用多层感知器模型由吸收光谱反演浮游植物色素

doi:10.11978/j.issn.1009-5470.2010.02.046

热带海洋学报 ›› 2010, Vol. 29 ›› Issue (2): 46-51.doi: 10.11978/j.issn.1009-5470.2010.02.046cstr: 32234.14.j.issn.1009-5470.2010.02.046

用多层感知器模型由吸收光谱反演浮游植物色素

周雯1, 曹文熙1, 王桂芬1, 梁少君1,2, 赵俊1,2, 孙兆华1

1. 中国科学院南海海洋研究所热带海洋动力学重点实验室, 广东广州 510301; 2. 中国科学院研究生院, 北京 100039

收稿日期:2009-05-06 修回日期:2009-12-25 出版日期:2010-03-23 发布日期:2010-03-23
作者简介:周雯(1982—), 女, 湖南省邵阳市人, 助理研究员, 主要从事海洋光学技术的研究。
基金资助:
中国科学院重要方向性项目(KZCX2-YW-215); 国家自然科学基金项目(40906022; 40906021; 40606011)

Retrieval of pigment concentrations from the absorption spectra of phytoplankton by multilayered perceptrons

ZHOU Wen1, CAO Wen-xi1, WANG Gui-fen1, LIANG Shao-jun1,2, ZHAO Jun1,2, SUN Zhao-hua1

1. LED, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China; 2. Graduate Univ. of Chinese Academy of Sciences, Beijing 10039, China

Received:2009-05-06 Revised:2009-12-25 Online:2010-03-23 Published:2010-03-23

摘要/Abstract

摘要：

浮游植物吸收光谱已逐渐成为高光谱水色遥感的可获取参量。文章采用了多层感知器模型, 由珠江口担杆群岛附近水体的浮游植物吸收光谱进行了色素浓度的反演, 感知器的输入量是浮游植物吸收光谱, 输出量分别对应叶绿素a、叶绿素b、叶绿素c、光保护类胡萝卜素和非光保护类胡萝卜素五大类主要色素的浓度。分析结果表明, 叶绿素a和叶绿素c估算结果的平均相对偏差比较低, 在测试数据集中两者的偏差分别为19.06%和15.90%; 光保护类胡萝卜素和非光保护类胡萝卜素的估算浓度的相对偏差比较高, 对于测试数据而言, 分别为37.62%和36.96%; 叶绿素b浓度在测试数据集中的估算相对偏差约为27.47%。五大类色素在测试数据集和训练数据集的估算偏差比较接近, 已训练好的多层感知器可用于担杆岛水体中色素信息的反演。同时, 此色素反演方法也为遥感监测水体浮游植物种群动态提供了重要的手段。

关键词: 吸收光谱, 色素浓度, 浮游植物, 多层感知器

Abstract:

The absorption spectra of phytoplankton have gradually become an accessible parameter from hyperspectral ocean color. The retrievals of main pigment concentrations from absorption spectra of phytoplankton by multilayered perceptrons were performed. The input parameters for multilayered perceptions were phytoplankton absorption spectra, and the retrieved parameters were Chlorophyll a, b, c, and photosynthetic and non-photosynthetic carotenoids, respectively. The results indicated that Chlorophyll a and c were the most accurate retrieval pigments with average relative deviation of 19.06% and 15.90%, respectively, for the test data subsets, while the poorest performances were found for photosynthetic and non-photosynthetic carotenoids, with average relative deviation of 37.62% and 36.96%, respectively, for the test subsets. Chlorophyll b was retrieved with average relative deviation of 27.47% for the test subsets. The comparable performances of multilayer perceptrons for the training subset and the test subsets suggest that they could be successfully operated on retrieval of main pigments for the waters around the Dangan Islands in the Pearl River Estuary. The multilayer perceptrons of retrieving main pigment from phytoplankton absorption spectra also provide an important way to detect phytoplankton community from hyperspectral ocean color.

Key words: absorption spectrum, pigment concentration, phytoplankton, multilayered perceptron

周雯,曹文熙,王桂芬,梁少君,赵俊,孙兆华. 用多层感知器模型由吸收光谱反演浮游植物色素[J]. 热带海洋学报, 2010, 29(2): 46-51.

ZHOU Wen,CAO Wen-xi,WANG Gui-fen,LIANG Shao-jun,ZHAO Jun,SUN Zhao-. Retrieval of pigment concentrations from the absorption spectra of phytoplankton by multilayered perceptrons[J]. Journal of Tropical Oceanography, 2010, 29(2): 46-51.

参考文献

[1] BRICAUD A, STRAMSKI D. Spectral absorption coefficients of living phytoplankton and nonalgal biogenous matter: A comparison between the Peru upwelling area and the Sargasso Sea[J]. Limnol Oceanogr, 1990, 35: 562–582.

[2] CHANG G C, DICKEY T D. Partitioning in situ total spectral absorption by use of moored spectral absorption-attenuation meters[J]. Appl Opt, 1999, 38: 3876–3887.

[3] OUBELKHEIR K, CLAUSTRE H, BRICAUD A, et al. Partitioning total spectral absorption in phytoplankton and colored detrital material ontributions
[J]. Limnol Oceanogr Methods, 2007, 5: 384–395.

[4] WANG G F, CAO W X, YANG D T, et al. Partitioning particulate absorption coefficient into contributions of phytoplankton and nonalgal particles: A case study in the northern South China Sea[J]. Estuarine, coastal and shelf Science. 2008,78: 513–520.

[5] LEE Z P, CARDER K L, ARNONE R. Deriving inherent optical properties from water color: A multi-band quasi-analytical algorithm for optically deep waters [J]. Appl Opt, 2002, 41: 5755–5772.

[6] GARVER S A, SIEGEL D. Inherent optical property inversion of ocean color spectra and its biogeochemical interpretation 1. Time series from the Sargasso Sea [J]. J Geophys Res, 1997, 102(C8): 18607–18625.

[7] SMYTH T J, MOORE G F, HIRATA T, et al. Semianalytical model for the derivation of ocean color inherent optical properties: description, implementation, and performance assessment[J]. Appl Opt 2006, 45(31): 8116–8131.

[8] CIOTTI A M, LEWIS M R, CULLEN J J. Assessment of the relationships between dominant cell size in natural phytoplankton communities and the spectral shape of the absorption coefficient[J]. Limnol Oceanogr, 2002, 47: 404–417.

[9] BRICAUD A, CLAUSTRE H, RAS J, et al. Natural variability of phytoplanktonic absorption in oceanic waters: In?uence of the size structure of algal populations[J]. J Geo phys Res, 2004, 109, C11010.

[10] MOREL A, BRICAUD A. Theoretical results concerning light absorption in a discrete medium, and application to speci?c absorption of phytoplankton[J]. Deep-Sea Res, 1981, 28: 1375–1393.

[11] BIDIGARE R R, MORROW J H, KIEFER D A. Derivative analysis of spectral absorption by photosynthetic pigments in the Western Sargasso sea
[J]. J Mar Res, 1989, 47: 323–341.

[12] MILLIE D F, SCHO?ELD O M, KIRKPATRICK G J, et al. Detection of harmful algal blooms using photopigments and absorption signatures: a case study of the Florida red-tide dino?agellate Gymnodinium breve[J]. Limnol Oceanogr, 1997, 42: 1240–1251.

[13] KIRKPATRICK G, MILLIE D F, MOLINE M A, et al. Optical discrimination of a phytoplankton species in natural mixed populations[J]. Limnol Oceanogr, 2000, 45: 467–471.

[14] BIDIGARE R R, ONDRUSEK M E, MORROW J H, et al. In vivo absorption properties of algal pigments[J]. Proc SPIE Ocean Opt X, 1990, 1302: 290–302.

[15] WANG GUIFEN, CAO WENXI, XU DAZHI, et al. Variability of phytoplankton absorption in the northern South China Sea: Influence of the size structure and pigment composition of algal populations[J]. Acta Oceanologica Sinica, 2007, 26(2): 12–25.

[16] HARIMOTO T, ISHIZAKA J, TSUDA R. Latitudinal and vertical distributions of phytoplankton absorption spectra in the central North Pacific during Spring 1994 [J]. J Oceanography, 1999, 55: 667–679.

[17] HOEPFFNER N, SATHYENDRANATH S. Determination of the major groups of phytoplankton pigments from the absorption spectra of total particulate matter[J]. J Geophys Res, 1993, 98: 2789–22803.

[18] STUART V, SATHYENDRANATH V S, PLATT T, et al. Pigment and species composition of natural phytoplankton populations: effect on the absorption spectra[J]. J Plankton Res, 1998, 20:187–217.

[19] LOHRENZ S E, WEIDEMANN A D, TUEL M. Phytoplankton spectral absorption as influenced by community size structure and pigment composition[J]. Journal of Plankton Research, 2003, 25(1): 35–61.

[20] BRICAUD A, MEJIA C, BLONDEAU-PATISSIER D, et al. Retrieval of pigment concentrations and size structure of algal populations from their absorption spectra using multilayered perceptrons[J]. Appl Opt, 2007, 46(8): 1251–1260.

[21] CAO W, YANG Y, XU X, et a1. Regional patterns of particulate spectral absorption in the Pearl River estuary[J]. Chinese Science Bulletin, 2003, 48(21): 2344–2351.

[22] 赵冬至, 罗虎, 傅云娜, 等. 海洋水色组分吸收系数的测定方法研究[J]. 海洋通报, 2004, 23 (3): 81–86.

[23] 王桂芬, 曹文熙, 许大志, 等. 南海北部水体浮游植物比吸收系数的变化[J]. 热带海洋学报, 2005, 24(5): 1–10.

[24] PARSONS T R, MAITA Y, LALLI C M. A Manual of Chemical and Biological Methods for Seawater Analysis[M]. Oxford: Pergamon Press, 1984.

[25] VIDUSSI F, CLAUSTRE H, BUSTILLOS-GUZMAN J, et al. Determination of chlorophylls and catotenoids of marine phytoplankton: Separation of chlorophyll a from divinychlorophyll a and zeaxanthin from lateen[J]. J Plank Res, 1996, 18(12): 2377–2382.

用多层感知器模型由吸收光谱反演浮游植物色素

Retrieval of pigment concentrations from the absorption spectra of phytoplankton by multilayered perceptrons

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	黄圆, 岑竞仪, 梁芊艳, 吕颂辉, 王建艳. 基于高通量测序技术的深圳湾真核浮游植物群落结构研究[J]. 热带海洋学报, 2024, 43(2): 21-33.
[2]	赵红五一, 周雯, 曾凯, 邓霖, 廖健祖, 曹文熙. 基于浮游植物吸收系数和光合有效辐射的南海区域性分粒级初级生产力算法初探[J]. 热带海洋学报, 2023, 42(1): 43-55.
[3]	周雯, 魏盼盼, 李彩, 王桂芬, 郑文迪, 邓霖, 赵红五一, 余凌晖, 曹文熙. 琼东水体后向散射系数与浮游植物生物量的关系模型^*[J]. 热带海洋学报, 2022, 41(3): 29-37.
[4]	李傲, 冯洋, 王云涛, 薛惠洁. 基于OC-CCI数据的南海高叶绿素a浓度水域面积的时空变化研究*[J]. 热带海洋学报, 2022, 41(2): 77-89.
[5]	向晨晖, 刘甲星, 柯志新, 周林滨, 谭烨辉. 大亚湾浮游植物粒级结构和种类组成对淡澳河河口水加富的响应^*[J]. 热带海洋学报, 2021, 40(2): 49-60.
[6]	苏芯莹, 钟瑜, 李尧, 谭美婷, 黄亚东, 刘珊, 徐向荣, 宋星宇. 珠江口典型海岛周边水域浮游植物分布特征及其影响因素*[J]. 热带海洋学报, 2020, 39(5): 30-42.
[7]	张立明, 谭烨辉, 李佳俊, 黄小平, 刘甲星. 大亚湾夏季浮游植物群落结构及对淡澳河输入的响应特征*[J]. 热带海洋学报, 2020, 39(5): 43-54.
[8]	周卫文, 李芊, 葛在名, 刘子嘉, 帅义萍, 马梦真. 珠江口羽流锋浮游植物群落对大气沉降的生态响应[J]. 热带海洋学报, 2020, 39(4): 50-60.
[9]	许泽婷, 李适宇, 胡嘉镗, 王思颖, 汪斌, 郭铭先, 耿兵绪. 夏季南海北部浮游植物对上升流与羽状流的响应[J]. 热带海洋学报, 2018, 37(6): 92-103.
[10]	王桂芬, 徐文龙, 周雯, 许占堂, 曹文熙. 基于船载走航观测高光谱颗粒物吸收系数反演浮游植物粒级结构*[J]. 热带海洋学报, 2018, 37(5): 50-61.
[11]	赵文静, 曹文熙, 胡水波, 王桂芬, 刘振宇, 徐敏. 南海典型海区浮游植物吸收光谱特征及遥感反演产品的精度评估[J]. 热带海洋学报, 2018, 37(3): 35-44.
[12]	谢福武, 刘华雪, 黄洪辉, 宋星宇. 大亚湾浮游植物粒级结构对温排水和营养盐输入的响应^*[J]. 热带海洋学报, 2018, 37(3): 55-64.
[13]	梁文钊, 唐丹玲. 南海西部夏季表层浮游植物粒径结构分布特征分析[J]. 热带海洋学报, 2017, 36(4): 93-101.
[14]	王符菁，林元烧，曹文清，张文静，郑连明，杨位迪，王宇杰. 北部湾北部浮游植物群落结构及其与营养盐的关系[J]. 热带海洋学报, 2015, 34(6): 73-85.
[15]	姚林杰, 曹文熙, 王桂芬, 许占堂, 胡水波, 周雯, 李彩. 基于支持向量机模型反演浮游植物粒级结构[J]. 热带海洋学报, 2015, 34(4): 37-47.