Inversion models of chlorophyll α mass concentration in Pearl River Estuary using SAR image

Abstract

Abstract: Base on the Radarsat-2 full polarimetric SAR data and the observed chlorophyll a data from the seasurface of the Pearl River Estuary, and using microwave scattering theory and the Cloude-Pottier theory, theSAR images were decomposed,which resulted in the average scattering angle a and scattering entropies H andVH, VV.HH and HV. A mathematical relationship model between the six parameters and the chlorophyll amass concentration was established using the BP artificial neural network model,and combined with themeasured data the chlorophyll a mass concentration was classified. The results shows that the net workstructure has a good result of the inversion to the chlorophyll a mass concentration when the hidden layernodes is 9,the transmit function of the input layer and the hidden layer is tansig and logsig respectively andthe learning rate and the momentum coefficient are both 0.2,namely, the determination coefficient betweenthe measured data and the predicted data of the chlorophyll a mass concentration (R²) is 0.826. When themodel was applied to two images of different period for verification,it worked well, and the results were ingood accordance with the actual situation.

Key words: Radarsat-2, SAR, BP artificial neural network, chlorophyll a mass concentration

CLC Number:

Ll Lu-feng, LIU Xiang-nan, Ll Zhi-bo, MI Yong-hong. Inversion models of chlorophyll α mass concentration in Pearl River Estuary using SAR image[J]. Journal of Marine Sciences, 2012, 30(2): 66-73.

References

[1] SHU Xiao-zhou,YIN Qiu,KUANG Ding-bo. Relationship be-tween algal chlorophyll concentration and spectral reflectance ofinland water[J]. Journal of Remote Sensing, 2000,4(1):41-45.
疏小舟,尹球,匡定波.内陆水体藻类叶绿素浓度与反射光谱特征的关系[J].遥感学报,2000, 4(1):41-45.
[2] CONG Pi-fu, NIU Zheng, MENG Ji-hua, et al. Variability of chlorophyll a retrieved from satellite in. Chinese shelf sea from 1998 to 2003 [J]. Marine Environmental Science, 2006,25, 1: 30-33.
丛丕福,牛铮,蒙继华,等.1998-2003年卫星反演的中国大陆架海洋叶绿素a浓度变化分析[J].海洋环境科学,2006,25(1): 30-33.
[3] LIU Da-zhao, TANG Shi-lin, FU Dong-yang. Study on retrieval of chlorophyll a concentration in the waters of Pearl River Estuary by hyperspectral technology [J]. Journal of Guangdong Ocean U-niversity,2008,28(1): 49-52.
刘大召,唐世林,付东洋.珠江口水体叶绿素a浓度高光谱反演研究[J].广东海洋大学学报,2008,28(1):49-52.
[4] MA Rong-hua, DAI Jin-fang. Chlorophyll-concentration estima-tion with field spectra of water-body near Meiliang Bayou in Taihu Lake[J]. Journal of Remote Sensing,2005,:(1): 78-97.
马荣华,戴锦芳.应用实测光谱估测太湖梅梁湾附近水体叶绿素a 浓度[J].遥感学报,2005,9(1): 78-97.
[5] DUAN Hong-tao, ZHANG Bo, SONG Kai-shan, et al. Hyper-spectral remote sensing of chlorophyll-a in the Chagan Lake, China[J]. Enviromental Science,2006,27(3):503-507.
段洪涛,张柏,宋开山,等.查干湖叶绿素a浓度高光谱定量模型研究[J].环境科学,2006,27(3), 03-507.
[6] LIU Tang-you, KUANG Ding-bo, YIN Qiu. Study on hyperspec-tral quan.titan.tive model of concentrations for chlorophyll-a of alga and suspended particles in Tailake[J]. J Infrared Millim Waves, 2004,23(1):11-15.
刘堂友,匡定波,尹球.湖泊藻类叶绿素a和悬浮物浓度的高光谱定量遥感模型研究[J].红外与毫米波学报,2004,23(1): 11-15.
[7] MEISL P, THOMPSON A A, LUSCOMBE A P, et al. Radar-sat-2 mission: Overview and development status[C]//Proceedings of the 3rd European conference on Synthetic Aperture Radar. Ger-many, 2000; 373-376.
[8] KEINER L, YAN X H. The use of a neural network in estimating surface chlorophyll and sediments from Thematic Mapper imagery [J]. Remote Sensing of Environment, 1998, 66(2): 153-165.
[9] Tang Jun-wu, Tian Guo-liang. Ocean color analysis and an algorithm for the retrieval of multiconstituents based on remote sensing reflectance[J]. Journal of Remote Sensing, 1997,1(4):252-256.
唐军武,田国良.水色光谱分析与多成分反演算法[J].遥感学报, 1997,1(4):252-256.
[10] ZHAN Hti-gaiig,SHIPing,CHEN Chu-qun. Using the neural network inversion seawater chlorophyll concentration.]. Chi-nese Science Bulletin, 2000,45(17);1 879-1 884.
詹海刚,施平,陈楚群.利用神经网络反演海水叶绿素浓度[J].科学通报,2000,45(17):1 879-1 884.
[11] CAO Wen-xi, YANG Yue-zhong. A bio-opical model for ocean photosynthetic available radiation.[J]. Journal of Tropical Ocea-nography, 2002,21(3)；47-54.
曹文熙,杨跃忠.海洋光合有效辐射分布的计算模式[J].热带海洋学报,2002,21(3):47-54.
[12] ZHANG Yuan-zhi, PULLIAINEN J, KOPONEN S, et al. Ap-plication of an empirical neural network to surface water quality estimation in the Gulf of Finland using combined optical data and microwave data[J]. Remote Sensing of Environment, 2002, 81(2/3):327-336.
[13] SATHYENDRANATH S, COTA G, STUART V, et al. Re-mote sensing of phytoplankton pigments: A comparison of em-pirical and theoretical approaches. International Journal of Remote Sensing,2001,22(2/3):249-273.
[14] HE Gui-fang, YUAN Guo-ming, LI Feng-qi. Effect of economic development on water quality in Zhujiang Estuary[J]. Marine Environmental Science, 2004,23(4): 50-52.
何桂芳,袁国明,李凤岐.珠江口沿岸城市经济发展对珠江口水质的影响[J].海洋环境科学,2004,23(4): 50-52.
[15] PENG Peng, ZHU You-zhi, ZHANG Ping. Multi-look complex POLSAR image feature extraction and classification method POLSAR[J]. Systems Engineering and Electronics,2008,30 (8):1 395-1 398.
彭鹏,朱友志,张平.多视复图像的特征提取和分类方法[J].系统工程与电子技术,2008,30(8):1 395-1 398.
[16] LEE J S, GRUNES M R, SCHULER D L, et al. Scatteringmodel-based speckle filtering of polarimetric SAR data [J] IEEE Trans Geoscience Remote sensing, 2006,44(1): 176-187.
[17] GABARRO C J, FONT A C, MVALL L. Retrieved sea surface salinity and wind speed from L-band measurements for WISE and EuroSTARRS campaigns[C]//Proceedings of the first results workshop on EuroSTARRS, WISE, LOSAC campaigns. 2003: 163-171.
[18] TURKAR V, RAO Y S. Classification of polarimetric synthetic aperture radar images from SIR-C and ALOS PALSAR[C]//Proceedings of recent advances in microwave theory and applica-tions. 2008:438-440.
[19] WANG Chao, ZHANG Hong,CHEN Xi,et al. The polarization synthetic aperture radar image processing[M]. Beijing: Science Press,2008.
王超,张红,陈曦,等.全极化合成孔径雷达图像处理[M].北京: 科学出版社,2008.
[20] ZHU Min-hui. Review of SAR oceanic remote sensing technology[J]. ModernRadar,2010,32(2): 1-5.
朱敏慧.SAR的海洋遥感探测技术综述[J].现代雷达,2010,32 (2):1-5.
[21] LI Xia, YE Jia-an, WANG Shu-gong,et al. Estimating man-grove wetland biomass using radar remote sensing[J]. Journal of Remote Sensing,2006,10(3): 387-396.
黎夏,叶嘉安,王树功,等.红树林湿地植被生物量的雷达遥感估算[J].遥感学报,2006,10(3):387-396.
[22] JIN Hai-long, WANG Xiang, WANG Yu-tian. Al fiber fluores-cence sea chlorophyll a concentration of on-line monitoring system[J]. Measurement Technique, 2004(7);30-31.
金海龙,汪翔,王玉田.全光纤荧光海水中叶绿素a浓度在线监测系统的研究[J].计量技术,2004(7)30-31.
[23] SUN Li. Using fluorescence method and spectrophotometry de-termination. chlorophyll a contrast test [J]. Anhui Chemicaf In-dustry, 003 (5):46-47.
孙力.荧光法与分光光度法测定叶绿素a的对比试验[J].安徽化工,2003(5), 46-47.
[24] LI Mi, LIU Xiang-nan, LIU Mii-ling. Fuzzy neural network model for predicting stress levels in rice fields polluted with heavy met al. s using hyperspectral data[J]. Acta Scientiae Cir-cumstantiae, 010, 0(10):2 108-2 115.
[25] WANG Shu-jun, GUAN Dong-sheng. Remote sensing method of forest biomass estimation by artificial neural network models[J].Ecology and Environment,2007, 6(1): 108-111.
王淑君,管东生.神经网络模型森林生物量遥感估测方法的研究 [J].生态环境,2007, 6(1), 08-111.
[26] Environmental Protection Department. The 2009 water quality annual report of Hong Kong Victoria bay[EB/OL]. [2011-04-15] http://sc.epd.gov.hk/gb/www.epd.gov.hk/epd/tc_chi/environ.mentin.hk/water/marine_quality/mwq_report.html.
李蜜,刘湘南,刘美玲.基于模糊神经网络的水稻农田重金属污染水平高光谱预测模型[J].环境科学学报, 010, 0(10):2 108-2 115.
环境保护署.香港维多利亚湾2009水质年报[EB/OL]. [2011-04-15] http://sc.epd.gov.hk/gb/www.epd.gov.hk/epd/tc_chi/environ.mentin.hk/water/marine_quality/mwq_report.html.