CAJ | 학술논문

为了提高近红外光谱技术快速测定番茄苗氮含量的准确度和稳健性，比较分析竞争自适应重加权采样法（CARS）、蒙特卡罗无信息变量消除法（MCUVE）、向后间隔偏最小二乘法（BiPLS ）和组合间隔偏最小二乘法（SiPLS ）四种特征波长挑选方法，筛选与番茄苗氮含量相关的特征光谱。在十种不同氮素处理水平下（尿素溶液浓度0～120 mg?L －1），培育60株番茄苗样本（每个处理6株），使其分别处于不同程度的过量氮素、氮素适度、缺氮素和无氮素状态。分别采集每株番茄苗样本的叶片，扫描其12500～3600 cm－1波段的近红外光谱。比较四种方法所建立的番茄苗氮素定量分析模型可知：CARS和 MCUVE挑选的特征变量所建定标模型的性能比BiPLS和SiPLS挑选的特征变量所建定标模型的性能更优，但是预测性能远低于后者。其中，基于BiPLS建立的番茄苗氮素含量预测模型性能最佳，相关系数（r）、预测均方根误差（RMSEP）和性能对标准差之比（RDP）分别为0.9527，0.1183和3.2910。因此，近红外光谱技术结合特征谱区筛选可以有效地提高番茄苗叶片氮素含量的定量分析模型指标，使模型更实用化。但是，特征波长挑选方法不具有普适性。基于单个波长变量筛选的方法所建立的模型较为敏感，更适用于样本状态较为均匀的待测对象；而基于波长区间筛选的方法所建的模型相对抗干扰性更强，更适用于样品状态不均匀，重现性较差的待测对象。因此，特征光谱筛选只有与样本状态及建模指标结合，才能使其在建模过程中发挥更好的作用。
위료제고근홍외광보기술쾌속측정번가묘담함량적준학도화은건성，비교분석경쟁자괄응중가권채양법（CARS）、몽특잡라무신식변량소제법（MCUVE）、향후간격편최소이승법（BiPLS ）화조합간격편최소이승법（SiPLS ）사충특정파장도선방법，사선여번가묘담함량상관적특정광보。재십충불동담소처리수평하（뇨소용액농도0～120 mg?L －1），배육60주번가묘양본（매개처리6주），사기분별처우불동정도적과량담소、담소괄도、결담소화무담소상태。분별채집매주번가묘양본적협편，소묘기12500～3600 cm－1파단적근홍외광보。비교사충방법소건립적번가묘담소정량분석모형가지：CARS화 MCUVE도선적특정변량소건정표모형적성능비BiPLS화SiPLS도선적특정변량소건정표모형적성능경우，단시예측성능원저우후자。기중，기우BiPLS건립적번가묘담소함량예측모형성능최가，상관계수（r）、예측균방근오차（RMSEP）화성능대표준차지비（RDP）분별위0.9527，0.1183화3.2910。인차，근홍외광보기술결합특정보구사선가이유효지제고번가묘협편담소함량적정량분석모형지표，사모형경실용화。단시，특정파장도선방법불구유보괄성。기우단개파장변량사선적방법소건립적모형교위민감，경괄용우양본상태교위균균적대측대상；이기우파장구간사선적방법소건적모형상대항간우성경강，경괄용우양품상태불균균，중현성교차적대측대상。인차，특정광보사선지유여양본상태급건모지표결합，재능사기재건모과정중발휘경호적작용。
In order to improve the accuracy and robustness of detecting tomato seedlings nitrogen content based on near-infrared spectroscopy (NIR) ,4 kinds of characteristic spectrum selecting methods were studied in the present paper ,i .e .competitive adaptive reweighted sampling (CARS) ,Monte Carlo uninformative variables elimination (MCUVE) ,backward interval partial least squares (BiPLS) and synergy interval partial least squares (SiPLS) .There were totally 60 tomato seedlings cultivated at 10 different nitrogen-treatment levels (urea concentration from 0 to 120 mg?L -1 ) ,with 6 samples at each nitrogen-treatment lev-el .They are in different degrees of over nitrogen ,moderate nitrogen ,lack of nitrogen and no nitrogen status .Each sample leav-es were collected to scan near-infrared spectroscopy from 12 500 to 3 600 cm-1 .The quantitative models based on the above 4 methods were established .According to the experimental result ,the calibration model based on CARS and MCUVE selecting methods show better performance than those based on BiPLS and SiPLS selecting methods ,but their prediction ability is much lower than that of the latter .Among them ,the model built by BiPLS has the best prediction performance .The correlation coef-ficient (r) ,root mean square error of prediction (RMSEP) and ratio of performance to standard derivate (RPD) is 0.952 7 , 0.118 3 and 3.291 ,respectively .Therefore ,NIR technology combined with characteristic spectrum selecting methods can im-prove the model performance .But the characteristic spectrum selecting methods are not universal .For the built model based on single wavelength variables selection is more sensitive ,it is more suitable for the uniform object .While the anti-interference abil-ity of the model built based on wavelength interval selection is much stronger ,it is more suitable for the uneven and poor repro-ducibility object .Therefore ,the characteristic spectrum selection will only play a better role in building model ,combined with the consideration of sample state and the model indexes .