of China land background and spectral reflectance characteristics of soil. Remote Sensing of Environment, 6(2): 142-151

徐彬彬, 季耿善, 朱永豪. 1991. 中国陆地背景和土壤光谱反射特性的地理分区的初步研究. 环境遥感, 6(2): 142-151

Zhang L N, Li G, Sun M X, Li H X, Wang Z N, Li Y X and Lin L. 2017. Kennard-Stone combined with least square support vector machine method for noncontact discriminating human blood species. Infrared Physics and Technology, 86: 116-119 [DOI: 10.1016/j.infrared.2017.08.020http://dx.doi.org/10.1016/j.infrared.2017.08.020]

Zhang X, Ding S T, Cen Y, Sun W C and Wang J N. 2022. Soil heavy metal Pb content estimation method by combining field spectra with laboratory spectra. Geomatics and Information Science of Wuhan University, 47(9): 1479-1485

张霞, 丁松滔, 岑奕, 孙伟超, 王晋年. 2022. 结合野外与实验室光谱的土壤Pb含量反演. 武汉大学学报(信息科学版), 47(9): 1479-1485 [DOI: 10.13203/j.whugis20200386http://dx.doi.org/10.13203/j.whugis20200386]

Zhang Z P, Ding J L, Zhu C M, Wang J Z, Ma G L, Ge X Y, Li Z S and Han L J. 2021. Strategies for the efficient estimation of soil organic matter in salt-affected soils through Vis-NIR spectroscopy: optimal band combination algorithm and spectral degradation. Geoderma, 382: 114729 [DOI: 10.1016/j.geoderma.2020.114729http://dx.doi.org/10.1016/j.geoderma.2020.114729]

Zhou B, Li B X, He X, Liu H X and Wang F Z. 2021. Classification of camouflages using hyperspectral images combined with fusing adaptive sparse representation and correlation coefficient. Spectroscopy and Spectral Analysis, 41(12): 3851-3856

周冰, 李秉璇, 贺宣, 刘贺雄, 王法臻. 2021. 融合自适应稀疏表示和相关系数的高光谱伪装分类方法. 光谱学与光谱分析, 41(12): 3851-3856 [DOI: 10.3964/j.issn.1000-0593(2021)12-3851-06http://dx.doi.org/10.3964/j.issn.1000-0593(2021)12-3851-06]

Alert me when the article has been cited

提交

CNN with coefficient of variation-based dimensionality reduction for hyperspectral remote sensing images classification