可见光光谱的冬小麦苗期地上生物量估算
|
摘要
地上生物量是表征冬小麦苗期长势的重要参数之一,对于监测冬小麦苗期长势,预测产量具有重要的实际意义。目前,通过计算光谱指数进行生物量估算是冬小麦苗期地上生物量无损测量的主要方法,但该方法需要一定的平台支撑,在便捷性方面存在一定的不足。为此,利用可见光图像数据获取方便、准确率高的特点,基于冬小麦苗期冠层可见光图像数据开展冬小麦苗期地上生物量估算研究。采用数码相机,采集冬小麦苗期冠层可见光图像并利用Canopeo进行冬小麦冠层与背景的分割。在获取冠层分割图像后,提取了CC(canopy cover)、 ExG(excessg reen)、 ExR(excess red)、 ExGR(ExG-ExR)、 NGRDI(normalized green-red difference index)、 GLI(green leaf index)、 RGRI(red-green ratio index)和RGBVI(RGB vegetation index)共8个可见光图像特征。利用相关性分析进行特征优选,选择与冬小麦苗期地上生物量实测数据相关性较高的图像特征构建估算模型。利用优选的图像特征,分别构建偏最小二乘回归(PLSR)、 BP神经网络(BPNN)、支持向量机回归(SVR)和随机森林(RF)模型,开展冬小麦苗期地上生物量估算研究,并定量分析特征数量和播种密度对估算模型准确率的影响。结果表明, ExR, GLI和RGBVI与生物量实测数据相关性较低,因此,将这3个特征剔除。CC, ExG, ExGR, NGRDI和RGRI与生物量实测数据的相关性较高,其中CC, ExG和ExGR与生物量实测数据呈正相关,而NGRDI和RGRI与生物量实测数据呈负相关。利用优选的图像特征构建估算模型,研究结果表明,基于优选的5个图像特征, PLSR的估算准确率最高,模型R~2为0.801 5, RMSE为0.0788 kg·m~(-2),表明PLSR能够实现冬小麦苗期地上生物量的准确估算。特征数量是影响估算模型准确率的因素之一,随着特征数量的减少,模型估算的准确率逐步下降。利用不同播种密度数据集对估算模型进行测试,结果表明, PLSR在不同的播种密度数据集上均取得了最高的估算准确率,模型R~2分别为0.897, 0.827 9和0.788 6, RMSE分别为0.062, 0.072和0.079 1 kg·m~(-2),表明PLSR估算的冬小麦苗期地上生物量数据与实测生物量数据之间具有良好的相关关系。随着播种密度的增加,所有估算模型的准确率均出现下降,而PLSR的准确率下降程度最小。由此可见,基于可见光图像数据,能够实现冬小麦苗期地上生物量的准确估算,为冬小麦苗期田间管理提供参考。
Above ground biomass(AGB) is one of the most commonly used traits indicating the growth of winter wheat at early growth stages. It is of great practical significance to monitor the growth and to estimate the yield. The conventional methods involving destructive sampling and manual calculating of the dry weight to measure AGB are prohibitively time consuming and laborious. The non-destructive approach to estimate AGB of winter wheat is through the estimation of vegetation indices(VIs) and regression analysis, which heavily depends on tools such as Remote Sensing and LiDAR. Therefore, the method is subject to specialized knowledge and high-cost. An estimating method for above ground biomass of wheat winter at early growth stages was proposed by using the digital images of winter wheat canopy. The canopy images were captured by a digital camera. The image segmentation of vegetation was achieved by using Canopeo. Based on the segmented images, eight images features, i. e., CC(Canopy Cover), ExG(Excessgreen), ExR(Excess red), ExGR(ExG-ExR), NGRDI(Normalized Green-Red Difference Index), GLI(Green Leaf Index), RGRI(Red-Green Ratio Index) and RGBVI(RGB Vegetation Index), were extracted. Correlation analysis was conducted between pairs of the images features and the biomass measurements. The feature that were highly correlated to the biomass measurements were used to build the estimation model. Results showed that ExR, GLIand RGBVI were not correlated to biomass, resulting in the elimination in the following experiments. The left five features were highly correlated to the biomass measurements. Among the five selected features, CC, ExG and ExGR were positively correlated to biomass measurements while NGRDI and RGRI were negatively correlated to biomass measurements. Based on the selected features, four model, i. e., Partial least squares regression(PLSR), BP neural network(BPNN), Support vector machine regression(SVR) and Random forest(RF), were built to estimate the above ground biomass. The influences of the number of features and the sowing density on the estimating accuracy were analyzed quantitatively. Results showed PLSR achieved the best accuracy based on the selected five features, the R~2 value was 0.801 5, and the RMSE was 0.078 8 kg·m~(-2), indicating that the PLSE was able to accurately estimate the above ground biomass of winter wheat at early growth stages. Thenumber of feature was proved to be an influence of factor. The accuracy of the model decreased with the reduction of the number of features. Experiments on the models by using different sowing density datasets were conducted as well. The results showed that PLSR outperformed the other three models over all the density datasets, the R~2 values were 0.897, 0.827 9 and 0.788 6, and the RMSE values were 0.062, 0.072 and 0.079 1 kg·m~(-2), indicating that the PLSR the estimated above ground biomass had a goof agreement with the ground truth. With the increase of the sowing density, the accuracy of all the models decreased while the PLSR achieved the minimum reduction. In Summary, the above ground biomass can be estimated by using the digital images, which can provide support to the field management of winter wheat at early growth stages.
Above ground biomass(AGB) is one of the most commonly used traits indicating the growth of winter wheat at early growth stages. It is of great practical significance to monitor the growth and to estimate the yield. The conventional methods involving destructive sampling and manual calculating of the dry weight to measure AGB are prohibitively time consuming and laborious. The non-destructive approach to estimate AGB of winter wheat is through the estimation of vegetation indices(VIs) and regression analysis, which heavily depends on tools such as Remote Sensing and LiDAR. Therefore, the method is subject to specialized knowledge and high-cost. An estimating method for above ground biomass of wheat winter at early growth stages was proposed by using the digital images of winter wheat canopy. The canopy images were captured by a digital camera. The image segmentation of vegetation was achieved by using Canopeo. Based on the segmented images, eight images features, i. e., CC(Canopy Cover), ExG(Excessgreen), ExR(Excess red), ExGR(ExG-ExR), NGRDI(Normalized Green-Red Difference Index), GLI(Green Leaf Index), RGRI(Red-Green Ratio Index) and RGBVI(RGB Vegetation Index), were extracted. Correlation analysis was conducted between pairs of the images features and the biomass measurements. The feature that were highly correlated to the biomass measurements were used to build the estimation model. Results showed that ExR, GLIand RGBVI were not correlated to biomass, resulting in the elimination in the following experiments. The left five features were highly correlated to the biomass measurements. Among the five selected features, CC, ExG and ExGR were positively correlated to biomass measurements while NGRDI and RGRI were negatively correlated to biomass measurements. Based on the selected features, four model, i. e., Partial least squares regression(PLSR), BP neural network(BPNN), Support vector machine regression(SVR) and Random forest(RF), were built to estimate the above ground biomass. The influences of the number of features and the sowing density on the estimating accuracy were analyzed quantitatively. Results showed PLSR achieved the best accuracy based on the selected five features, the R~2 value was 0.801 5, and the RMSE was 0.078 8 kg·m~(-2), indicating that the PLSE was able to accurately estimate the above ground biomass of winter wheat at early growth stages. Thenumber of feature was proved to be an influence of factor. The accuracy of the model decreased with the reduction of the number of features. Experiments on the models by using different sowing density datasets were conducted as well. The results showed that PLSR outperformed the other three models over all the density datasets, the R~2 values were 0.897, 0.827 9 and 0.788 6, and the RMSE values were 0.062, 0.072 and 0.079 1 kg·m~(-2), indicating that the PLSR the estimated above ground biomass had a goof agreement with the ground truth. With the increase of the sowing density, the accuracy of all the models decreased while the PLSR achieved the minimum reduction. In Summary, the above ground biomass can be estimated by using the digital images, which can provide support to the field management of winter wheat at early growth stages.
引文
[1] MAO Bo-hui,LI Min-zan,SUN Hong,et al(毛博慧,李民赞,孙红,等).Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2017,33(Supp.1):164.
[2] Eitel J U H,Magney T S,Vierling L A,et al.Field Crops Research,2014,159:21.
[3] Schirrmann M,Hamdorf A,Garz A,et al.Computers and Electronics in Agriculture,2016,121:374.
[4] Walter J,Edwards J,McDonald G,et al.Field Crops Research,2018,216:165.
[5] Zhang L,Verma B,Stockwell D,et al.Expert Systems with Applications,2018,101:213.
[6] CUI Ri-xian,LIU Ya-dong,FU Jin-dong(崔日鲜,刘亚东,付金东).Spectroscopy and Spectral Analysis(光谱学与光谱分析),2015,35(9):2596.
[7] LIU Bing-feng,LI Jun,HE Jia,et al(刘冰峰,李军,贺佳,等).Transactions of the Chinese Society for Agricultural Machinery(农业机械学报),2016,47(3):254.
[8] XU Xu,CHEN Guo-qing,WANG Liang,et al(徐旭,陈国庆,王良,等).Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2015,31(22):169.
[9] Wang L,Zhou X,Zhu X,et al.Crop Journal,2016,4(3):212.
[10] Rasmussen J,Ntakos G,Nielsen J,et al.European Journal of Agronomy,2016,74:75.
[11] Gnyp M L,Bareth G,Li F,et al.International Journal of Applied Earth Observation and Geoinformation,2014,33(1):232.
[12] Casadesús J,Villegas D.Journal of Integrative Plant Biology,2014,56(1):7.
[13] González-Esquiva J M,Oates M J,García-Mateos G,et al.Computers and Electronics in Agriculture,2017,141:15.
[14] Neumann K,Klukas C,Friedel S,et al.Plant,Cell and Environment,2015,38(10):1980.
[15] Patrignani A,Ochsner T E.Agronomy Journal,2015,107(6):2312.
[16] Bai G,Ge Y,Hussain W,et al.Computers and Electronics in Agriculture,2016,128:181.
[17] Chung Y S,Choi S C,Silva R R,et al.Biomass and Bioenergy,2017,105:207.
[18] Baresel J P,Rischbeck P,Hu Y,et al.Computers and Electronics in Agriculture,2017,140:25.
[19] Woebbecke D M,Meyer G E,Von Bargen K,et al.Transactions of the American Society of Agricultural Engineers,1995,38(1):259.
[20] Meyer G E,Hindman T W,Lakshmi K.Precision Agriculture and Biological Quality.1998:327.
[21] Meyer G E,Neto J C.Computers and Electronics in Agriculture,2008,62(2):282.
[22] Gitelson A A,Kaufman Y J,Stark R,et al.Remote Sensing of Environment,2002,80(1):76.
[23] Louhaichi M,Borman M M,Johnson D E.Geocarto International,2001,16(1):65.
[24] WANG Xiao-qin,WANG Miao-miao,WANG Shao-qiang,et al(汪小钦,王苗苗,王绍强,等).Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2015,31(5):152.
[25] Bendig J,Yu K,Aasen H,et al.International Journal of Applied Earth Observation and Geoinformation,2015,39:79.
[26] Kusnierek K,Korsaeth A.Computers and Electronics in Agriculture,2015,117:200.
[27] Wang L,Zhou X,Zhu X,et al.Crop Journal,2016,4:212.
[28] Clevers J G P W,van der Heijden G W A M,Verzakov S,et al.Photogrammetric Engineering and Remote Sensing,2007,73(10):1141.
[29] Breiman L.Mach.Learn,2001,45(1):5.
[2] Eitel J U H,Magney T S,Vierling L A,et al.Field Crops Research,2014,159:21.
[3] Schirrmann M,Hamdorf A,Garz A,et al.Computers and Electronics in Agriculture,2016,121:374.
[4] Walter J,Edwards J,McDonald G,et al.Field Crops Research,2018,216:165.
[5] Zhang L,Verma B,Stockwell D,et al.Expert Systems with Applications,2018,101:213.
[6] CUI Ri-xian,LIU Ya-dong,FU Jin-dong(崔日鲜,刘亚东,付金东).Spectroscopy and Spectral Analysis(光谱学与光谱分析),2015,35(9):2596.
[7] LIU Bing-feng,LI Jun,HE Jia,et al(刘冰峰,李军,贺佳,等).Transactions of the Chinese Society for Agricultural Machinery(农业机械学报),2016,47(3):254.
[8] XU Xu,CHEN Guo-qing,WANG Liang,et al(徐旭,陈国庆,王良,等).Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2015,31(22):169.
[9] Wang L,Zhou X,Zhu X,et al.Crop Journal,2016,4(3):212.
[10] Rasmussen J,Ntakos G,Nielsen J,et al.European Journal of Agronomy,2016,74:75.
[11] Gnyp M L,Bareth G,Li F,et al.International Journal of Applied Earth Observation and Geoinformation,2014,33(1):232.
[12] Casadesús J,Villegas D.Journal of Integrative Plant Biology,2014,56(1):7.
[13] González-Esquiva J M,Oates M J,García-Mateos G,et al.Computers and Electronics in Agriculture,2017,141:15.
[14] Neumann K,Klukas C,Friedel S,et al.Plant,Cell and Environment,2015,38(10):1980.
[15] Patrignani A,Ochsner T E.Agronomy Journal,2015,107(6):2312.
[16] Bai G,Ge Y,Hussain W,et al.Computers and Electronics in Agriculture,2016,128:181.
[17] Chung Y S,Choi S C,Silva R R,et al.Biomass and Bioenergy,2017,105:207.
[18] Baresel J P,Rischbeck P,Hu Y,et al.Computers and Electronics in Agriculture,2017,140:25.
[19] Woebbecke D M,Meyer G E,Von Bargen K,et al.Transactions of the American Society of Agricultural Engineers,1995,38(1):259.
[20] Meyer G E,Hindman T W,Lakshmi K.Precision Agriculture and Biological Quality.1998:327.
[21] Meyer G E,Neto J C.Computers and Electronics in Agriculture,2008,62(2):282.
[22] Gitelson A A,Kaufman Y J,Stark R,et al.Remote Sensing of Environment,2002,80(1):76.
[23] Louhaichi M,Borman M M,Johnson D E.Geocarto International,2001,16(1):65.
[24] WANG Xiao-qin,WANG Miao-miao,WANG Shao-qiang,et al(汪小钦,王苗苗,王绍强,等).Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2015,31(5):152.
[25] Bendig J,Yu K,Aasen H,et al.International Journal of Applied Earth Observation and Geoinformation,2015,39:79.
[26] Kusnierek K,Korsaeth A.Computers and Electronics in Agriculture,2015,117:200.
[27] Wang L,Zhou X,Zhu X,et al.Crop Journal,2016,4:212.
[28] Clevers J G P W,van der Heijden G W A M,Verzakov S,et al.Photogrammetric Engineering and Remote Sensing,2007,73(10):1141.
[29] Breiman L.Mach.Learn,2001,45(1):5.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |