Thickness estimation of crude oil slicks by hyperspectral data based on partial least square regression method

doi:10.6046/gtzyyg.2019.02.16

Abstract
Figures/Tables
References
Related Articles
Metrics

Download: PDF(5044 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Thickness of oil slick is an important parameter of oil spill volume. In order to confirm the feasibility of oil thickness estimation with hyperspectral data,the authors used ASD FieldSpec3, quartz halogen lamp and crude oil for a laboratory experiment which simulates oil slick and spectral measurement. 27 pairs of oil thickness and reflection data were acquired. To make full use of spectral information of the hyperspectral data,the authors selected partial least square (PLS) to slick thickness and reflection modeling with 21 set model data and 6 test data set. Model result shows that PLS model expresses optimal effect when five principal components are selected which interpret 74% information of independent variables and 99.8% information of dependent variable, the prediction capability of the model runs up to 92.8%. The root mean squared error is 0.01 for modeling samples and 0.04 for validation samples. The PLS model shows better accuracy of modeling and validation error compared with traditional model, and thus it can be used in oil slicks thickness modeling with hyperspectral data.

Keywords oil slick simulation experiment thickness of oil slicks hyperspectral data partial least square

TP79

Issue Date: 23 May 2019

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Xuewen XING
	Song LIU
	Degang XU
	Kaijun QIAN

Cite this article:

Xuewen XING,Song LIU,Degang XU, et al. Thickness estimation of crude oil slicks by hyperspectral data based on partial least square regression method[J]. Remote Sensing for Land & Resources, 2019, 31(2): 111-117.

URL:

https://www.gtzyyg.com/EN/10.6046/gtzyyg.2019.02.16 OR https://www.gtzyyg.com/EN/Y2019/V31/I2/111

Fig.1 Sketch map of oil slicks measurement

Fig.2 Computational method of oil slick thickness

Fig.3 Reflection spectra of crude oil slicks

Fig.4 Linear correlation matrix

Fig.5 Plane graph of t₁-t₂ and T² ellipse

Fig.6 Determination of the principal component number

Tab.1 Explanation ability of each principle component(%)

Fig.7 Correlation of component t and component u

Fig.8 Relationship between measured and predicted oil slick thickness

Fig.9 Importance indexes of the independent variable factors of PLS model

Fig.10 w*c₁-w*c₂ map of component t₁and t₂

Fig.11 Curve fitting of oil slick’s thickness and reflection

模型	自变量	方程	RMSE
模型	自变量	方程	建模样本	验证样本
PLS	R₃₅₀—R_{2 500}	—	0.01	0.04
单波段指数模型	R_{1 086}	Y=1.729 4 $e - 4 048 x$	0.11	0.15

Tab.2 Comparison of different models

[1]	宋莎莎, 安伟, 李建伟 , 等. 海上溢油量评估方法研究综述[J]. 海岸工程, 2017,36(1):83-88. doi: 10.3969/j.issn.1002-3682.2017.01.009 url: http://www.cnki.com.cn/Article/CJFDTOTAL-HAGC201701010.htm
[1]	Song S S, An W, Li J W , et al. Review on the methods for assessment of marine oil spill volume[J]. Coastal Engineering, 2017,36(1):83-88.
[2]	安超 . 光学遥感溢油检测机理及实例分析[D]. 青岛:中国海洋大学, 2013.
[2]	An C . The Mechanism of Optical Remote Sensing in Oil Spill Detection and Case Studies[D]. Qingdao:Ocean University of China, 2013.
[3]	赵冬至, 丛丕福 . 海面溢油的可见光波段地物光谱特征研究[J]. 遥感技术与应用, 2000,15(3):160-164. doi: 10.3969/j.issn.1004-0323.2000.03.005 url: http://www.cnki.com.cn/Article/CJFD2000-YGJS200003004.htm
[3]	Zhao D Z, Cong P F . The research of visual light wave-band feature spectrum of sea-surface oil spill[J]. Remote Sensing Technology and Application, 2000,15(3):160-164.
[4]	刘旭拢, 邓孺孺, 秦雁 , 等. 水面浮油光谱测量及光谱特征分析[J]. 海洋科学, 2016,40(10):63-70. doi: 10.11759/hykx20160118001 url: http://www.cnki.com.cn/Article/CJFDTotal-HYKX201610009.htm
[4]	Liu X L, Deng R R, Qin Y , et al. Spectral measurement and characteristic analysis of an oil film floating above water[J]. Marine Sciences, 2016,40(10):63-70.
[5]	臧影 . 高光谱溢油图像波段选择在油膜厚度估算中的应用[D]. 大连:大连海事大学, 2010.
[5]	Zang Y . Application of Hyperspectral Band Selection in Detection of Oil Slick Thickness[D]. Dalian:Dalian Maritime University, 2010.
[6]	兰国新 . 海上溢油遥感光谱信息挖掘与应用研究[D]. 大连:大连海事大学, 2012.
[6]	Lan G X . Study on Spectral Information Mining and Application for Oil Spill Remote Sensing Monitoring[D]. Dalian:Dalian Maritime University, 2012.
[7]	肖剑伟, 田庆久 . 基于生物光学模型的水面薄油膜厚度的高光谱遥感反演实验研究[J]. 光谱学与光谱分析, 2012,32(1):183-187. url: http://www.opticsjournal.net/Articles/Abstract?aid=OJ120220000134C9FbHe
[7]	Xiao J W, Tian Q J . Experimental study of offshore oil thickness hyperspectral inversion based on bio-optical model[J]. Spectroscopy and Spectral Analysis, 2012,32(1):183-187.
[8]	孙鹏, 宋梅萍, 安居白 . 基于光谱曲线响应特性的油膜厚度估计模型分析[J]. 光谱学与光谱分析, 2013,33(7):1881-1885. url: http://www.opticsjournal.net/Articles/Abstract?aid=OJ1309300001270FbIeL
[8]	Sun P, Song M P, An J B . Study of prediction models for oil thickness based on spectral curve[J]. Spectroscopy and Spectral Analysis, 2013,33(7):1881-1885.
[9]	刘丙新, 李颖, 张至达 , 等. 不同厚度海上油膜高光谱遥感波段敏感性研究[J]. 东北师大学报(自然科学版), 2015,47(4):156-160. doi: 10.16163/j.cnki.22-1123/n.2015.04.032 url: http://www.cnki.com.cn/Article/CJFDTotal-DBSZ201504032.htm
[9]	Liu B X, Li Y, Zhang Z D , et al. Study on the sensitivity of hyperspectral imagery to detect oil film with different thickness[J]. Journal of Northeast Normal University(Natural Science Edition), 2015,47(4):156-160.
[10]	Winkelmann K H . On the applicability of imaging spectrometry for the detection and investigation of contaminated sites with particular consideration given to the detection of fuel hydrocarbon contaminants in soil[D]. Berlin:BTU Cottbus, 2005.
[11]	高保彬, 潘家宇, 刘云鹏 , 等. 偏最小二乘法的煤层瓦斯含量预测模型研究[J]. 河南理工大学学报(自然科学版), 2015,34(2):146-150. doi: 10.16186/j.cnki.1673-9787.2015.02.002 url: http://d.wanfangdata.com.cn/Periodical/jzgxyxb201502002
[11]	Gao B B, Pan J Y, Liu Y P , et al. Study on prediction model of seam gas content based partial least squares regression[J]. Journal of Henan Polytechnic University(Natural Science), 2015,34(2):146-150.
[12]	李朋成, 朱军桃, 马云栋 , 等. 基于偏最小二乘法的近红外光谱分析应用[J]. 测绘地理信息, 2015,40(2):53-56. doi: 10.14188/j.2095-6045.2015.02.015 url: http://www.cnki.com.cn/Article/CJFDTotal-CHXG201502017.htm
[12]	Li P C, Zhu J T, Ma Y D , et al. Near infrared spectral analysis based on partial least squares[J]. Journal of Geomatics, 2015,40(2):53-56.
[13]	刘忠华, 李云梅, 吕恒 , 等. 基于偏最小二乘法的巢湖悬浮物浓度反演[J]. 湖泊科学, 2011,23(3):357-365. doi: 10.18307/2011.0307 url: http://d.old.wanfangdata.com.cn/Periodical/hpkx201103007
[13]	Liu Z H, Li Y M, Lyu H , et al. Inversion of suspended matter concentration in lake Chaohu based on partial least squares regression[J]. Journal of Lake Sciences, 2011,23(3):357-365.
[14]	王慧文 . 偏最小二乘回归方法及其应用[M]. 北京: 国防工业出版社, 1999.
[14]	Wang H W. Partial Least-Squares Regression Method and Applications[M]. Beijing: National Defense Industry Press, 1999.
[15]	杨杰, 方俊, 胡德秀 , 等. 偏最小二乘法回归在水利工程安全监测中的应用[J]. 农业工程学报, 2007,23(3):136-140. doi: 10.3321/j.issn:1002-6819.2007.03.028 url: http://www.cnki.com.cn/Article/CJFDTotal-NYGU200703028.htm
[15]	Yang J, Fang J, Hu D X , et al. Application of partial least-squares regression to safety monitoring of water conservancy projects[J]. Transactions of the Chinese Society of Agricultural Engineering, 2007,23(3):136-140.
[16]	杨鹏程 . 紫外吸收光谱结合偏最小二乘法海水硝酸盐测量技术研究[D]. 天津:国家海洋技术中心, 2013.
[16]	Yang P C . Research on Determination of Nitrate in Seawater Based on Ultraviolet Spectra Combined with PLS Method[D]. Tianjin:National Ocean Technology Center, 2013.

[1]	LI Shuangquan, MA Yufeng, LIU Xun, LI Changchun, DU Jun. Hyperspectral inversion of macro element content in loess based on the profile of Zaoshugou Village, Mangshan Mountain, Zhengzhou City[J]. Remote Sensing for Natural Resources, 2021, 33(3): 121-129.
[2]	GAO Kaixuan, JIAO Haiming, WANG Xinchuang. Inversion model of forest canopy height based on image texture,spectral and topographic features[J]. Remote Sensing for Land & Resources, 2020, 32(3): 63-70.
[3]	Junliang HE, Chaoshan HAN, Rui WEI, Zhiyong ZHOU, Qiliang DONG. Research on indirect hyperspectral estimating model of heavy metal Cd based on partial least squares regression[J]. Remote Sensing for Land & Resources, 2019, 31(4): 96-103.
[4]	Xifeng CAO, Lin SUN, Zifei ZHAO, Xiaofeng HAN, Mingjie YAN. Application of MODIS remote sensing products in the estimation of grass yield in Sanjiang Source Area[J]. Remote Sensing for Land & Resources, 2018, 30(4): 115-124.
[5]	Dongyang WU, Li MA. Multi-manifold LE algorithm for dimension reduction and classification of multitemporal hyperspectral image[J]. Remote Sensing for Land & Resources, 2018, 30(2): 80-86.
[6]	YANG Yuwei, DAI Xiaoai, NIU Yutian, LIU Hanhu, YANG Xiaoxia, LAN Yan. Inversion of leaf area index in Heihe Oasis based on CASI data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(4): 179-184.
[7]	FAN Xue, LIU Qingwang, TAN Bingxiang. Classification of forest species using airborne PHI hyperspectral data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(2): 110-116.
[8]	YU Junchuan, LIU Wenliang, YAN Bokun, DONG Xinfeng, WANG Zhe, LI Na. Inversion of geochemical compositions of basalts based on field measured spectra[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 158-163.
[9]	LI Xiaoming, WANG Shuguang, HAN Jichang. Hyperspectral remote sensing inversion of soil salinity in north Shaanxi based on PLSR[J]. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(3): 113-116.
[10]	LI Guanghui, WANG Cheng, XI Xiaohuan, ZHENG Zhaojun, LUO Shezhou, YUE Cairong. Extraction of glacier snowline based on airborne LiDAR and hyperspectral data fusion[J]. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(3): 79-84.
[11]	ZHANG Yuan-Fei, Wu De-Wen, ZHANG Gen-Zhong, ZHU Gu-Chang, LI Hong. Study on Band Sequence Structure Analysis of Hyperspectral Data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2010, 22(1): 30-38.
[12]	WANG Yuan-Yuan, CHEN Yun-Hao, LI Jing, JIANG Jin-Bao. THE APPLICATION OF PARTIAL LEAST SQUARE TO THE INVERSION OF SEVERITY OF WINTER WHEAT STRIPE RUST DISEASE[J]. REMOTE SENSING FOR LAND & RESOURCES, 2007, 19(1): 57-60.
[13]	JIAO Quan-Jun, ZHANG Xia, ZHANG Bing, WEI Zheng, ZHENG Lan-Fen. THE RETRIEVAL OF FOREST CHLOROPHYLL CONCENTRATION BASED ON FOLIAR SPECTRA[J]. REMOTE SENSING FOR LAND & RESOURCES, 2006, 18(2): 26-30.
[14]	FAN Xue-wei, ZHANG Han-de, SUN Xing-wen. THE APPLICATION OF HYPERSPECTRAL DATA TO THE DETECTION AND IDENTIFICATION OF RED TIDES[J]. REMOTE SENSING FOR LAND & RESOURCES, 2003, 15(1): 8-12.
[15]	Liu Dechang, Xie Hongjie, Li Jianfeng, Zhao Yingjun, Huang Shutao, Zhang Jinye, Dong Jishi, Chen Baoshu. HYPERSPECTRAL DATA PROCESSING AND RESEARCH ON GEOLOGICAL APPLICATION IN MIAOERSHAN DISTRICT, GUANGXI PROVINCE[J]. REMOTE SENSING FOR LAND & RESOURCES, 1999, 11(3): 65-71.

Viewed

Full text

Abstract

Cited

Shared

Discussed