Leaf Area Index Estimation of Spring Maize with Canopy Hyperspectral Data Based on Linear Regression Algorithm
WANG Hong-bo1, ZHAO Zi-qi1, LIN Yi2, FENG Rui1, LI Li-guang1, ZHAO Xian-li1, WEN Ri-hong1, WEI Nan3, YAO Xin4, ZHANG Yu-shu1*
1. Institute of Atmospheric Environment, China Meteorological Administration, Shenyang 110166, China
2. Liaoning Province Public Meteorological Service Center, Shenyang 110166, China
3. Liaoning Province Meteorological Information Center, Shenyang 110166, China
4. Liaoning Meteorological Bureau, Shenyang 110166, China
Abstract：Based on the leaf area index (LAI) and canopy hyperspectral data during growing season of spring maize under different soil moisture conditions in Jinzhou, Liaoning province in 2013, the relationship between LAI and the characteristics of canopy hyperspectral in different development periods with different growth status were analyzed. Canopy spectral reflectance, its logarithm of the reciprocal and its first derivative in 350～2 500 nm of 313 valid data sets were collected and calculated, after rejecting the bands which were serious influenced by the atmospheric water content. Multivariate step linear regression (MSLR) and partial least squares regression (PLS) were used as the dimensionality reduction methods to establish the maize LAI models, and the models' precision were compared and tested respectively. The results show that, the LAI of spring maize has significant negative correlation with the spectral reflectance of visible band (350～680 nm), and infrared band (1 430～1 800 and 1 950～2 450 nm), but it has significant positive correlation with the logarithm of the reflectance reciprocal in these bands. The reflectance first derivative and LAI have significant positive correlation bands in visible band and infrared band (350～1 350 nm). Linear regression algorithm of spring maize LAI with the whole band of hyperspectral data, using PLS with the spectral reflectance as the independent variable to establish the LAI model, the fitting degree is better than that of MSLR; the root mean square error (RMSE) is 0.480 7, and using MSLR with the logarithm of the reflectance reciprocal and the reflectance first derivative as the independent variable, have better fitting degree than that of PLS, the RMSE are 0.333 5 and 0.348 8 respectively. Use MSLR with the logarithm of the spectral reflectance reciprocal as the independent variable to establish the maize LAI model, the fitting degree is better in the three canopy hyperspectral data of spring maize of the two regression algorithm.
Key words：Multivariate step linear regression (MSLR); Partial least squares regression (PLS); Spectral reflectance of hyperspectral; Logarithm of the reciprocal; First derivative
王宏博，赵梓淇，林 毅，冯 锐，李丽光，赵先丽，温日红，魏 楠，姚 欣，张玉书. 基于线性回归算法的春玉米叶面积指数的冠层高光谱反演研究[J]. 光谱学与光谱分析, 2017, 37(05): 1489-1496.
WANG Hong-bo, ZHAO Zi-qi, LIN Yi, FENG Rui, LI Li-guang, ZHAO Xian-li, WEN Ri-hong, WEI Nan, YAO Xin, ZHANG Yu-shu. Leaf Area Index Estimation of Spring Maize with Canopy Hyperspectral Data Based on Linear Regression Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(05): 1489-1496.
[1] Arora V K, Boer G J. A. Earth Interactions, 2003, 7(6): 1.
[2] CHEN Hai-shan, NI Dong-hong, LI Zhong-xian, et al(陈海山, 倪东鸿, 李忠贤, 等). Journal of Nanjing Institute of Meteorology(南京气象学院学报), 2006, 29(6): 725.
[3] Darvishzadeh R, Skidmore A, Atzberger C, et al. International Journal of Applied Earth Observation and Geoinformation, 2008, 10(3): 358.
[4] XUE Li-hong, CAO Wei-xin, LUO Wei-hong, et al(薛利红, 曹卫星, 罗卫红, 等). Acta Phytoecologica Sinica(植物生态学报), 2004, 28(1): 47.
[5] LI Feng-xiu, ZHANG Bai, SONG Kai-shan, et al(李凤秀, 张 柏, 宋开山, 等). Remote Sensing Technology and Application(遥感技术与应用), 2007, 22(5): 586.
[6] Feng R, Zhang Y S, Yu W Y, et al. Acta Ecologica Sinica, 2013, 33(6): 301.
[7] Lee K S, Kennedy R E, Cohen W B, et al. Remote Sensing of Environment, 2004, 91(3): 508.
[8] LIANG Liang, YANG Min-hua, ZHANG Lian-peng, et al(梁 亮, 杨敏华, 张连蓬, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2011, 31(6): 1658.
[9] LIN Hui, LIANG Liang, ZHANG Lian-peng, et al(林 卉, 梁 亮, 张连篷, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013, 29(11): 139.
[10] ZHANG Zheng-yang, MA Xin-ming, JIA Fang-fang, et al(张正杨, 马新明, 贾方方, 等). Acta Ecologica Sinica(生态学报), 2012, 32(1): 0168.
[11] QIU Lin, LIN Hui, SUN Hua, et al(邱 林, 林 辉, 孙 华, 等). Journal of Central South University of Forestry & Technology(中南林业科技大学学报), 2012, 32(7): 28.
[12] BAI Jun-hua, LI Shao-kun, WANG Ke-ru, et al(柏军华, 李少昆, 王克如, 等). Scientia Agricultura Sinica(中国农业科学), 2007, 40(1): 63.
[13] Li X C, Zhang Y J, Bao Y S, et al. Remote Sensing, 2014, 6(7): 6221.
[14] Delegldo J, Verrelst J, Meza C M, et al. European Journal of Agronomy, 2013(46): 42.
[15] FENG Xiao, ZHENG Guo-qing, QIAO Shu, et al(冯 晓, 郑国清, 乔 淑, 等). Journal of Maize Sciences(玉米科学), 2008, 16(6): 86.
[16] MA Xue-yan, ZHOU Guang-sheng(麻雪艳, 周广胜). Acta Ecologica Sinica(生态学报), 2013, 33(8): 2596.
[17] SONG Kai-shan, ZHANG Bai, WANG Zong-ming, et al(宋开山, 张 柏, 王宗明, 等). Scientia Agricultura Sinica, 2006, 39(6): 1138.
[18] SHEN Guang-rong, WANG Ren-chao(申广荣, 王人潮). Journal of Zhejiang University·Agriculture and Life Sciences(浙江大学学报·农业与生命科学版), 2001, 27(6): 682.
[19] WANG Hui-wen(王惠文). Partial Least-Squares Regression-Method and Applications(偏最小二乘回归方法及其应用). Beijing: National Defense Industry Press(北京：国防工业出版社), 1994.
[20] Wold S, Albano C, Dun M. Pattern Regression Finding and Using Regularities in Multivariate Data. London: Analysis Applied Science Publication, 1983.
[21] TONG Qing-xi, ZHANG Bing, ZHENG Lan-fen(童庆禧, 张 兵, 郑兰芬). Hyperspectral Remote Sensing(高光谱遥感—原理、技术与应用). Beijing: Higher Education Press(北京：高等教育出版社), 2006.
