浏览全部资源
扫码关注微信
Published： 07 April 2022 ，
扫 描 看 全 文
周晓雪，李楠，潘耀忠，孙莉昕.2022.人工蜂群算法优化SVR的叶面积指数反演.遥感学报，26（4）： 766-780
Zhou X X，Li N，Pan Y Z and Sun L X. 2022. Optimized SVR based on artificial bee colony algorithm for leaf area index inversion. National Remote Sensing Bulletin， 26（4）：766-780
支持向量机回归SVR（Support Vector Regression）方法作为叶面积指数反演的一种新思路，在LAI反演中具有一定的应用价值和前景，但SVR算法中惩罚系数
C
、核函数宽度参数
g
、不敏感损失函数参数
ε
的取值对回归精度有显著的影响。本文提出了一种基于人工蜂群算法ABC（Artificial Bee Colony）优化SVR参数的遥感影像叶面积指数反演方法。研究数据为美国土壤水分实验（SMEX02）2002年LAI实测数据和同期的Landsat 7 ETM+地表反射率数据，为了验证ABC算法优化SVR各个参数对反演精度的影响，建立了未优化参数（SVR）、优化单个参数（ABC-SVR-
C
，ABC-SVR-
g
，ABC-SVR-
ε
）、优化3个参数（ABC-SVR）的3类LAI反演模型，并比较了其回归拟合精度。在此基础上，分析了3个关键参数对LAI反演模型精度的敏感性，并对ABC算法优化SVR模型的精度进行显著性检验。研究表明：（1）相比未优化参数模型，ABC算法优化模型具有更高的反演精度，优化3个参数优于优化单个参数，回归直线斜率
k
达到0.797、决定系数
r
2
达到0.775。（2）SVR的3个关键参数对模型精度都有影响，相较参数
C
和
g
，参数
ε
引起模型精度的不确定性更高。（3）95%的置信区间下，ABC-SVR模型与SVR模型的回归直线斜率
k
、
r
2
、RMSE的差异显著性检验
P
值均小于0.005，ABC算法显著改善了SVR模型的精度。
Support Vector Regression (SVR) method as a new idea in LAI inversion has certain application value and prospect. However
the value of penalty coefficient
C
width parameter g of kernel function and insensitive loss function parameter
<math id="M1"><mi>ε</mi></math>
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=36316336&type=
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=36316333&type=
1.18533325
2.28600001
in the SVR algorithm have a significant impact on regression accuracy. This paper proposed a method for Leaf Area Index (LAI) inversion using remote sensing images based on ABC (Artificial Bee Colony) algorithm to optimize SVR parameters. In addition
the LAI measurement values were from the Soil Moisture Experiment 2002 in US (SMEX02) and Landsat 7 ETM + surface reflectance data at the same time. In order to verify the effect of SVR optimized by ABC
this paper established three types of LAI inversion models with non-optimized parameters(SVR)
optimized single parameter(ABC-SVR-
C
ABC-SVR-
g
ABC-SVR-
ε
)
and optimized three parameters (ABC-SVR)
and compared the accuracy of the three kinds of models. Based on this
we analyzed the sensitivity of LAI inversion model of three key parameters of SVR
and did a significant test on the accuracy of the ABC algorithm optimized SVR model. The study showed: (1) Compared with the model without optimizing parameters
the four models with the SVR parameters optimized by ABC algorithm had higher accuracy
and the optimized three parameters model had better accuracy than the model with optimizing single parameter
the slope of regression straight line reaching 0.797 and decision coefficient reaching 0.775. (2) The three key parameters of SVR have an influence on the accuracy of the LAI model
and compared with the parameters
C
and
g
the parameter
ε
is more uncertain to the accuracy of the model. (3) At the confidence interval of 95%
the
P
value of difference significance test on the slope
k
r
2
and RMSE between ABC-SVR model and SVR model all less than 0.005
indicated that the ABC algorithm significantly improved the accuracy of the SVR model.
支持向量机回归SVR人工蜂群算法ABC参数优化Landsat 7叶面积指数LAI
Support Vector Regression (SVR)Artificial Bee Colony (ABC) algorithmparameter optimizationLandsat 7Leaf Area Index (LAI)
Chang C C and Lin C J. 2011. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3): 1-27 [DOI: 10.1145/1961189.1961199http://dx.doi.org/10.1145/1961189.1961199]
Chen J M and Black T A. 1992. Defining leaf area index for non-flat leaves. Plant, Cell and Environment, 15(4): 421-429 [DOI: 10.1111/j.1365-3040.1992.tb00992.xhttp://dx.doi.org/10.1111/j.1365-3040.1992.tb00992.x]
Cheng P and Wang X L. 2011. Influence of SVR parameter on non-linear function approximation. Computer Engineering, 37(3): 189-191, 194
成鹏, 汪西莉. 2011. SVR参数对非线性函数拟合的影响. 计算机工程, 37(3): 189-191, 194 [DOI: 10.3969/j.issn.1000-3428.2011.03.067http://dx.doi.org/10.3969/j.issn.1000-3428.2011.03.067]
Cherkassky V. 1997. The nature of statistical learning theory. IEEE Transactions on Neural Networks, 8(6): 1564 [DOI: 10.1109/TNN.1997.641482http://dx.doi.org/10.1109/TNN.1997.641482]
Dorigo M and Gambardella L M. 1997. Ant colony system: a cooperative learning approach to the traveling salesman problem. IEEE Transactions on Evolutionary Computation, 1(1): 53-66 [DOI: 10.1109/4235.585892http://dx.doi.org/10.1109/4235.585892]
Durbha S S, King R L and Younan N H. 2007. Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer. Remote Sensing of Environment, 107(1/2): 348-361 [DOI: 10.1016/j.rse.2006.09.031http://dx.doi.org/10.1016/j.rse.2006.09.031]
Fang X Q and Zhang W C. 2003. The application of remotely sensed data to the estimation of the leaf area index. Remote Sensing for Land and Resources, 15(3): 58-62
方秀琴, 张万昌. 2003. 叶面积指数(LAI)的遥感定量方法综述. 国土资源感, 15(3): 58-62 [DOI: 10.3969/j.issn.1001-070X.2003.03.014http://dx.doi.org/10.3969/j.issn.1001-070X.2003.03.014]
Forsati R, Moayedikia A, Keikha A and Shamsfard M. 2012. A novel approach for feature selection based on the bee colony optimization. International Journal of Computer Applications, 43(8): 13-16 [DOI: 10.5120/6122-8329http://dx.doi.org/10.5120/6122-8329]
Ghamisi P, Couceiro M S and Benediktsson J A. 2015. A novel feature selection approach based on FODPSO and SVM. IEEE Transactions on Geoscience and Remote Sensing, 53(5): 2935-2947 [DOI: 10.1109/TGRS.2014.2367010http://dx.doi.org/10.1109/TGRS.2014.2367010]
Guo L, Pei Z Y, Zhang S L, Sun J Y, Liang Z L and Teng D J. 2010. Estimation method of sugarcane leaf area index using HJ CCD images. Transactions of the CSAE, 26(10): 201-205
郭琳, 裴志远, 张松龄, 孙娟英, 梁自力, 滕冬建. 2010. 基于环境星CCD图像的甘蔗叶面积指数反演方法. 农业工程学报, 26(10): 201-205 [DOI: 10.3969/j.issn.1002-6819.2010.10.034http://dx.doi.org/10.3969/j.issn.1002-6819.2010.10.034]
He Y Z, Zhang Z Q and Guan C Y. 2015. Application and prospect of hyperspectral remote sensing technology in precision agriculture monitoring. Crop Research, 29(1): 96-100
何友铸, 张振乾, 官春云. 2015. 高光谱遥感技术在精细农业监测上的应用及展望. 作物研究, 29(1): 96-100 [DOI: 10.3969/j.issn.1001-5280.2015.01.23http://dx.doi.org/10.3969/j.issn.1001-5280.2015.01.23]
Holland J H. 1975. Adaption in Natural and Artificial Systems. Ann Arbor: University of Michigan Press
Karaboga D. 2005. An Idea Based on Honey Bee Swarm for Numerical Optimization. Erciyes University
Karaboga D and Akay B. 2009. A comparative study of artificial bee colony algorithm. Applied Mathematics and Computation, 214(1): 108-132 [DOI: 10.1016/j.amc.2009.03.090http://dx.doi.org/10.1016/j.amc.2009.03.090]
Karaboga D and Basturk B. 2007. A powerful and efficient algorithm for numerical function optimization: Artificial Bee Colony (ABC) algorithm. Journal of Global Optimization, 39(3): 459-471 [DOI: 10.1007/s10898-007-9149-xhttp://dx.doi.org/10.1007/s10898-007-9149-x]
Karaboga D, Gorkemli B, Ozturk C and Karaboga N. 2014. A comprehensive survey: Artificial Bee Colony (ABC) algorithm and applications. Artificial Intelligence Review, 42(1): 21-57 [DOI: 10.1007/s10462-012-9328-0http://dx.doi.org/10.1007/s10462-012-9328-0]
Kennedy J and Eberhart R. 1995. Particle swarm optimization//Proceedings of 1995 IEEE International Conference on Neural Networks. Perth, WA, Australia: IEEE: 1942-1948 [DOI: 10.1109/ICNN.1995.488968http://dx.doi.org/10.1109/ICNN.1995.488968]
Kwok J T Y. 1998. Support vector mixture for classification and regression problems//Proceedings of the 14th International Conference on Pattern Recognition. Brisbane, Queensland: IEEE [DOI: 10.1109/ICPR.1998.711129http://dx.doi.org/10.1109/ICPR.1998.711129]
Latifi H and Galos B. 2010. Remote sensing-supported vegetation parameters for regional climate models: a brief review. iForest-Biogeosciences and Forestry, 3(4): 98-101 [DOI: 10.3832/ifor0543-003http://dx.doi.org/10.3832/ifor0543-003]
Li N, Zhu X F, Pan Y Z and Zhan P. 2018. Optimized SVM based on artificial bee colony algorithm for remote sensing image classification. Journal of Remote Sensing, 22(4): 559-569
李楠, 朱秀芳, 潘耀忠, 詹培. 2018. 人工蜂群算法优化的SVM遥感影像分类. 遥感学报, 22(4): 559-569 [DOI: 10.11834/jrs.20187176http://dx.doi.org/10.11834/jrs.20187176]
Liang D, Guan Q S, Huang W J, Huang L S and Yang G J. 2013. Remote sensing inversion of leaf area index based on support vector machine regression in winter wheat. Transactions of the Chinese Society of Agricultural Engineering, 29(7): 117-123
梁栋, 管青松, 黄文江, 黄林生, 杨贵军. 2013. 基于支持向量机回归的冬小麦叶面积指数遥感反演. 农业工程学报, 29(7): 117-123 [DOI: 10.3969/j.issn.1002-6819.2013.07.015http://dx.doi.org/10.3969/j.issn.1002-6819.2013.07.015]
Liang S L, Cheng J, Jia K, Jiang B, Liu Q, Liu S H, Xiao Z Q, Xie X H, Yao Y J, Yuan W P, Zhang X T and Zhao X. 2016. Recent progress in land surface quantitative remote sensing. Journal of Remote Sensing, 20(5): 875-898
梁顺林, 程洁, 贾坤, 江波, 刘强, 刘素红, 肖志强, 谢先红, 姚云军, 袁文平, 张晓通, 赵祥. 2016. 陆表定量遥感反演方法的发展新动态. 遥感学报, 20(5): 875-898 [DOI: 10.11834/jrs.20166258http://dx.doi.org/10.11834/jrs.20166258]
Liu X C, Fan W J, Tian Q J and Xu X R. 2008. Comparative analysis among different methods of leaf area index inversion. Acta Scientiarum Naturalium Universitatis Pekinensis, 44(2): 827-834
刘晓臣, 范闻捷, 田庆久, 徐希孺. 2008. 不同叶面积指数反演方法比较研究. 北京大学学报(自然科学版), 44(2): 827-834 [DOI: 10.3321/j.issn:0479-8023.2008.05.025http://dx.doi.org/10.3321/j.issn:0479-8023.2008.05.025]
Liu Y, Liu R G, Chen J M, Cheng X and Zheng G. 2013. Current Status and Perspectives of Leaf Area Index Retrieval from Optical Remote Sensing. Journal of Geo-information Science. 15(05): 734-743
刘洋,刘荣高,陈镜明,程晓,郑光. 2013. 叶面积指数遥感反演研究进展与展望.地球信息科学学报, 15(05): 734-743 [DOI:10.3724/SP.J.1047.2013.00734http://dx.doi.org/10.3724/SP.J.1047.2013.00734]
Steinbrunn M, Moerkotte G and Kemper A. 1997. Heuristic and randomized optimization for the join ordering problem. The VLDB Journal, 6(3): 191-208 [DOI: 10.1007/s007780050040http://dx.doi.org/10.1007/s007780050040]
Tuia D, Verrelst J, Alonso L, Perez-Cruz F and Camps-Valls G. 2011. Multioutput support vector regression for remote sensing biophysical parameter estimation. IEEE Geoscience and Remote Sensing Letters, 8(4): 804-808 [DOI: 10.1109/LGRS.2011.2109934http://dx.doi.org/10.1109/LGRS.2011.2109934]
Wang D C, Fang T J, Tang Y and Ma Y J. 2003. Review of support vector machines regression theory and control. Pattern Recognition and Artificial Intelligence, 16(2): 192-197
王定成, 方廷健, 唐毅, 马永军. 2003. 支持向量机回归理论与控制的综述. 模式识别与人工智能, 16(2): 192-197 [DOI: 10.3969/j.issn.1003-6059.2003.02.012http://dx.doi.org/10.3969/j.issn.1003-6059.2003.02.012]
Wang L, Zhang Y, Peng W H, Xu B and Wang Q C. 2014. SVR approach based on artificial bee colony optimization. Systems Engineering and Electronics, 36(2): 326-330
王琳, 张赟, 彭文辉, 徐波, 王前程. 2014. 基于人工蜂群优化的支持向量回归预测方法. 系统工程与电子技术, 36(2): 326-330 [DOI: 10.3969/j.issn.1001-506X.2014.02.20http://dx.doi.org/10.3969/j.issn.1001-506X.2014.02.20]
Wu X X, Xie Q Y. 2014. Research progress on inversion methods of leaf area index use remote sensing.China Agriculture Information. (07): 285-286
武旭霞, 谢巧云. 2014. 植被叶面积指数遥感反演方法研究进展. 中国农业信息, (07):285-286 [DOI:10.3969/j.issn.1672-0423.2014.04.230http://dx.doi.org/10.3969/j.issn.1672-0423.2014.04.230]
Wang Y F and Zheng X J. 2010. Sensitivity analysis of model parameters and υ-SVR model of slope deformation due to excavating from open-pit to underground mining. Chinese Journal of Rock Mechanics and Engineering, 29(S1): 2902-2907
王云飞, 郑晓娟. 2010. 露天转地下边坡变形υ-SVR模型及参数敏感性分析. 岩石力学与工程学报, 29(S1): 2902-2907
Xia T, Wu W B, Zhou Q B and Zhou Y. 2013. Comparison of two inversion methods for winter wheat leaf area index based on hyperspectral remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 29(3): 139-147
夏天, 吴文斌, 周清波, 周勇. 2013. 冬小麦叶面积指数高光谱遥感反演方法对比. 农业工程学报, 29(3): 139-147 [DOI: 10.3969/j.issn.1002-6819.2013.03.019http://dx.doi.org/10.3969/j.issn.1002-6819.2013.03.019]
Xing Z R, Feng Y G, Li W M, Wang P and Yang G J. 2010. The research status of inversion of leaf area index with hyperspectral remote sensing. Science of Surveying and Mapping, 35(S1): 162-164, 62
邢著荣, 冯幼贵, 李万明, 王萍, 杨贵军. 2010. 高光谱遥感叶面积指数(LAI)反演研究现状. 测绘科学, 35(S1): 162-164, 62
Yan G H and Zhu Y S. 2009. Parameters selection method for support vector machine regression. Computer Engineering, 35(14): 218-220
闫国华, 朱永生. 2009. 支持向量机回归的参数选择方法. 计算机工程, 35(14): 218-220 [DOI: 10.3969/j.issn.1000-3428.2009.14.076http://dx.doi.org/10.3969/j.issn.1000-3428.2009.14.076]
Yang M, Lin J, Gu Z Y, Tong G C, Wong Y B, Zhang J C and Lu X Z. 2015. Leaf area index retrieval based on Landsat 8 OLI multi-spectral image data and BP neural network. Science of Soil and Water Conservation, 13(4): 86-93
杨敏, 林杰, 顾哲衍, 佟光臣, 翁永兵, 张金池, 鲁小珍. 2015. 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. 中国水土保持科学, 13(4): 86-93 [DOI: 10.3969/j.issn.1672-3007.2015.04.013http://dx.doi.org/10.3969/j.issn.1672-3007.2015.04.013]
Yang M, Liu Y and Kong B. 2009. Research on parameters selection method of SVR model. Computer ERA, (11): 53-55
杨玫, 刘瑜, 孔波. 2009. SVR模型参数选择方法的研究. 计算机时代, (11): 53-55 [DOI: 10.3969/j.issn.1006-8228.2009.11.020http://dx.doi.org/10.3969/j.issn.1006-8228.2009.11.020]
Yu M and Ai Y Q. 2012. SVM parameter optimization and application based on artificial bee colony algorithm. Journal of Optoelectronics·Laser, 23(2): 374-378
于明, 艾月乔. 2012. 基于人工蜂群算法的支持向量机参数优化及应用. 光电子·激光, 23(2): 374-378
Zai S M, Wen J, Guo D D, Han Q B, Deng Z, Sun H and Zhao D B. 2011. Determination of leaf area of sweet pepper based on support vector machine model and image processing. Transactions of the Chinese Society of Agricultural Engineering, 27(3): 237-241
宰松梅, 温季, 郭冬冬, 韩启彪, 邓忠, 孙浩, 赵东彬. 2011. 基于支持向量机模型和图像处理技术的甜椒叶面积测定. 农业工程学报, 27(3): 237-241 [DOI: 10.3969/j.issn.1002-6819.2011.03.045http://dx.doi.org/10.3969/j.issn.1002-6819.2011.03.045]
Zang S Y, Zhang C, Zhang L J and Zhang Y H. 2012. Wetland remote sensing classification using support vector machine optimized with genetic algorithm: a case study in Honghe nature national reserve. Scientia Geographica Sinica, 32(4): 434-44
臧淑英, 张策, 张丽娟, 张玉红. 2012. 遗传算法优化的支持向量机湿地遥感分类——以洪河国家级自然保护区为例. 地理科学, 32(4): 434-441 [DOI: 10.13249/j.cnki.sgs.2012.04.434http://dx.doi.org/10.13249/j.cnki.sgs.2012.04.434]
相关作者
相关机构
京公网安备11010802024621