Using General Regression Neural Network to Retrieve Suspend Matter Concentration

Abstract

Abstract:

The measured data was obtained from the ocean color experiments in Pearl River Esturay in January, 2003 and January, 2004. General regression neural network model (GRNN) is established to retrieve the suspended matter concentration from remote sensing reflectance. At last, the concentration of suspend matter is derived based on moderate-resolution imaging spectroradiometer data. The result demonstrates that GRNN can get better prediction with a simple algorithm, and the model of using bands of 8~15 is better than other models, the averaged relative error is 17.01% and the correction coefficient is 0.965.

Key words: ocean optics, suspended matter, moderate-resolution imaging spectroradiometer, remote sensing reflectance, general regression neural network

CLC Number:

P733.3

LI Jian, MA Jin-Ji, JI Wei. Using General Regression Neural Network to Retrieve Suspend Matter Concentration[J]. Journal of Atmospheric and Environmental Optics, 2010, 5(4): 305-310.

References

[1] Richard L M, Brent A M. Using MODIS Terra 250 m imagery to map concentrations of total suspended matter in coastal waters [J]. Remote Sensing of Environment, 2004, 93(1-2): 259-266.
[2] Wang Fang, Li guosheng. Two parameters retrieval models of suspended sediment concentration of Bohai Sea based on MODIS data [J]. Geographical Research, 2007, 26(6): 1186-1196(in Chinese).
王芳, 李国胜. 海洋悬浮泥沙二元特征参数MODIS遥感反演模型研究 [J]. 地理研究, 2007, 26(6):1186-1196.
[3] Liu fenfen, Chen chuqun, Tang shilin, et al. A piecewise algorithm for retrieval of suspended sediment concentration based on in situ spectral data by MERIS in Zhujiang River estuary [J]. Journal of Tropical Oceanography, 2009, 28(1): 9-14(in Chinese).
刘汾汾, 陈楚群, 唐世林, 等. 基于现场光谱数据的珠江口MERIS悬浮泥沙分段算法 [J]. 热带海洋学报, 2009, 28(1): 9-14.
[4] Mao zhihua, Huang haiqing, Zhu qiankun, et al. The atmospheric correction algorithm of SeaWiFS data in China seas [J]. Oceanologia Etlimnologia Sinica, 2001, 32(6): 58l-587(in Chinese).
毛志华, 黄海清, 朱乾坤, 等. 我国海区SeaWiFS资料大气校正 [J]. 海洋与湖沼, 2001, 32(6): 58l-587. [5] Liu liangming, Zhang hongmei. The application of MODIS imagery to mapping concentrations of suspended sediments in coastal waters [J]. Remote Sensing for Land & Resources, 2006, (2): 42-45(in Chinese).
刘良明, 张红梅. 基于MODIS数据的悬浮泥沙定量遥感方法 [J]. 国土资源遥感, 2006, (2): 42-45.
[6] Meters L A K, Smith M O, Adams J B. Estimating suspended sediment concentration in surface waters of the Amazon river wetlands from Landsat images [J]. Remote Sensing Environment, 1993, 43(3): 281-301.
[7] Feisi Technology Products Center. The Theory of Neural Network and MATLAB7 Application [M]. Beijing: Publishing House of Electronics Industry, 2005(in Chinese).
飞思科技产品研发中心.神经网络理论与MATLAB7实现 [M]. 北京: 电子工业出版社, 2005.
[8] Wang jiacheng, Yang Shizhi, Ma jinji, et al. Automatic could detection applied to MODIS image in the southeast of China [J]. Geomatics and Information Science of Wuhan University, 2006, 31(3): 270-273(in Chinese).
王家成, 杨世植, 麻金继, 等. 东南沿海MODIS图像自动云检测的实现 [J]. 武汉大学学报(信息科学版), 2006, 31(3): 270-273.
[9] Ma Jinji, Chen hao, Jiang xinhua. A method to identify case Ⅰ and case Ⅱ waters based on the MODIS images [J]. Journal of Atmospheric and Environmental Optics, 2009, 4(3): 201-205(in Chinese).
麻金继, 陈浩, 江新华. 基于MODIS图像Ⅰ类水和Ⅱ类水的识别方法研究 [J]. 大气与环境光学学报, 2009, 4(3): 201-205(in Chinese).
[10] Ma Jinji, Yang Shizhi, Wang Xianbing, et al. Atmospheric correction: computing atmospheric diffuse transmittance [J]. Atmospheric Research, 2006, 80(1): 1-14.