可见/近红外光谱技术识别树叶树种的研究
|
摘要
探索使用可见/近红外光谱技术识别树叶树种的可行性,为野外可见/近红外光谱技术用于树种识别提供方法。本试验识别了9个树种,测试了光谱预处理方法、识别方法对可见/近红外光谱识别的准确率的影响。对9种阔叶树种共46棵树,分别采用距离法和PLS-DA建立识别模型,比较不同波段和导数预处理方法对模型预测效果的影响。结果表明,使用距离法对原始光谱进行识别时,识别准确率<50%,不能够有效识别树叶树种。使用距离法对预处理后的光谱进行识别时,识别准确率为近红外350～2 500nm(99.16%)>350～1 000nm(88.05%)>1 000～2 500nm(81.24%),且任意单个树种的识别准确率都>98%,能够有效识别树叶树种。使用偏最小二乘法(PLS-DA)结合单列识别变量矩阵时,识别准确率高达100%,识别模型的相关系数为0.993 6,RMSEC为0.120,RMSEP为0.144,但只能成功识别4种树叶树种,当树叶种数>4时,预测模型的识别准确率陡降。使用偏最小二乘法(PLS-DA)结合多列识别变量矩阵对9种树叶的识别准确率高达99.58%,识别模型的相关系数为0.888 6～0.956 9,RMSEC为0.084 5～0.15,RMSEP为0.088 7～0.155。本试验为可见/近红外光谱技术快速识别树种提供了一种新的方法和思路。
A feasibility study was carried out to identify tree leaf and species by visible and near infrared spectroscopy(Vis/NIRS)technique to provide a practical method for the identification of tree species in the field.Forty-six broad-leaved trees of 9species were sampled to examine the influences of different spectral pretreatments and identification methods on the rate of identification accuracy were tested.Different wavelengths and identification methods(distance method and PLS-DA)were compared over the effect of model prediction.The results showed that by using distance method to identify the raw spectrum,the rates of identification accuracy of all species were under 50%,which could not effectively identify the tree species.However,when the distance method was used to identify the pretreated spectra,the rates of identification accuracy were 99.16%(350-2 500nm),88.05%(350-1 000nm)and 81.24%(1 000-2 500nm),respectively.With the wavelength of 350-2 500 nm,the accuracy rates for all the individual tree species achieved over 98%.When the PLS-DA method combined with single column identification variable matrix was used,the rates of identification accuracy were 100%,with the correlation coefficient of 0.993 6,RMSEC 0.120,and RMSEP 0.144.With this method,the maximum number of identifying tree species was 4,over 4,the rate of identification accuracy decreased significantly.When the PLS-DA method combined withmultiple column identification variable matrix was used to identify the 1st and smoothing spectrum of 9species,the rate of identification accuracy was 99.58%,with correlation coefficients of 0.888 6-0.956 9,RMSEC 0.084 5-0.15,and RMSEP 0.088 7-0.155.The results of this study would provide a new method and way in rapid identification of common tree species.
A feasibility study was carried out to identify tree leaf and species by visible and near infrared spectroscopy(Vis/NIRS)technique to provide a practical method for the identification of tree species in the field.Forty-six broad-leaved trees of 9species were sampled to examine the influences of different spectral pretreatments and identification methods on the rate of identification accuracy were tested.Different wavelengths and identification methods(distance method and PLS-DA)were compared over the effect of model prediction.The results showed that by using distance method to identify the raw spectrum,the rates of identification accuracy of all species were under 50%,which could not effectively identify the tree species.However,when the distance method was used to identify the pretreated spectra,the rates of identification accuracy were 99.16%(350-2 500nm),88.05%(350-1 000nm)and 81.24%(1 000-2 500nm),respectively.With the wavelength of 350-2 500 nm,the accuracy rates for all the individual tree species achieved over 98%.When the PLS-DA method combined with single column identification variable matrix was used,the rates of identification accuracy were 100%,with the correlation coefficient of 0.993 6,RMSEC 0.120,and RMSEP 0.144.With this method,the maximum number of identifying tree species was 4,over 4,the rate of identification accuracy decreased significantly.When the PLS-DA method combined withmultiple column identification variable matrix was used to identify the 1st and smoothing spectrum of 9species,the rate of identification accuracy was 99.58%,with correlation coefficients of 0.888 6-0.956 9,RMSEC 0.084 5-0.15,and RMSEP 0.088 7-0.155.The results of this study would provide a new method and way in rapid identification of common tree species.
引文
[1]多化豫,孙枭雄,袁云梅.基于图像处理提高木材识别准确性的新方法[J].西北林学院学报,2017,32(1):244-247.DUO H Y,SUN X X,YUAN Y M.Improvement of wood identification accuracy based on image processing[J].Journal of Northwest Forestry University,2017,32(1):244-247.(in Chinese)
[2]周熊,多化琼,王振柱,等.基于图像处理和SVM探索木材与树皮的新识别参数[J].西北林学院学报,2014,29(5):199-202.ZHOU X,DUO H Q,WANG Z Z,et al.New recognition parameters of wood nnd bark rate based on image processing and the SVM[J].Journal of Northwest Forestry University,2014,29(5):199-202.(in Chinese)
[3] DA E S,PEDRINI H.Inferring patterns in mitochondrial DNA sequences through hypercube independent spanning trees[J].Computers in Biology and Medicine,2016,70:51-57.
[4] AYED R A A,DEGNAN J H.Inferring rooted species trees from unrooted gene trees using approximate Bayesian computation[J].Molecular Phylogenetics and Evolution,2017,116:13-24.
[5] BARMPOUTIS P,DIMITROPOULOS K,BARBOUTIS I,et al.Wood species recognition through multidimensional texture analysis[J].Computers and Electronics in Agriculture,2018,144:241-248.
[6] ROJAS J A M,ALPUENTE J,POSTIGO D,et al.Wood species identification using stress-wave analysis in the audible range[J].Applied Acoustics,2011,72:934-942.
[7]严衍禄.近红外光谱分析基础与应用[M].北京:中国轻工业出版社,2005.
[8]窦刚,陈广胜,赵鹏.基于近红外光谱反射率特征的木材树种分类识别系统的研究与实现[J].光谱学与光谱分析,2016,36(8):2425-2429.DOU G,CHEN G S,ZHAO P.Research and implementation of wood species recowition system with wood near infrared spectral reflection features[J].Spectroscopy and Spectral Analysis,2016,36(8):2425-2429.(in Chinese)
[9]梁龙,房桂干,崔宏辉,等.近红外光谱结合支持向量机快速识别树种[J].林产化学与工业,2016,36(1):55-60.LIANG L,FANG G G,CUI H H,et al.Fast identification of wood species by near infrared spectroscopy coupling with support vector machine[J].Chemistry and Industry of Forest Products,2016,36(1):55-60.(in Chinese)
[10]张雯雅.近红外光谱技术在珍稀木材鉴别领域的研究与应用[D].杭州:浙江农林大学,2015.
[11]唐忠炳,张愈,易金,等.乌饭树叶保健饮料工艺技术及关键参数试验研究[J].江西科学,2018,36(1):54-59.
[12]陆志科,冯雁,苏泉,等.麻疯树叶提取物的抗菌作用研究[J].西北林学院学报,2012,27(4):181-185.LU Z K,FENG Y,SU Q,et al.Antimicrobial activity of the extracts fromJatropha curcas leaves[J].Journal of Northwest Forestry University,2012,27(4):181-185.(in Chinese)
[13]唐周怀,郭晓霞,张雅莉,等.国槐行道树叶螨种群消长与环境因子的分析[J].西北林学院学报,2000,15(3):76-79.TANG Z H,GUO X X,ZHANG Y L,et al.Studies on the relationship between spider-mate population dynamics and environmintal factors[J].Journal of Northwest Forestry University,2000,15(3):76-79.(in Chinese)
[14]吴朝学,严理,秦武明,等.木荷人工林营养元素分布格局[J].西北林学院学报,2017,32(1):54-61.WU C X,YAN L,QIN W M,et al.Distribution characteristics of nutrient elements in schima superba plantation[J].Journal of Northwest Forestry University,2017,32(1):54-61.(in Chinese)
[15]林恋竹,刘雪梅,赵谋明.神秘果树叶提取物降尿酸作用及其有效成分鉴定[J].中国食品学报,2018,18(1):270-277.LIN L Z,LIU X M,ZHAO M M.Decreasing uric acid effect of the extracts of miracle fruit(synepalum dulcificum)’leaf and identification of its active ingredient[J].Journal of Chinese Institute of Food Science and Technology,2018,18(1):270-277.(in Chinese)
[16]高玉萍.茶制品近红外快速测定方法的研究及指纹图谱的建立[D].杭州:浙江大学,2013.
[17] MEES C,SOUARD F,DELPORTE C,et al.Identification of coffee leaves using FT-NIR spectroscopy and SIMCA[J].Talanta,2018,177:4-11.
[18] LANG C,FLAVLA R C C,JOSE L C C.Near infrared spectroscopy facilitates rapid identification of both young and mature amazonian tree species[J].Plos One,2015,10(8):1-15.
[19]杨忠,吕斌,黄安民,等.近红外光谱技术快速识别针叶材和阔叶材的研究[J].光谱学与光谱分析,2012,32(7):1785-1789.YANG Z,LUB,HUANG A M,et al.Rapid identification of softwood and hardwood by near infrared spectroscopy of cross-sectional surfaces[J].Spectroscopy and Spectral Analysis,2012,32(7):1785-1789.(in Chinese)
[20]蒋焕煜,应义斌.尖椒叶片叶绿素含量的近红外检测分析实验研究[J].光谱学与光谱分析,2007,27(3):499-502.JIANG H Y,YING Y B.Measurement of clorophyll content in pepper Leaves by near infrared analysis[J].Spectroscopy and Spectral Analysis,2007,27(3):499-502.(in Chinese)
[21] WORKMAN J,WEYER L.近红外光谱解析实用指南[M].北京:化学工业出版社,2009.
[2]周熊,多化琼,王振柱,等.基于图像处理和SVM探索木材与树皮的新识别参数[J].西北林学院学报,2014,29(5):199-202.ZHOU X,DUO H Q,WANG Z Z,et al.New recognition parameters of wood nnd bark rate based on image processing and the SVM[J].Journal of Northwest Forestry University,2014,29(5):199-202.(in Chinese)
[3] DA E S,PEDRINI H.Inferring patterns in mitochondrial DNA sequences through hypercube independent spanning trees[J].Computers in Biology and Medicine,2016,70:51-57.
[4] AYED R A A,DEGNAN J H.Inferring rooted species trees from unrooted gene trees using approximate Bayesian computation[J].Molecular Phylogenetics and Evolution,2017,116:13-24.
[5] BARMPOUTIS P,DIMITROPOULOS K,BARBOUTIS I,et al.Wood species recognition through multidimensional texture analysis[J].Computers and Electronics in Agriculture,2018,144:241-248.
[6] ROJAS J A M,ALPUENTE J,POSTIGO D,et al.Wood species identification using stress-wave analysis in the audible range[J].Applied Acoustics,2011,72:934-942.
[7]严衍禄.近红外光谱分析基础与应用[M].北京:中国轻工业出版社,2005.
[8]窦刚,陈广胜,赵鹏.基于近红外光谱反射率特征的木材树种分类识别系统的研究与实现[J].光谱学与光谱分析,2016,36(8):2425-2429.DOU G,CHEN G S,ZHAO P.Research and implementation of wood species recowition system with wood near infrared spectral reflection features[J].Spectroscopy and Spectral Analysis,2016,36(8):2425-2429.(in Chinese)
[9]梁龙,房桂干,崔宏辉,等.近红外光谱结合支持向量机快速识别树种[J].林产化学与工业,2016,36(1):55-60.LIANG L,FANG G G,CUI H H,et al.Fast identification of wood species by near infrared spectroscopy coupling with support vector machine[J].Chemistry and Industry of Forest Products,2016,36(1):55-60.(in Chinese)
[10]张雯雅.近红外光谱技术在珍稀木材鉴别领域的研究与应用[D].杭州:浙江农林大学,2015.
[11]唐忠炳,张愈,易金,等.乌饭树叶保健饮料工艺技术及关键参数试验研究[J].江西科学,2018,36(1):54-59.
[12]陆志科,冯雁,苏泉,等.麻疯树叶提取物的抗菌作用研究[J].西北林学院学报,2012,27(4):181-185.LU Z K,FENG Y,SU Q,et al.Antimicrobial activity of the extracts fromJatropha curcas leaves[J].Journal of Northwest Forestry University,2012,27(4):181-185.(in Chinese)
[13]唐周怀,郭晓霞,张雅莉,等.国槐行道树叶螨种群消长与环境因子的分析[J].西北林学院学报,2000,15(3):76-79.TANG Z H,GUO X X,ZHANG Y L,et al.Studies on the relationship between spider-mate population dynamics and environmintal factors[J].Journal of Northwest Forestry University,2000,15(3):76-79.(in Chinese)
[14]吴朝学,严理,秦武明,等.木荷人工林营养元素分布格局[J].西北林学院学报,2017,32(1):54-61.WU C X,YAN L,QIN W M,et al.Distribution characteristics of nutrient elements in schima superba plantation[J].Journal of Northwest Forestry University,2017,32(1):54-61.(in Chinese)
[15]林恋竹,刘雪梅,赵谋明.神秘果树叶提取物降尿酸作用及其有效成分鉴定[J].中国食品学报,2018,18(1):270-277.LIN L Z,LIU X M,ZHAO M M.Decreasing uric acid effect of the extracts of miracle fruit(synepalum dulcificum)’leaf and identification of its active ingredient[J].Journal of Chinese Institute of Food Science and Technology,2018,18(1):270-277.(in Chinese)
[16]高玉萍.茶制品近红外快速测定方法的研究及指纹图谱的建立[D].杭州:浙江大学,2013.
[17] MEES C,SOUARD F,DELPORTE C,et al.Identification of coffee leaves using FT-NIR spectroscopy and SIMCA[J].Talanta,2018,177:4-11.
[18] LANG C,FLAVLA R C C,JOSE L C C.Near infrared spectroscopy facilitates rapid identification of both young and mature amazonian tree species[J].Plos One,2015,10(8):1-15.
[19]杨忠,吕斌,黄安民,等.近红外光谱技术快速识别针叶材和阔叶材的研究[J].光谱学与光谱分析,2012,32(7):1785-1789.YANG Z,LUB,HUANG A M,et al.Rapid identification of softwood and hardwood by near infrared spectroscopy of cross-sectional surfaces[J].Spectroscopy and Spectral Analysis,2012,32(7):1785-1789.(in Chinese)
[20]蒋焕煜,应义斌.尖椒叶片叶绿素含量的近红外检测分析实验研究[J].光谱学与光谱分析,2007,27(3):499-502.JIANG H Y,YING Y B.Measurement of clorophyll content in pepper Leaves by near infrared analysis[J].Spectroscopy and Spectral Analysis,2007,27(3):499-502.(in Chinese)
[21] WORKMAN J,WEYER L.近红外光谱解析实用指南[M].北京:化学工业出版社,2009.