浏览全部资源
扫码关注微信
Received：29 July 2017，
Revised：2017-9-25，
Published：16 May 2018
移动端阅览
目的
2
叶面积指数（LAI）是重要的植被生物理化参数，对农作物长势和产量预测具有重要研究意义。基于物理模型和经验模型的LAI估算方法被认为是当前最常用的方法，但两种方法的估算效率和精度有限。近年来，机器学习算法在遥感监测领域广泛应用，算法具有描述非线性数据拟合、融合更多辅助信息的能力，为了评价机器学习算法在玉米LAI遥感估算中的适用性，本文分析比较了随机森林和BP神经网络算法估算玉米LAI的能力，并与传统经验模型进行了比较。
方法
2
以河北省怀来县东花园镇为研究区，基于野外实测玉米LAI数据，结合同时期国产高分卫星（GF1-WFV影像），首先分析了8种植被指数与LAI的相关性，进而采用保留交叉验证的方式将所有样本数据分为两部分，65%的数据作为模型训练集，35%作为验证集，重复随机分为3组，构建以8种植被指数为自变量，对应LAI值为因变量的RF模型、BP神经网络模型及传统经验模型。采用决定系数
$$ R^2$$
和均方根误差（RMSE）作为模型评价指标。
结果
2
8种植被指数与LAI的相关性分析表明所有样本数据中，实测LAI值与各植被指数均在（
$$ P$$
＜0.01）水平下极显著相关，且相关系数均高于0.5；将3组不同样本数据在随机森林、BP神经网络算法中多次训练，并基于验证数据集进行估算精度检验，经验模型采用训练数据集建模，验证数据集检验，结果表明，RF模型表现出了较强的预测能力，LAI预测值与实测值
$$ R^2$$
分别为0.681、0.757、0.701，均高于BP模型（0.504、0.589、0.605）和经验模型（0.492、0.557、0.531），对应RMSE分别为0.264、0.292、0.259；均低于BP模型（0.284、0.410、0.283）和经验模型（0.541、0.398、0.306）。
结论
2
研究表明，RF算法能更好地进行玉米LAI遥感估算，为快速准确进行农作物LAI遥感监测提供了技术参考。
Objective
2
Leaf area index (LAI) is an important biological and physical parameter of vegetation
and it plays an important role in predicting crop growth and yield. A number of LAI estimation methods have been developed from remotely sensed data
each of which presents unique advantages and limitations. The empirical regression and physical models are the most widely used among these methods. The empirical regression model can reduce the effect of background noise on the spectral reflectance of plant canopies
and the physical model simulates the radiative transfer process in vegetation and describes the canopy spectral variation as a function of canopy
leaf
and soil background characteristics. However
the efficiency and accuracy of the two methods are limited. In recent years
machine learning algorithms have been widely used in remote sensing monitoring
and they can describe nonlinear data fitting and fuse more auxiliary information. This study evaluates the applicability of machine learning algorithms in maize LAI remote sensing estimation.
Method
2
In this study
the east garden of Huailai County in Hebei Province was used as the study area. Eight kinds of vegetation indices based on the GF1 WFV satellite images were calculated
and the correlation between the same-period measured LAI and the vegetation index was analyzed. Then
all the in situ measured corn LAI and corresponding eight vegetation indices were randomly divided into a training dataset and an independent model validation dataset (65% and 35% of the data
respectively). These datasets were randomly divided into three groups repeated three times. The training dataset was used to establish models to predict corn LAI
and the validation dataset was employed to test the quality of each prediction model. Finally
utilizing random forest
backpropagation (BP) neural network algorithm
and the traditional empirical model
the LAI inverting model was established based on previous work. This study compared the estimation accuracy of the three models for each sample group on the basis of the coefficient of determination (
$$ R^2$$
) and root mean square error (RMSE) to evaluate the estimation accuracy of each model and to compare the performances of the three models further.
Result
2
Results showed that the LAI values were significantly correlated with the vegetation index at the
$$ P$$
<
0.01 level in all the sample data and that the correlation coefficients were higher than 0.5. Three groups of different sample data were trained in random forest and BP neural network for many times
and the accuracy of estimation was checked based on the validation dataset. The empirical model was established by training dataset and verified by validation dataset. The results show that the RF model outperformed BP and the traditional empirical model in each group of sample data. For the RF models
$$ R^2$$
of the estimated and measured LAI values were 0.681
0.757
and 0.701 in contrast to the RMSE of 0.264
0.292
and 0.259
respectively. For the BP model
$$ R^2$$
for the three groups was 0.504
0.589
and 0.605
and the corresponding RMSE was 0.284
0.410
and 0.283
respectively. However
for the traditional empirical model
$$ R^2$$
for the three groups was 0.492
0.557
and 0.531
and the corresponding RMSE was 0.541
0.398
and 0.306
respectively.
Conclusion
2
The RF algorithm provides an effective approach to improve the prediction accuracy of corn LAI and provides a technical reference for the rapid and accurate monitoring of crop LAI remote sensing.
Chen J M, Black T A. Defining leaf area index for non-flat leaves[J]. Plant, Cell&Environment, 1992, 15(4):421-429.[DOI:10.1111/j.1365-3040.1992.tb00992.x]
Liu Y, Liu R G, Chen J M, et al. Current status and perspectives of leaf area index retrieval from optical remote sensing data[J]. Journal of Geo-information Science, 2013, 15(5):734-743.
刘洋, 刘荣高, 陈镜明, 等.叶面积指数遥感反演研究进展与展望[J].地球信息科学学报, 2013, 15(5):734-743. [DOI:10.3724/SP.J.1047.2013.00734]
Neinavaz E, Skidmore A K, Darvishzadeh R, et al. Retrieval of leaf area index in different plant species using thermal hyperspectral data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 119:390-401.[DOI:10.1016/j.isprsjprs.2016.07.001]
Haboudane D, Miller J R, Pattey E, et al. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies:modeling and validation in the context of precision agriculture[J]. Remote Sensing of Environment, 2004, 90(3):337-352.[DOI:10.1016/j.rse.2003.12.013]
Pinty B, Lavergne T, Widlowski J L, et al. On the need to observe vegetation canopies in the near-infrared to estimate visible light absorption[J]. Remote Sensing of Environment, 2009, 113(1):10-23.[DOI:10.1016/j.rse.2008.08.017]
Chen Y H, Zhang W C, Yong B, et al. Retrieving leaf area index using a neural network based on classification knowledge[J].Acta Ecologica Sinica, 2007, 27(7):2785-2793.
陈艳华, 张万昌, 雍斌, 等.基于分类知识利用神经网络反演叶面积指数[J].生态学报, 2007, 27(7):2785-2793. [DOI:10.3321/j.issn:1000-0933.2007.07.015]
Zhao J, Huang W J, Zhang Y H, et al. Inversion of leaf area Index during different growth stages in winter wheat[J]. Spectroscopy and Spectral Analysis, 2013, 33(9):2546-2552.
赵娟, 黄文江, 张耀鸿, 等.冬小麦不同生育时期叶面积指数反演方法[J].光谱学与光谱分析, 2013, 33(9):2546-2552. [DOI:10.3964/j.issn.1000-0593(2013)09-2546-07]
Li F X, Zhang B, Song K S, et al. Research and analysis of the correlation between hyperspectral vegetation index and leaf area index[J]. Remote Sensing Technology and Application, 2007, 22(5):586-592.
李凤秀, 张柏, 宋开山, 等.玉米叶面积指数与高光谱植被指数关系研究[J].遥感技术与应用, 2007, 22(5):586-592. [DOI:10.3969/j.issn.1004-0323.2007.05.002]
Yang F, Sun J L, Fang H L, et al. Comparison of different methods for corn LAI estimation over northeastern China[J]. International Journal of Applied Earth Observation and Geoinformation, 2012, 18:462-471.[DOI:10.1016/j.jag.2011.09.004]
Liu J, Pang X, Li Y R, et al. Inversion study on leaf area index of summer maize using remote sensing[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(9):309-317.
刘珺, 庞鑫, 李彦荣, 等.夏玉米叶面积指数遥感反演研究[J].农业机械学报, 2016, 47(9):309-317. [DOI:10.6041/j.issn.1000-1298.2016.09.042]
Wang L H, Du J, Huang J L, et al. Retrieving leaf area index of maize based on GF-1 multispectral remote sensing data[J]. Journal of Central China Normal University:Natural Sciences, 2016, 50(1):120-127.
王立辉, 杜军, 黄进良, 等.基于GF-1号卫星WFV数据反演玉米叶面积指数[J].华中师范大学学报:自然科学版, 2016, 50(1):120-127. [DOI:10.3969/j.issn.1000-1190.2016.01.023]
Meng Q Y, Wang C M, Gu X F, et al. Hot dark spot index method based on multi-angular remote sensing for leaf area index retrieval[J]. Environmental Earth Sciences, 2016, 75(9):#732.[DOI:10.1007/s12665-016-5549-x]
Qiao H L, Li W, Niu Z. Estimating leaf area index of maize based on multi-angular CHRIS/PROBA data[J]. Journal of Geo-information Science, 2015, 17(10):1243-1248.
乔海浪, 李旺, 牛铮.玉米叶面积指数的CHRIS/PROBA数据反演分析[J].地球信息科学学报, 2015, 17(10):1243-1248. [DOI:10.3724/SP.J.1047.2015.01243]
Li X C, Xu X G, Bao Y S, et al. Retrieving LAI of winter wheat based on sensitive vegetation index by the segmentation method[J]. Scientia Agricultura Sinica, 2012, 45(17):3486-3496.
李鑫川, 徐新刚, 鲍艳松, 等.基于分段方式选择敏感植被指数的冬小麦叶面积指数遥感反演[J].中国农业科学, 2012, 45(17):3486-3496. [DOI:10.3864/j.issn.0578-1752.2012.17.004]
Han Z Y, Zhu X C, Fang X Y, et al. Hyperspectral estimation of apple tree canopy LAI based on SVM and RF regression[J]. Spectroscopy and Spectral Analysis, 2016, 36(3):800-805.
韩兆迎, 朱西存, 房贤一, 等.基于SVM与RF的苹果树冠LAI高光谱估测[J].光谱学与光谱分析, 2016, 36(3):800-805. [DOI:10.3964/j.issn.1000-0593(2016)03-0800-06]
Verrelst J, Mu?oz J, Alonso L, et al. Machine learning regression algorithms for biophysical parameter retrieval:opportunities for Sentinel-2 and -3[J]. Remote Sensing of Environment, 2012, 118:127-139.[DOI:10.1016/j.rse.2011.11.002]
Xia T, Wu W B, Zhou Q B, et al. Comparison of two inversion methods for winter wheat leaf area index based on hyperspectral remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(3):139-147.
夏天, 吴文斌, 周清波, 等.冬小麦叶面积指数高光谱遥感反演方法对比[J].农业工程学报, 2013, 29(3):139-147. [DOI:10.3969/j.issn.1002-6819.2013.03.019]
Liang D, Guan Q S, Huang W J, et al. Remote sensing inversion of leaf area index based on support vector machine regression in winter wheat[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(7):117-123.
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, 29(7):117-123. [DOI:10.3969/j.issn.1002-6819.2013.07.015]
Wang L A, Zhou X D, Zhu X K, et al. Inverting wheat leaf area index based on HJ-CCD remote sensing data and random forest algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(3):149-154.
王丽爱, 周旭东, 朱新开, 等.基于HJ-CCD数据和随机森林算法的小麦叶面积指数反演[J].农业工程学报, 2016, 32(3):149-154. [DOI:10.11975/j.issn.1002-6819.2016.03.021]
Dahms T, Seissiger S, Conrad C, et al. Modelling biophysical parameters of maize using Landsat 8 Time Series[C]//Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLI-B2. Prague, Czech Republic: ISPRS, 2016: 171-175. [ DOI:10.5194/isprsarchives-XLI-B2-171-2016 http://dx.doi.org/10.5194/isprsarchives-XLI-B2-171-2016 ]
Zhao Y S. Principles and Methodsof Remote Sensing Application Analysis[M]. Beijing:Science Press, 2003
赵英时.遥感应用分析原理与方法[M].北京:科学出版社, 2003.
Yan S. Introduction to Remote Sensing Digital Image Processing[M]. Beijing:Machinery Industry Press, 2007.
延森.遥感数字影像处理导论[M].北京:机械工业出版社, 2007.
Broge N H, Leblanc E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density[J]. Remote Sensing of Environment, 2001, 76(2):156-172.[DOI:10.1016/S0034-4257(00)00197-8]
Rouse J W Jr, Haas R H, Schell J A, et al. Monitoring vegetation systems in the great plains with ERTS[C]//The 3rd ERTS Symposium. Washington, DC: NASA, 1973, 351: 309-317.
Rondeaux G, Steven M, Baret F. Optimization of soil-adjusted vegetation indices[J]. Remote Sensing of Environment, 1996, 55(2):95-107.[DOI:10.1016/0034-4257(95)00186-7]
Huete A R. A soil-adjusted vegetation index (SAVI)[J]. Remote Sensing of Environment, 1988, 25(3):295-309.[DOI:10.1016/0034-4257(88)90106-X]
Kaufman Y J, Tanre D. Atmospherically resistant vegetation index (ARVI) for EOS-MODIS[J]. IEEE Transactionson Geoscience and Remote Sensing, 1992, 30(2):261-270.[DOI:10.1109/36.134076]
Liu H Q, Huete A R. A feedback based modification of the NDVI to minimize canopy background and atmospheric noise[J]. IEEE Transactions on Geoscience and Remote Sensing, 1995, 33(2):457-465.[DOI:10.1109/36.377946]
Huete A R, Liu H Q, Batchily K, et al. A comparison of vegetation indices over a global set of TM images for EOS-MODIS[J]. Remote Sensing of Environment, 1997, 59(3):440-451.[DOI:10.1016/S0034-4257(96)00112-5]
Chen J M. Evaluation of vegetation indices and a modified simple ratio for boreal applications[J]. Canadian Journal of Remote Sensing, 1996, 22(3):229-242.[DOI:10.1080/07038992.1996.10855178]
Tang S H, Zhu Q J, Wang J D, et al. Principle and application of three-band gradient difference vegetation index[J]. Science in China Series D:Earth Sciences, 2003, 33(11):1094-1102.
唐世浩, 朱启疆, 王锦地, 等.三波段梯度差植被指数的理论基础及其应用[J].中国科学(D辑), 2003, 33(11):1094-1102. [DOI:10.3321/j.issn:1006-9267.2003.11.008]
Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.[DOI:10.1023/A:1010933404324]
Archer K J, Kimes R V. Empirical characterization of random forest variable importance measures[J]. Computational Statistics&Data Analysis, 2008, 52(4):2249-2260.[DOI:10.1016/j.csda.2007.08.015]
Zhu Y F, Zhu L, Li J G, et al. The study of inversion of chlorophyll a in Taihu based on GF-1 WFV image and BP neural network[J]. Acta Scientiae Circumstantiae, 2017, 37(1):130-137.
朱云芳, 朱利, 李家国, 等.基于GF-1 WFV影像和BP神经网络的太湖叶绿素a反演[J].环境科学学报, 2017, 37(1):130-137. [DOI:10.13671/j.hjkxxb.2016.0275]
Gao S, Niu Z, Wu M Q. The neural network algorithm for estimating plantation forest leaf area index based on ENVISAT/ASAR[J]. Remote Sensing Technology and Application, 2013, 28(2):205-211.
高帅, 牛铮, 邬明权.基于ENVISAT/ASAR的神经网络反演人工林叶面积指数研究[sJ].遥感技术与应用, 2013, 28(2):205-211. [DOI:10.11873/j.issn.1004-0323.2013.2.205]
Yang Y J, Huang D. Research and applications of artificial neural networks[J]. Journal of East China University of Science and Technology, 2002, 28(5):551-554.
杨源杰, 黄道.人工神经网络算法研究及应用[J].华东理工大学学报, 2002, 28(5):551-554. [DOI:10.3969/j.issn.1006-3080.2002.05.022]
Yao X, Yu K Y, Yang Y J, et al. Estimation of forest leaf area index based on random forest model and remote sensing data[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(5):159-166.
姚雄, 余坤勇, 杨玉洁, 等.基于随机森林模型的林地叶面积指数遥感估算[J].农业机械学报, 2017, 48(5):159-166. [DOI:10.6041/j.issn.1000-1298.2017.05.019]
Ma Y C, Yan G J, Ding W, et al. Leaf area index retrieval of winter wheat using artificial neural network[J]. Transactions of the CSAE, 2009, 25(12):187-192.
马茵驰, 阎广建, 丁文, 等.基于人工神经网络方法的冬小麦叶面积指数反演[J].农业工程学报, 2009, 25(12):187-192. [DOI:10.3969/j.issn.1002-6819.2009.12.033]
Song K S, Zhang B, Wang Z M, et al. Soybean LAI estimation with $$ in-situ$$ collected hyperspectral data based on BP-Neural networks[J]. Scientia Agricultura Sinica, 2006, 39(6):1138-1145.
宋开山, 张柏, 王宗明, 等.基于人工神经网络的大豆叶面积高光谱反演研究[J].中国农业科学, 2006, 39(6):1138-1145. [DOI:10.3321/j.issn:0578-1752.2006.06.007]
Liang S L, Cheng J, Jia K, et al. Recent progress in land surface quantitative remote sensing[J]. Journal of Remote Sensing, 2016, 20(5):875-898.
梁顺林, 程洁, 贾坤, 等.陆表定量遥感反演方法的发展新动态[J].遥感学报, 2016, 20(5):875-898. [DOI:10.11834/jrs.20166258]
相关文章
相关作者
相关机构
京公网安备11010802024621
