Abstract：[Background] As an indispensable vegetation parameter in land ecosystem and hydrological models, Leaf area index controls many physiological and ecological processes of plant canopies. Therefore, real-time and accurate acquisition of regional LAI is very important for studying vegetation and soil erosion. Combining the physical model and the statistical model to estimate physiological parameters of the plant is non-destructive, simple, and highly efficient, which is one of the major approaches to quantitative remote sensing.[Methods] In the paper, leaf area index of broad-leaved forest was studied in Beijing. Geosail model, a combination of a geometric model and a mixed medium model, was used to simulate the broad band reflectance of canopy. Prospect model, a kind of leaf optical physical model, was used to simulate the leaf hyperspectral reflectance of broad-leaved forest. The leaf hyperspectral reflectance was converted into leaf broad band reflectance by the spectral response function, and then Geosail model used leaf broad band reflectance to simulate reflectance of canopy of broad-leaved forest. LAI and 7 kinds of remote sensing vegetation indexes were generated by simulated canopy reflectance, including RVI, NDVI, GNDVI, RDVI, SAVI, OSAVI, and MSAVI. Then 4 types of statistical regression methods (Linear function, quadratic function, exponential function, logarithmic function) and SVR algorithm were used to establish LAI inversion models. The accuracy of LAI inversion models was verified by Landsat 8 OLI remote sensing data and measured data.[Results] The analysis showed:1) SVR algorithm could improve accuracy and prediction accuracy of LAI inversion models than other statistical regression methods. 2) The prediction results of LAI inversion models showed that the performance of OSAVI was better than that of NDVI and other vegetation indices in the field of LAI inversion. This indicated that OSAVI could eliminate the most influence of atmospheric condition and soil background by using the correction factor of canopy background in computing formula, and had better anti-interference ability. 3)The LAI inversion modeling and models prediction showed that the modeling accuracy of NDVI index was very high, but in reality, the prediction accuracy of NDVI index was relatively low. 4) The accuracy and stability of the model constructed by the OSAVI and SVR algorithm were better, and it was the preference model for LAI inversion. Its prediction results were the most accurate, its value of coefficient of determination (R2) was 0.852 8, its value of root mean square error (RMSE) was 0.204 6, and its value of Slope was 0.988 1.[Conclusions] Therefore, the inversion method based on Geosail model and SVR algorithm was feasible, which could improve the accuracy of LAI inversion and provide new ideas and methods for the application of LAI inversion in large area. Through the LAI inversion model, the ground measured data could be converted to the remote sensing image data scale, which expanded the application potential of Geosail model, SVR algorithm and Landsat 8 OLI remote sensing data in LAI inversion.
杨维, 张学霞, 赵静瑶. 基于Geosail模型和SVR算法的叶面积指数遥感反演[J]. 中国水土保持科学, 2018, 16(6): 48-55.
YANG Wei, ZHANG Xuexia, ZHAO Jingyao. Remote sensing inversion of leaf area index based on Geosail model and SVR algorithm. SSWC, 2018, 16(6): 48-55.
王志慧, 姚文艺, 汤秋鸿, 等. 2000-2014年黄土高原植被叶面积指数时空变化特征[J]. 中国水土保持科学, 2017, 15(1):72. WANG Zhihui,YAO Wenyi, TANG Qiuhong, et al. Spatio-temporal change analysis of leaf area index in the Loess Plateau during 2000-2014[J]. Science of Soil and Water Conservation, 2017, 15(1):72.
[2]
林杰, 张金池, 顾哲衍, 等. 基于叶面积指数的植被覆盖管理措施因子C的遥感定量估算[J]. 林业科学, 2013,49(2):87. LIN Jie,ZHANG Jinchi, GU Zheyan, et al. Quantitative assessment of Vegetation cover and management factor based on leaf area index and remote sensing[J]. Scientia Silvae Sinicae, 2013,49(2):87.
[3]
刘晓臣, 范闻捷, 田庆久, 等. 不同叶面积指数反演方法比较研究[J]. 北京大学学报(自然科学版), 2008(2):57. LIU Xiaochen, FAN Wenjie, TIAN Qingjiu, et al. Comparative analysis among different methods of leaf area index inversion[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2008(2):57.
[4]
谷成燕, 杜华强, 周国模, 等.基于PROSAIL辐射传输模型的毛竹林叶面积指数遥感反演[J].应用生态学报, 2013, 24(8):2248. GU Chengyan, DU Huaqiang, ZHOU Guomo, et al. Retrieval of leaf area index of Moso bamboo forest with Landsat Thematic Mapper image based on PROSAIL canopy radiative transfer moedel[J]. Chinese Journal of Applied Ecology, 2013, 24(8):2248.
[5]
林卉, 梁亮, 张连蓬, 等.基于支持向量机回归算法的小麦叶面积指数高光谱遥感反演[J].农业工程学报, 2013, 29(11):139. LIN Hui, LIANG Liang, ZHANG Lianpeng, et al. Wheat leaf area index inversion with hyperspectral remote sensing based on support vector regression algorithm[J]. Transactions of the CSAE, 2013, 29(11):139.
[6]
杨敏, 林杰, 顾哲衍, 等.基于Landsat 8 OLI多光谱影像数据和BP神经网络的叶面积指数反演[J].中国水土保持科学, 2015, 13(4):86. YANG Min, LIN Jie, GU Zheyan, et al. Leaf area index retrieval based on Landsat 8 OLI multi-spectral image data and BP neural network[J]. Science of Soil and Water Conservation, 2015, 13(4):86.
[7]
薛云, 陈水森, 夏丽华, 等.几个典型的叶片/冠层模型[J].西部林业科学, 2005, 34(1):70. XUE Yun, CHEN Shuisen, XIA Lihua, et al. A brief introduction to several typical leaf/canopy models[J]. Journal of West China Forestry Science, 2005, 34(1):70.
[8]
杨贵军, 赵春江, 邢著荣, 等.基于PROBA/CHRIS遥感数据和PROSAIL模型的春小麦LAI反演[J].农业工程学报, 2011, 27(10):88. YANG Guijun, ZHAO Chunjiang, XING Zhurong, et al. LAI inversion of spring wheat based on PROBA/CHRIS hyperspectral multi-angular data and PROSAIL model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2011, 27(10):88.
[9]
李海洋, 范文义, 于颖, 等.基于Prospect, Liberty和Geosail模型的森林叶面积指数的反演[J].林业科学,2011,47(9):75. LI Haiyang, FAN Wenyi, YU Ying, et al. Leaf area index retrieval based on prospect, liberty and Geosail models[J]. Scientia Silvae Sinicae, 2011, 47(9):75.
[10]
QI J, KERR Y H, MORAN M S, et al. Leaf area index estimates using remotely sensed data and BRDF models in a semiarid region[J]. Remote Sensing of Environment, 2000, 73:18.
[11]
SANTIS A D, CHUVIECO E, VAUGHAN P J. Short-term assessment of burn severity using the inversion of PROSPECT and GeoSail models[J]. Remote Sensing of Environment, 2009, 113(1):126
[12]
SURYA S D, ROGER L K, NICOLAS H Y. Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer[J]. Remote Sensing of Environment, 2007, 107(1):348.
[13]
TAN K, WANG S, LIU Y, et al. Estimating nitrogen status of rice canopy using hyperspectral reflectance combined with BPSO-SVR in cold region[J]. Chemometrics & Intelligent Laboratory Systems, 2017, 172.
[14]
张强, 黄生志, 陈晓宏. 基于支持向量机的土壤湿度模拟及预测研究[J]. 土壤学报, 2013, 50(1):60. ZHANG Qiang, HUANG Shengzhi, CHEN Xiaohong. Simulation and prediction of soil moisture based on support vector machine technique[J]. Acta Pedologica Sinica, 2013, 50(1):60.
[15]
康峰峰. 北京西南山森林绿量遥感反演的研究[D]. 北京:北京林业大学, 2011:25. KANG Fengfeng. Study on remote sensing retrieval of forest vegetation quantity in mountainous area South-western Beijing China[D]. Beijing:Beijing Forestry University, 2011:25.
[16]
蒲莉莉, 刘斌.结合光谱响应函数的Landsat-8影像大气校正研究[J].遥感信息, 2015(2):117. PU Lili, LIU Bin. Atmospheric correction of Landsat-8 imagery based on spectral response function[J]. Remote Sensing Information, 2015(2):117.
[17]
HALL F G, HUEMMRICH K F. BOREAS TE-18 GeoSail Canopy Reflectance Model[M]. NASA Goddard Space Flight Center, 2000:3.
[18]
莫云华, 张文娟, 张连蓬. 基于PROSAIL模型的高光谱遥感图像模拟研究[J]. 红外, 2016, 37(9):7. MO Yunhua, ZHANG Wenjuan, ZHANG Lianpeng. Simulation of hyperspectral remote sensing image based on PROSAIL model[J]. Infrared, 2016, 37(9):7.
[19]
罗桑扎西. 基于SPOT5影像的植被类型识别及叶面积指数定量估算研究[D]. 南京:南京农业大学, 2013:54. LUOSANGZHAXI. Study on forest classification and estimation of LAI based on SPOT-5 image[D]. Nanjing:Nanjing Agricultural University, 2013:54.
[20]
林升梁, 刘志. 基于RBF核函数的支持向量机参数选择[J]. 浙江工业大学学报, 2007, 35(2):164. LIN Shengliang, LIU Zhi.[J]. Journal of Zhejiang University of Technology, 2007, 35(2):164.
[21]
CHANG C C, LIN C J. 2001. LIBSVM:A library for support vector machines[EB/OL]. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[22]
杜育璋, 姜小光, 张雨泽, 等.基于Landsat-8遥感数据和PROSAIL辐射传输模型反演叶面积指数[J].干旱区地理, 2016(5):1101. DU Yuzhang, JIANG Xiaoguang, ZHANG Yuze, et al. Retrieving leaf area index using PROSAIL radiative transfer model based on Landsat 8 image[J]. Arid Land Geography, 2016(5):1101.
[23]
邢丽玮, 李小娟, 李昂晟, 等. 基于高光谱与多光谱植被指数的洪河沼泽植被叶面积指数估算模型对比研究[J]. 湿地科学, 2013, 11(3):316. XING Liwei, LI Xiaojuan, LI Aangsheng, et al. A Comparative on estimation model for leaf area index of vegetation in marshes in Honghe National Nature Reserve based on hyperspectral and multispectral vegetation indices[J]. Wetland Science, 2013, 11(3):316.
[24]
吴朝阳, 牛铮.基于辐射传输模型的高光谱植被指数与叶绿素浓度及叶面积指数的线性关系改进[J].植物学报, 2008, 25(6):714. WU Chaoyang, NIU Zheng. Improvement in linearity between hyperspectral vegetation indices and chlorophyll content, leaf area index based on radiative transfer models[J]. Chinese Bulletin of Botany, 2008, 25(6):714.
[25]
梁栋, 管青松, 黄文江, 等. 基于支持向量机回归的冬小麦叶面积指数遥感反演[J]. 农业工程学报, 2013(7):117. LIANG Dong, GUAN Qingsong, HUANG Wenjiang, et al. Remote sensing inversion of leaf area index based on support vector machine regression in winter wheat[J]. Transactions of the CSAE, 2013(7):117.
[26]
刘轲,周清波,吴文斌, 等.基于多光谱与高光谱遥感数据的冬小麦叶面积指数反演比较[J].农业工程学报,2016,32(3):160. LIU Ke, ZHOU Qingbo, WU Wenbin, et al. Comparison between multispectral and hyperspectral remote senseing for LAI estimation[J]. Transactions of the CSAE, 2016, 32(3):160.
2018, Vol. 16 
