The Application of Hyper-spectral Data and RBF Neural Network Method to Retrieval of Leaf Area Index of Grassland
BAO Gang1,2,3, QIN Zhi-hao3, ZHOU Yi3, BAO Yu-hai2, XIN Xiao-ping1, HONG Yu4, HAI Quan-sheng5
1. Hulunber Grassland Ecosystem Observation and Research Station, Beijing 100081, China;
2. Inner Mongolia Key Laboratory of Remote Sensing and Geographic Information System, Inner Mongolia Normal University, Huhehot 010022, China;
3. International Institute for Earth System Science, Nanjing University, Nanjing 210093, China;
4. College of Life Science and Technology, Inner Mongolia Normal University, Huhehot 010022, China;
5. Baotou Normal University, Baotou 014030, China
Abstract：In accordance with the 120 sites of grassland canopy spectral reflectance and the leaf area index (LAI) data collected by Chinese Academy of Agricultural Science,the method of Radial Basis Function (RBF) neural network was developed for the prediction of LAI after the compression of spectral reflectance using principal component analysis (PCA).The PCA results show that the cumulative reliability of the first 9 PCs is up to 99.782%,covering the majority of original spectral information. The 120 sites of LAI and 9 PC samples were classified randomly for training dataset (90 sites) and predicting dataset (30 sites),and were used to establish the neural network and predict the LAI, respectively. The results show that the accuracy rate of training data is up to 100% (RMSE=0.009 6,R2=0.999).The root mean square error (RMSE) and correlation coefficient (R2) for the prediction dataset are 0.839 and 0.218 6 respectivdg, thus achieving more preferable results and improved the accuracy (RMSE=0.416 5,R2=0.570)of the traditional multiple linear regression method.
包刚, 覃志豪, 周义, 包玉海, 辛晓平, 红雨, 海全胜. 基于高光谱数据和RBF神经网络方法的草地叶面积指数反演[J]. 国土资源遥感, 2012, 24(2): 7-11.
BAO Gang, QIN Zhi-hao, ZHOU Yi, BAO Yu-hai, XIN Xiao-ping, HONG Yu, HAI Quan-sheng. The Application of Hyper-spectral Data and RBF Neural Network Method to Retrieval of Leaf Area Index of Grassland. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(2): 7-11.
[1] 蒙继华,吴炳方,李强子.全国农作物叶面积指数遥感估算方法[J].农业工程学报,2007,23(2):160-167.[2] Chen J M,Cihlar J.Retrieving Leaf Area Index of Boreal Conifer Forests Using Landsat TM Images[J].Remote Sensing of Environment,1996,55(2):153-162.[3] 吴彤,倪绍祥,李云梅,等.基于地面高光谱数据的东亚飞蝗危害程度监测[J].遥感学报,2007,11(1):104-108.[4] 赵巧丽,郑国清,段韶芬,等.基于冠层反射光谱的玉米LAI和地上干物重估测研究[J].华北农学报,2008,23(1):219-222.[5] 马勤建,王登伟,黄春燕,等.棉花叶面积指数和地上干物质积累量的高光谱估算模型研究[J].棉花学报,2008,20(3):217-222.[6] 王登伟,赵鹏举,黄春燕,等.基于棉花冠层FPAR的LAI和地面上鲜生物量估算研究[J].西北农林科技大学学报:自然科学版,2009,37(3):114-118.[7] Moran M S,Clarke T R,Inoue Y,et al.Estimating Crop Water Deficit Using the Relation Between Surface-air Temperature and Spectral Vegetation Index[J].Remote Sensing of Environment,1994,49(3):246-263.[8] Moran M S,Mass S J,Pinter P J Tr.Combining Remote Sensing and Modeling for Estimating Surface Evaporation and Biomass Production[J].Remote Sensing Review,1995,12(3-4):335-353.[9] 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,2006:116-130.[10] Hummels D M,Ahemed W,Musavi M T.Adaptive Detection of Small Sinusoidal Signals in Non-gaussian Noise Using an RBF Neural Network[J].IEEE Trans on Neural Networks,1995,6(1):214-219.[11] 许东,吴铮.基于MATLAB 6 x的系统分析与设计——神经网络[M].2版.西安:电子科技大学出版社,2002.[12] 单杨,朱向荣,许青松,等.近红外光谱结合小波变换-径向基神经网络用于奶粉蛋白质与脂肪含量的测定[J].红外与毫米波学报,2010,29(2):129-131.[13] Kokaly R F,Clark R N.Spectroscopic Determination of Leaf Biochemistry Using Band-depth Analysis of Absorption Features and Stepwise Multiple Linear Regression[J].Remote Sensing of Environment,1999,67(3):267-287.[14] Curran P J,Dungan J L,Peterson D L.Estimating the Foliar Biochemical Concentration of Leaves with Reflectance Spectrometry:Testing the Kokaly and Clark Methodologies[J].Remote Sensing of Environment,2001,76(3):349-359.
2012, Vol. 24 
