Please wait a minute...
 
国土资源遥感  2012, Vol. 24 Issue (3): 6-10    DOI: 10.6046/gtzyyg.2012.03.02
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
用人工神经网络方法反演水体吸收系数
朱金山1,2, 梁士英1, 苏循波3
1. 山东科技大学测绘科学与工程学院, 青岛 266590;
2. 国家测绘局海岛(礁)测绘重点实验室, 青岛 266590;
3. 山东科技大学土木建筑学院, 青岛 266590
A Method to Retrieve the Oceanic Absorption Coefficient Based on Artificial Neural Network
ZHU Jin-shan1,2, LIANG Shi-ying1, SU Xun-bo3
1. Geomatics College, Shandong University of Science and Technology, Qingdao 266590, China;
2. Key Laboratory of Surveying and Mapping Technology on Island and Reed, SBSM, Qingdao 266590, China;
3. College of Civil and Architectural Engineering, Shandong University of Science and Technology, Qingdao 266590, China
全文: PDF(951 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 吸收系数是水体的固有光学参数,是进行水体光学遥感研究的基础。讨论了一种基于人工神经网络(artificial neural networks,ANN)、利用遥感反射比数据反演水体吸收系数的方法。该方法用实测的水体遥感反射比(Rrs)数据集建立BP神经网络,用以反演水体在波长440 nm处的吸收系数(α(440))。实测遥感反射比数据集的80%数据用于训练样本,20%数据用于预测样本。研究结果表明: 正确选择神经网络的传递函数、训练函数和隐含层节点个数是至关重要的; 用最优的传递函数、训练函数和隐含层节点个数得到的预测结果与实际测量结果的相关系数高达0.978,证明了该方法的可行性。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
王长海
刘登忠
刘金龙
黄慧
关键词 遥感解译混杂带岩片组合蛇绿岩    
Abstract:The absorption coefficient of water is an inherent optical parameter and constitutes the foundation of research on water optics remote sensing. A method for retrieving the oceanic absorption coefficient using the data of remote sensing reflectance (Rrs) and based on the artificial neural network (ANN) is presented in this paper. The algorithm retrieves the oceanic absorption coefficient with 440 nm as its wavelength, using the situ data of remote sensing reflectance (Rrs) to establish BP neural network. 80% of the situ data of Rrs were used for training data set, and the other 20% were used for testing data set. The results show that making the right choice of the hidden layer joints, transfer function and train function is very important. If we choose the optimal hidden layer joints, transfer function and train function, the correlation coefficient between testing data and situ data can be as high as 0.978, which shows that the method for retrieving the oceanic absorption coefficient based on the artificial neural network is effective.
Key wordsremote sensing interpretation    melange zone    slices assemblage    ophiolite
收稿日期: 2011-09-15      出版日期: 2012-08-20
:  TP75  
基金资助:国家测绘局海岛(礁)测绘重点实验室开放基金(编号: 2009A04); "泰山学者"建设工程特别基金; 国家自然科学基金(编号: 41074003)及山东科技大学研究生科技创新基金(编号: YCA110315)共同资助。
引用本文:   
朱金山, 梁士英, 苏循波. 用人工神经网络方法反演水体吸收系数[J]. 国土资源遥感, 2012, 24(3): 6-10.
ZHU Jin-shan, LIANG Shi-ying, SU Xun-bo. A Method to Retrieve the Oceanic Absorption Coefficient Based on Artificial Neural Network. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(3): 6-10.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2012.03.02      或      https://www.gtzyyg.com/CN/Y2012/V24/I3/6
[1] Jerlov N G.Marine Optics[M].New York:Elsevier,1976:11-20.
[2] Marshall B R,Smith R C.Raman Scattering and In-water Ocean Properties[J].Applied Optics,1990,29(1):71-84.
[3] Hawes S K.Quantum Fluorescence Efficiencies of Marine Fulvic and Humic Acids[D].USA:University of South Florida,Master Master’s Thesis Depth of Marine Science,1992:1-92.
[4] Morel A,Gentili B.Diffuse Reflectance of Oceanic Waters:Its Dependence on Sun Angle as Influenced by the Molecular Scattering Contribution[J].Applied Optics,1991,30(30):4427-4438.
[5] Morel A,Gentili B.Diffuse Reflectance of Oceanic Waters:Ⅱ Bidirectional Aspects[J].Applied Optics,1993,32(33):6864-6879.
[6] Morel A,Gentili B.Diffuse Reflectance of Oceanic Waters:Ⅲ Implication of Bidirectionality for the Remote Sensing Problem[J].Applied Optics,1996,35(24):4666-4952.
[7] Morel A,Antoine D,Gentili B.Bidirectional Reflectance of Oceanic Waters:Accounting for Raman Emission and Varying Particle Scattering Phase Function[J].Applied Optics,2002,41(30):6289-6306.
[8] 胡连波.黄东海水体漫衰减系数研究[D].青岛:中国海洋大学,2008. Hu L B.Research on the Diffuse Attenuation Coefficients in the East China Seas[D].Qingdao:Ocean University of China,2008(in Chinese with English Abstract).
[9] Morel A,Prieur L.Analysis of Variations in Ocean Color[J].Limnology and Oceanography,1977,22(4):709-722.
[10] Gordon H R,Morel A.Remote Assessment of Ocean Color for Interpretation of Satellite Visible Imagery:A Review[M].New York:New York,Springer-Verlag,Lecture Notes on Coastal and Estuarine Studies,1983(4):1-114.
[11] 胡连波,刘智深.利用准分析算法由遥感反射比反演黄海水体吸收系数[J].中国海洋大学学报:自然科学版,2007,37(s2):157-164. Hu L B,Liu Z S.Deriving Absorption Coefficients from Remote Sensing Reflectance Using the Quasi-analytical Algorithm (QAA) in the Yellow Sea[J].Periodical of Ocean University of China:Natural Science Version,2007,37(s2):157-164(in Chinese with English Abstract).
[12] Bricaud A,Babin M,Morel A,et al.Variability in the Chlorophyll Specific Absorption Coefficients of Natural Phytoplankton:Analysis and Parameterization[J].J Geophys Res,1995,100(7):13321-13332.
[13] Lee Z P,Carder K L,Peacock T G,et al.Method to Derive Ocean Absorption Coefficients from Remote Sensing Reflectance[J].Applied Optics,1996,35(3):453-462.
[14] He M X,Liu Z S,Du K P,et al.Retrieval of Chlorophyll from Remote-Sensing Reflectance in the China Seas[J].Applied Optics,2000,39(15):2467-2474.
[15] 王晓梅,唐军武,宋庆君,等.黄海、东海水体总吸收系数光谱特性及其统计反演模式研究[J].海洋与湖沼,2006,37(3):256-263. Wang X M,Tang J W,Song Q J,et al.The Statistic Inversion Algorithm’s and Spectral Relations of Total Absorption Coefficients for the Huanghai Sea and the East China Sea[J].Oceanologia Et Limnologia Sinica,2006,37(3):256-263(in Chinese with English Abstract).
[16] Lee Z P,Carder K L,Mobley C D,et al.Hyperspectral Remote Sensing for Shallow Waters.1.Semi-analytical Model[J].Applied Optics,1998,37(27):6329-6338.
[17] 刘雪锋,张亭禄.由粒子吸收光谱提取浮游植物吸收光谱的人工神经网络方法[J].海洋技术,2006,25(3):45-50. Liu X F,Zhang T L.An Artificial Neural Network Method for Extraction of Phytoplankton Absorption Spectra from Total Particulate Absorption Spectra[J].Ocean Technology,2006,25(3):45-50(in Chinese with English Abstract).
[18] 施英妮.基于人工神经网络技术的高光谱遥感浅海水深反演研究[D].青岛:中国海洋大学,2005. Shi Y N.Study of the Hyperspectral Remote Sensing of Shallow Waters Bathymetry with Artificial Neural Network Technology[D].Qingdao:Ocean University of China,2005(in Chinese with English Abstract).
[1] 刘志中, 宋英旭, 叶润青. 渝东北2014年“8·31”暴雨诱发滑坡遥感解译与分析[J]. 自然资源遥感, 2021, 33(4): 192-199.
[2] 谢小平, 白毛伟, 陈芝聪, 柳伟波, 席书娜. 龙门山断裂带北东段活动断裂的遥感影像解译及构造活动性分析[J]. 国土资源遥感, 2019, 31(1): 237-246.
[3] 随欣欣, 眭素文. 基于MapGIS和ArcGIS的遥感解译成果图件数据库设计与实现[J]. 国土资源遥感, 2018, 30(4): 218-224.
[4] 随欣欣, 眭素文, 刘锟. 面向遥感业务应用的解译成果数据管理系统研究和构建[J]. 国土资源遥感, 2018, 30(3): 238-243.
[5] 王瑞军, 闫柏琨, 李名松, 董双发, 孙永彬, 汪冰. 甘肃红山地区重要控矿地质单元GF-1数据遥感解译与应用[J]. 国土资源遥感, 2018, 30(2): 162-170.
[6] 王瑞军, 董双发, 孙永彬, 李婧玥. 基于高分一号卫星数据新疆索拉克地区控矿地质单元遥感解译与应用[J]. 国土资源遥感, 2017, 29(s1): 137-143.
[7] 张策, 揭文辉, 付丽华, 魏本赞. 新疆新源县滑坡灾害遥感影像特征及分布规律[J]. 国土资源遥感, 2017, 29(s1): 81-84.
[8] 李海鹰. 国产高分辨率遥感数据在环境地质调查中的应用[J]. 国土资源遥感, 2017, 29(s1): 46-51.
[9] 李晓民, 张焜, 李冬玲, 李得林, 李宗仁, 张兴. 青藏高原札达地区多年冻土遥感技术圈定方法与应用[J]. 国土资源遥感, 2017, 29(1): 57-64.
[10] 李晓民, 燕云鹏, 刘刚, 李冬玲, 张兴, 庄永成. ZY-1 02C星数据在西藏札达地区水文地质调查中的应用[J]. 国土资源遥感, 2016, 28(4): 141-148.
[11] 高孟绪, 王卷乐, 柏中强, 祝俊祥. 基于RapidEye影像的农村居民地遥感监测——以江西省泰和县为例[J]. 国土资源遥感, 2016, 28(1): 130-135.
[12] 宿渊源, 张景发, 何仲太, 姜文亮, 蒋洪波, 李强. 资源卫星三号DEM数据在活动构造定量研究中的应用评价[J]. 国土资源遥感, 2015, 27(4): 122-130.
[13] 刘德长, 童勤龙, 林子喻, 杨国防. 欧洲大陆遥感地质解译、诠释与矿产勘查战略选区[J]. 国土资源遥感, 2015, 27(3): 136-143.
[14] 胥兵, 方臣. ZY-102C星图像与ETM+图像融合方法及效果评价[J]. 国土资源遥感, 2014, 26(3): 80-85.
[15] 徐岳仁, 何宏林, 陈立泽, 申旭辉. 基于CBERS数据的福建南平地质灾害动态遥感解译[J]. 国土资源遥感, 2014, 26(3): 153-159.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发