CAJ | 학술논문

利用野外便携式ASD Qualityspec 光谱仪,实测了田间甜菜冠层光谱数据,采用植被指数对氮含量进行预测,发现估算精度较低,分析 NDVI 与 VLOPT 与氮含量的相关性,得出氮含量在很小的时候就达到饱和水平. 根据4 种预处理下的甜菜冠层光谱,分别采用偏最小二乘回归( PLSR )和主成分回归( PCR )建立甜菜氮含量估算模型,比较不同预处理和不同回归方法对估算精度的影响. 结果表明:对 PLSR 来说,一阶导数处理的光谱数据建立的模型精度最好( RMSE=2 .3 4 g/kg , RE=1 9 .6%) ,平滑、MSC 和SNV建立的估算模型次之;对 PCR 来说,平滑处理的光谱数据建立的模型精度最好(RMSE=2.34g/kg,RE=19.4%). 总的看来,不同预处理对估算模型精度有一定的差异,但PLSR和 PCR两种回归方法对甜菜氮含量估算模型影响不大.
이용야외편휴식ASD Qualityspec 광보의,실측료전간첨채관층광보수거,채용식피지수대담함량진행예측,발현고산정도교저,분석 NDVI 여 VLOPT 여담함량적상관성,득출담함량재흔소적시후취체도포화수평. 근거4 충예처리하적첨채관층광보,분별채용편최소이승회귀( PLSR )화주성분회귀( PCR )건립첨채담함량고산모형,비교불동예처리화불동회귀방법대고산정도적영향. 결과표명:대 PLSR 래설,일계도수처리적광보수거건립적모형정도최호( RMSE=2 .3 4 g/kg , RE=1 9 .6%) ,평활、MSC 화SNV건립적고산모형차지;대 PCR 래설,평활처리적광보수거건립적모형정도최호(RMSE=2.34g/kg,RE=19.4%). 총적간래,불동예처리대고산모형정도유일정적차이,단PLSR화 PCR량충회귀방법대첨채담함량고산모형영향불대.
This paper analyzes the beet canopy spectra under four pretreatment were used partial least squares regression ( PLSR) and principal component regression ( PCR) to establish beet nitrogen content estimation model , compare differ-ent methods of pretreatment and different regression estimation accuracy impact on PLSR , the first order derivative of the spectral data processing model established best accuracy ( RMSE=2.34g/kg, RE=19.6%), smoothing, estimation model followed by MSC and SNV established;for PCR toHe said precision spectral data smoothing model established best (RMSE=2.34g/kg,RE=19.4%).Overall, there are some different pre-treatment model to estimate the accuracy of differences , but the two regression PLSR and PCR methods to estimate the nitrogen content of beet little effect model .