地球科学进展 ›› 2012, Vol. 27 ›› Issue (2): 202 -208. doi: 10.11867/j.issn.1001-8166.2012.02.0202

研究论文 上一篇    下一篇

基于遗传神经网络的克钦湖叶绿素反演研究
朱子先, 臧淑英 *   
  1. 黑龙江省普通高等学校地理环境遥感监测重点实验室,哈尔滨师范大学地理科学学院,黑龙江 哈尔滨 150025
  • 收稿日期:2011-08-27 修回日期:2011-10-16 出版日期:2012-02-10
  • 通讯作者: 臧淑英(1963-),男,黑龙江哈尔滨人,博士生导师,主要从事LUCC、3S综合应用研究.  E-mail:zsy6311@163.com
  • 基金资助:

    国家自然科学基金重点项目“松嫩平原LUCC对湖沼湿地生态系统的影响及调控机理研究”(编号:41030743)资助.

Research on Chlorophyll Concentration Retrieval Models of Keqin Lake based on Genetic Neural Networks

Zhu Zixian, Zang Shuying   

  1. Key Laboratory of Remote Sensing Monitoring of Geographic Environment, College of Geographical Science, Harbin Normal University,Harbin150025, China
  • Received:2011-08-27 Revised:2011-10-16 Online:2012-02-10 Published:2012-02-10

]叶绿素a浓度能够在一定程度上反映内陆湖泊水质情况。为实现对克钦湖水体叶绿素a浓度的监测,于2010 年8月15日对克钦湖进行了现场光谱测量和同步采样。通过分析叶绿素a浓度和光谱数据之间的关系,建立基于反射比、人工神经网络和遗传神经网络的叶绿素a浓度估测模型。结果表明:利用R700nm/R670nm反射比建立的模型估测精度为R2= 0.67;人工神经网络模型的估测精度较高,R2= 0.882;将遗传算法引入神经网络之后,模型的估测精度进一步提高,R2达到0.956,将模型预测的结果与克里格内插法相结合对研究区的叶绿素a空间分布情况进行定量估测,发现北湖的叶绿素a浓度明显高于南湖,有由北向南逐渐递减的趋势,这为今后利用高光谱数据对克钦湖叶绿素a浓度大面积遥感反演提供了研究基础。

The concentration of Chlorophyll-a could reflect the water quality of inland lakes to some extent. In order to monitor the concentration of chlorophyll-a, hyperspectral reflectance was measured from July to August in 2010 with ASD FieldSpec HH in Keqin Lake. Concurrently, water samples were collected. Three models including spectral ratio, artificial neural networks, and genetic neural networks were developed by analyzing the correlations between concentration and hyperspectral reflectance data. The results show that spectral ratio gives determination coefficient R2=0.67. Artificial neural networks gives better results with higher determination coefficient R2=0.882 which was further improved to 0.956 after introducing genetic algorithm to neural networks. All of the three models with significance level P<0.01, and are applied to estimate chlorophyll-a concentration. Finally, the author used the predicted results of the GANN model and the Kriging analysis technique to obtain the quantitative estimation of the spatial distribution of Chlorophyll-a in the study area. These algorithms provided a research basis of future large area remote sensing inversion with hyperspectral data in Keqin Lake.

中图分类号: 

[1]Li Suju, Wu Qing, Wang Xuejun, et al. Correlations between reflectance spectra and contents of chlorophyll-a in Chaohu Lake[J]. Journal of Lake Sciences, 2002, 14(3): 228-234.[李素菊,吴情,王学军,等.巢湖浮游植物叶绿素含量与反射光谱特征的关系[J]. 湖泊科学,2002,14(3): 228-234.]
[2]Song Ping, Liu Yuanbo, Liu Chunyan. Advances in satellite retrieval of terrestrial surface water parameters[J].Advances in Earth Science,2011,7(26): 731-740.[宋平,刘元波,刘春燕.陆地水体参数的卫星遥感反演研究进展[J]. 地球科学进展,2011,7(26):731-740.]
[3]Shu Xiaozhou, Yin Qiu, Kuang Dingbo. Relationship between algal chlorophyll concentration and spectral reflectance of  inland 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.]
[4]Hoogenboom H J,Dekker A G,Althuis I J A. Simulation of AVIRIS sensitivity for detecting Chlorophyll over coastal and inland waters[J]. Remote Sensing of Environment,1998,65: 333-340.
[5]Frater R N. Hyperspectral remote sensing of turbidity and chlorophyll-a among nebraska sand hills lakes[J].International Journal of Remote Sensing, 1998, 19(8): 1 579-1 589.
[6]Lu Zhijuan, Zhu Ling, Pei Hongping, et al. The model of chlorophyll-a concentration forecast in the West Lake based on wavelet analysis and BP neural networks[J]. Acta Ecological Sinica, 2008, 28(10): 4 965-4 973.[卢志娟,朱玲,裴洪平,等.基于小波分析与BP神经网络的西湖叶绿素a浓度预测模型[J]. 生态学报, 2008,28(10): 4 965-4 973.]
[7]Kong Weijuan, Ma Ronghua, Duan Hongtao. The neural network model for estimation of chlorophyll-a with water temperature in Lake Taihu[J]. Journal of Lake Sciences, 2009, 21(2): 193-198.[孔维娟,马荣华,段洪涛. 结合温度因子估算太湖叶绿素a含量的神经网络模型[J]. 湖泊科学,2009,21(2): 193-198.]
[8]Gao Duo, Fang Shenghui, Zhang Xuehu, et al. Water quality parameter identification of Wuhan Donghu Lake based on genetic algorithm[J]. Journal of Geomatics, 2006, 31(6): 42-44. [高铎,方圣辉,张雪虎,等. 基于遗传算法的东湖水质参数反演方法探讨[J]. 测绘信息与工程, 2006, 31(6): 42-44.]
[9]Yi Weihong, Yang Liu, Zhang Zhengxiang. Method of wetland classification based on Landsat7 ETM+ image[J].Wetland Science, 2004, 2(3):208-212.[衣伟宏,杨柳,张正祥.基于ETM+影像的扎龙湿地遥感分类研究[J]. 湿地科学,2004,2(3): 208-212.]
[10]Tang Junwu, Tian Guoliang, Wang Xiaoyong, et al. The methods of water spectra measurement and analysisⅠ: Above-water method[J]. Journal of Remote Sensing, 2004, 8(1): 37-44.[唐军武,田国良,汪小勇,等.水体光谱测量与分析Ⅰ:水面以上测量法[J]. 遥感学报,2004,8(1): 37-44.]
[11]Jiao Hongbo, Zha Yong, Li Yunmei, et al. Modelling chlorophyll-a concentration in Taihu Lake from hyperspectral reflectance data[J]. Journal of Remote Sensing, 2006, 10(2): 242-248.[焦红波,查勇,李云梅,等. 基于高光谱遥感反射比的太湖水体叶绿素a含量估算模型[J]. 遥感学报,2006,10(2):242-248.]
[12]Oron G,Gitelson A. Real-time quality monitoring by remote sensing of contaminated water-bodies: Waste stabilization pond effluent[J]. Water Research,1996,30(12): 3 106-3 114.
[13]Gitelson A. The peak near 700nm on radiance spectra of algae and water relationships of its magnitude and position with chlorophyll[J]. Internation Journal of Remote Sensing,1993,13(17): 3 367-3 373.
[14]Liu Ying, Wang Ke, Zhou Bin, et al. Preliminary study on hyperspectral remote sensing of Qiandao Lake chlorophyll-a concentration[J].Journal of Zhejiang University (Agriculture  & Life Science),2003, 29(6): 621-626.[刘英,王珂,周斌,等. 千岛湖水体叶绿素浓度高光谱遥感检测初报[J]. 浙江大学学报:农业与生命科学版,2003,29(6): 621-626.]
[15]Koponen S,Pulliainen J,Kallio K,et al. Lake water quality classification with airborne hyperspectral spectrometer and simulated MERIS data[J].Remote Sensing of Environment,2002,79:51-59.
[16]Li Weichao, Song Dameng, Chen Bin. Artificial neural network based on genetic algorithm[J]. Computer Engineering and Design, 2006, 27(2): 316-318.[李伟超,宋大盟,陈斌. 基于遗传算法的人工神经网络[J]. 计算机工程与设计,2006,27(2): 316-318.]
[17]Zhou Shiguan, Li Zhongxia. Genetic algorithm for optimization of neural network structure and weight distribution[J]. Measurement and Control Technique,2004, 23(4): 48-49. [周世官,李钟侠.神经网络结构及其权值优化的遗传算法[J]. 测控技术,2004,23(4):48-49.]
[18]Yu Jianli, Kroumov V, Sun Zengqi, et al. Fast algorithm for path planning based on neural network[J]. Robot,2001, 23(3): 150-158.[禹建丽,Kroumov V,孙增圻,等.一种快速神经网络路径规划算法[J]. 机器人,2001,23(3): 150-158.]
[19]Jin Jianbin, Wang Yuanqin, Chen Yuan. Application of artificial neural network based on genetic algorithm to cooperative transport of multi-robots system[J]. Computer and Modernization,2010, 1(9): 88-91.[靳建彬,王元钦,陈源.基于遗传算法的BP神经网络优化策略研究[J]. 计算机与现代化,2010,1(9): 88-91.]
[20]Wang Xuejun. The combination of spatial analysis technique and GIS[J].Geographical Research, 1997, 16(3): 70-74.[王学军. 空间分析技术与地理信息系统的结合[J]. 地理研究,1997,16(3): 70-74.]

[1] 王根, 张华, 杨寅. 高光谱大气红外探测器AIRS资料质量控制研究进展[J]. 地球科学进展, 2017, 32(2): 139-150.
[2] 崔月菊, 杜建国, 李营, 刘雷, 周晓成, 陈扬, 陈志, 韩晓昆. 张渤地震带高光谱气体地球化学特征[J]. 地球科学进展, 2016, 31(1): 59-65.
[3] 崔月菊, 李静, 王燕艳, 刘永梅, 陈志, 杜建国. 遥感气体探测技术在地震监测中的应用[J]. 地球科学进展, 2015, 30(2): 284-294.
[4] 张韧, 洪梅, 刘科峰, 朱伟军. 基于副热带高压异常活动个例的动力模型重构与变异特性剖析[J]. 地球科学进展, 2014, 29(11): 1250-1261.
[5] 刘旸,蔡波,班显秀,袁健,耿树江,赵姝慧,李帅彬. AIRS红外高光谱资料反演大气水汽廓线研究进展[J]. 地球科学进展, 2013, 28(8): 890-896.
[6] 王志慧, 刘良云. 黑河中游绿洲灌溉区土地覆盖与种植结构空间格局遥感监测[J]. 地球科学进展, 2013, 28(8): 948-956.
[7] 崔月菊, 杜建国, 张德会,孙玉涛. 应用于地震预测的遥感气体地球化学[J]. 地球科学进展, 2012, 27(10): 1173-1177.
[8] 温健婷,张霞,张兵,赵冬. 土壤铅含量高光谱遥感反演中波段选择方法研究[J]. 地球科学进展, 2010, 25(6): 625-629.
[9] 李双成,郑度. 人工神经网络模型在地学研究中的应用进展[J]. 地球科学进展, 2003, 18(1): 68-076.
[10] 赵德华,李建龙,宋子键. 高光谱技术提取植被生化参数机理与方法研究进展[J]. 地球科学进展, 2003, 18(1): 94-099.
阅读次数
全文


摘要