脐橙糖度近红外光谱在线检测的建模变量优选

【目的】采用小波压缩结合遗传算法,优选脐橙糖度近红外光谱在线检测的建模变量,提高在线检测精度。【方法】利用近红外光谱检测装置采集脐橙样品的光谱,并将其转换为反射比光谱,在700.28～933.79 nm波段,利用小波变换将一阶微分处理后的近红外反射比光谱变量压缩成小波系数变量。经遗传算法优选后,建立偏最小二乘法（PLS）模型,并对该模型的预测结果进行评价。【结果】利用小波压缩结合遗传算法优选变量建立的脐橙糖度PLS模型,预测效果最优,模型的相关系数为0.759,模型预测均方根误差为0.468 °Brix。【结论】采用小波压缩结合遗传算法对变量进行优选,可提高脐橙糖度近红外光谱在线检测的精度。     

基于田间原位土壤含水量估测的可见/近红外光谱建模方法

为实时、准确地获取原位土壤含水量信息,利用可见/近红外光谱技术,分别使用全局偏最小二乘(PLS)建模、局部PLS建模方法,对田间原位土壤含水量进行快速估测。结果表明:全局PLS模型中,其建模集的决定系数(R~2)、交叉验证均方根误差(RMSECV)分别为0.943和1.750%,检验集的决定系数(R~2)、预测均方根误差(RMSEP)分别为0.956和1.260%。局部PLS模型中,分别比较了选取定标子集的2种方法(欧氏距离法和马氏距离法),采用欧氏距离法和马氏距离法选取定标子集进行建模的R~2值分别为0.974和0.979,RMSEP值分别为0.976%和0.943%。因此,将可见/近红外光谱技术应用到田间原位含水量测量是可行的,其中,使用局部建模方法的效果优于全局建模。     

基于近红外光谱不同波段的红松木材含水率预测分析

运用近红外光谱技术结合偏最小二乘法(PLS),对所采集光谱进行一阶导数和二阶导数处理,并对未处理原始光谱、一阶导数处理光谱和二阶导数处理光谱分别在7个不同波段范围内建立红松含水率预测模型.结果表明红松样本近红外光谱经一阶导数处理,波段在1 000～2 100nm范围内所建模型最优,其校正集相关性系数为0.992 5,校...     

长波近红外光谱在土壤总氮分析与稳定性中的应用

[目的]通过定标集、预测集、检验集的建模过程,采用偏最小二乘(PLS)方法结合波段选择建立土壤总氮快速分析的近红外(NIR)光谱模型。[方法]为了避免模型评价失真,基于随机性、相似性和稳定性,提出一种严谨的建模体系。将全谱扫描区(400～2 498nm)分成可见区(400～780 nm)、短波近红外区(780～1 100 nm)和长波近红外区(1 100～2 498 nm)。[结果]经过比较、检验,结果表明长波近红外达到了最好的模型效果和稳定性,最优PLS因子数为8,检验的预测均方根误差(V-SEP)和预测相关系数(V-RP)分别为0.118 g/kg和0.857,得到客观、稳定的预测模型。     

Strategies for monitoring within-field soybean yield using Sentinel-2 Vis-NIR-SWIR spectral bands and machine learning regression methods

Soybean crop plays an important role in world food production and food security, and agricultural production should be increased accordingly to meet the global food demand. Satellite remote sensing data is considered a promising proxy for monitoring and predicting yield. This research aimed to evaluate strategies for monitoring within-field soybean yield using Sentinel-2 visible, near-infrared and shortwave infrared (Vis/NIR/SWIR) spectral bands and partial least squares regression (PLSR) and support vector regression (SVR) methods. Soybean yield maps (over 500 ha) were recorded by a combine harvester with a yield monitor in 15 fields (3 farms) in Paraná State, southern Brazil. Sentinel-2 images (spectral bands and 8 vegetation indices) across a cropping season were correlated to soybean yield. Information pooled across the cropping season presented better results compared to single images, with best performance of Vis/NIR/SWIR spectral bands under PLSR and SVR. At the grain filling stage, field-, farm- and global-based models were evaluated and presented similar trends compared to leaf-based hyperspectral reflectance collected at the Brazilian National Soybean Research Center. SVR outperformed PLSR, with a strong correlation between observed and predicted yield. For within-field soybean yield mapping, field-based SVR models (developed individually for each field) presented the highest accuracies. The results obtained demonstrate the possibility of developing within-field yield prediction models using Sentinel-2 Vis/NIR/SWIR bands through machine learning methods.

     

基于光谱技术和SIMCA方法的润滑油鉴别

采用可见-近红外反射光谱结合独立软模式法(SIMCA)建立了不同品牌种类的发动机润滑油鉴别模型。研究在对光谱曲线进行预处理和聚类分析后,选取7个主成分作为SIMCA的最佳主成分,随机采用20×7个样本作为建模样本,其余的10×7个样本作为预测样本,应用SIMCA进行分类,在显著性水平为5%下,其预测分辨率为98.75%。根据变量建模能力值,找到敏感波段420~425 nm、492~518 nm和796~816 nm,并将相应波段的光谱值作为SIMCA的输入,进行建模预测,结果发现,预测分辨率达95.71%,能快速正确区分7类不同品种的发动机润滑油。     

近红外在线检测装置参数对苹果糖度模型适用性的影响

目的 近红外(Near-infrared)光谱在线检测装置的检测速度和积分时间等因素会影响所建立苹果糖度模型的性能,本文旨在分析检测速度和积分时间对模型适用性的影响,以提高在线检测的精度。方法 近红外光谱在线检测装置检测速度和积分时间分别设置为0.3 m/s+100 ms、0.5 m/s+70 ms、0.5 m/s+100 ms、0.5 m/s+120 ms、0.5 m/s+150 ms,共5个实验组,试验所用苹果样本共180个,在350~1 150 nm波长下采集5个试验组苹果的近红外光谱,应用偏最小二乘法(Partial least squares,PLS)建立苹果可溶性固形物含量(Soluble solid content,SSC)的预测模型。结果 近红外在线检测装置积分时间对苹果糖度的检测存在阈值,当积分时间低于70 ms时,模型预测性能较差。预测模型中建模集与预测集的检测速度与积分时间相同时的预测效果优于二者不同时的。检测速度和积分时间会影响在线检测的精度,不同检测速度和积分时间下,光线在苹果内部的传输路线不同,会导致光纤探头获得的内部信息有所差异,使预测性能变差。在0.3 m/s+100 ms、0.5 m/s+100 ms、0.5 m/s+120 ms和0.5 m/s+150 ms 4个试验组中使用Kennard-Stone算法挑选出135个具有代表性的样本光谱,建立了混合检测速度和积分时间的预测模型,其预测集相关系数(R_P)均在0.85以上,预测集均方根误差(RMSE_P)均低于0.65。结论 本研究建立的混合检测速度和积分时间的预测模型可对苹果的糖度达到更好的预测,满足不同检测装置参数下苹果糖度在线检测的要求。     

Nondestructive measurement of internal quality of Nanfeng mandarin fruit by charge coupled device near infrared spectroscopy

The soluble solids content (SSC) and total acidity (TA) are the major characteristics for assessing quality and maturity of Nanfeng mandarin fruits. The feasibility of charge coupled device near infrared spectroscopy (CCD-NIRS) combining with effective wavelengths selection algorithm used to measure SSC and TA nondestructively was investigated. The effective wavelengths to SSC and TA were chosen by interval partial least squares (iPLS) in the wavelength range of 600–980 nm. The predictive ability of SSC model used PLS regression was improved with r of 0.92 and RMSEP of 0.65 °Brix using effective wavelengths of 681.36–740.51 nm, 798.60–836.19 nm and 945.52–962.75 nm. The TA model was simplified with r of 0.64 and RMSEP of 0.09% using effective wavelengths of 817.57–836.19 nm, 909.85–927.60 nm and 945.52–962.75 nm. The experimental results demonstrated that the CCD-NIRS technique combining with iPLS algorithm was a feasible method to measure SSC and TA of Nanfeng mandarin fruits nondestructively.     

基于近红外技术的落叶松木材密度预测模型

运用近红外光谱对落叶松(Larix gemelinii Rupr)样品密度进行了研究,分别运用偏最小二乘法及主成分回归建立预测模型,并用建立的模型分别对每一个样品进行了预测。基于偏最小二乘法的校正模型及验证模型相关系数分别为0.964和0.918,校正标准误差及预测标准误差分别为0.016和0.021,模型预测值与实测值决定系数为0.93;主成分回归模型中,校正模型及验证模型相关系数分别为0.954和0.911,校正标准误差及预测标准误差分别为0.017和0.023,模型预测值与实测值决定系数为0.91。研究表明:基于主成分回归法与偏最小二乘法的近红外光谱分析建模,都可以实现对落叶松木材密度的有效预测,但相比较而言,偏最小二乘法略优于主成分回归法,所建立的模型对落叶松木材密度预测更加准确可靠。     

Identification of pummelo cultivars by using Vis/NIR spectra and pattern recognition methods

Vis/NIR spectroscopy was used in combination with pattern recognition methods to identify cultivars of pummelo (Citrus grandis (L.) Osbeck). A total of 240 leaf samples, 60 for each of the four cultivars were analyzed by Vis/NIR spectroscopy. Soft independent modeling of class analogy (SIMCA), partial least square discriminant analysis (PLS-DA), back propagation neural network (BPNN) and least squares support vector machine (LS-SVM) were applied to the spectral data. The first 8 principal components extracted by principal component analysis were used as inputs in building the BPNN and the LS-SVM models. The results showed that a 97.92 % of discrimination accuracy was achieved for both the BPNN and the LS-SVM models when used to identify samples of the validation set, indicating that the performance of the two models was acceptable. Comparatively, the results of the PLS-DA and the SIMCA models were unacceptable because they had lower discrimination accuracy. The overall results demonstrated that use of Vis/NIR spectroscopy coupled with the use of BPNN and LS-SVM could achieve an accurate identification of pummelo cultivars.     

Predicting plant available phosphorus using infrared spectroscopy with consideration for future mobile sensing applications in precision farming

Phosphorus (P) fertilisation recommendations rely primarily on soil content of plant available P (P_avl) that vary spatially within farm fields. Spatially optimized P fertilisation for precision farming requires reliable, rapid and non-invasive P_avl determination. This laboratory study aimed to test and to compare visible-near infrared (Vis–NIR) and mid-infrared (MIR) spectroscopy for P_avl prediction with emphasis on future application in precision agriculture. After calibration with the conventional calcium acetate lactate (CAL) extraction method, limitations of Vis–NIRS and MIRS to predict P_avl were evaluated in loess topsoil samples from different fields at six localities. Overall calibration with 477 (Vis–NIRS) and 586 (MIRS) samples yielded satisfactory model performance (R² 0.70 and 0.72; RPD 1.8 and 1.9, respectively). Local Vis–NIRS models yielded better results with R² up to 0.93 and RPD up to 3.8. For MIRS, results were comparable. However, an overall model to predict P_avl on independent test data partly failed. Sampling date, pre-crop harvest residues and fertilising regime affected model transferability. Varying transferability could partly be explained after deriving the cellulose absorption index from the Vis–NIR spectra. In 62 (Vis–NIRS) and 67% (MIRS) of all samples, prediction matched the correct P_avl content class. Rapid discrimination between high, optimal and low P classes could be carried out on many samples from single fields thus marking an improvement over the common practice. However, P_avl determination by means of IR spectroscopy is not yet satisfactory for determination of precision fertilizer dosage. For introduction into agricultural practice, a standardized sampling protocol is recommended to help achieve reliable spectroscopic P_avl prediction.

     

基于近红外光谱技术的大米掺伪定量判别

针对现在市场上常见的两种大米掺伪现象,利用近红外光谱技术结合化学计量学方法分别建立了大米中掺入低档米和掺入矿物油的定量分析模型。制配不同掺伪比例的大米样品,采集其近红外光谱,并选用标准正态变量变换、最大最小归一化、平滑和一阶导数4种方法对原始光谱进行预处理,分别结合偏最小二乘法建立PLS定量分析模型。通过对比建模结果选出的最优预处理方法是最大最小归一化,建立的掺低档米模型的校正集和预测集相关系数分别为0.9698和0.9845,均方根误差分别为8.66和6.46;掺矿物油米模型的校正集和预测集相关系数分别为0.9739和0.9888,均方根误差分别为0.106和0.0698。模型的预测精度和稳定性均很好,实现了对两种掺伪大米快速、准确的定量判别,为大米的品质监控提供了一种新的方法思路。     

基于PLS的不同水氮条件下带状套作玉米产量预测

[目的]利用高光谱数据构建一种"高光谱参数-光合色素-产量"模型间接估测套作玉米产量,为带状套作玉米产量无损预测提供技术手段.[方法]以不同年份、地点、品种、处理(氮肥、水分)的田间试验为基础,综合分析带状套作玉米各生育时期及全生育期光合色素参数与冠层高光谱参数和玉米产量的关系,明确玉米产量预测的最佳生育时期及光合色素...     

基于小波压缩的木材密度近红外光谱的预处理研究

近红外光谱数据维数多、数据量大,直接保存需要庞大储存空间,且海量数据会对网络化在线检测的分析速度和准确性产生影响。为探讨应用小波压缩进行近红外光谱预处理的可行性及其对枫桦木材密度预测精度的影响,通过强光探头采集木材圆盘的近红外光谱,在Matlab软件中应用小波变换法对枫桦木材密度近红外光谱数据进行压缩。结果表明:当小波基sym2分解层为6时,基于均衡稀疏标准形式的全局硬阈值压缩效果最好,将2 151个变量压缩成38个小波系数,其能量保留成分、零系数成分、压缩比分别为99.66%、98.34%、56.61%。用未处理光谱数据和压缩后的38个小波系数分别建立偏最小二乘定标分析模型,同时做内部交叉验证,并用未处理和压缩后的预测集做外部检验,得知压缩后校正模型对压缩后样品预测能力较好,预测决定系数为0.913 9。因此,小波压缩可有效简化近红外光谱数据,提高近红外光谱对枫桦木材密度的预测精度。      

杀菌剂及贮藏温度对砂糖桔贮藏效果的影响

研究了不同杀菌剂和贮藏温度对砂糖桔贮藏效果的影响。结果表明,特克多2 mL/L、施保克1000 mg/L的杀菌效果最好;其次为多菌灵0.1%、多菌灵0.2%、朴海因500倍、朴海因1000倍;特克多4 mL/L的效果最差。在20℃贮藏条件下,果实的贮藏时间较短,且果实腐烂指数显著高于低温条件(3~5℃、5~7℃、7~9℃)。随着低温贮藏时间的延长,果实SSC和TA均呈下降趋势,这3个低温条件对果实SSC含量的影响不明显,然而3~5℃贮藏条件可缓解果实TA含量的下降并可在一定程度上保持果实的口感。分析认为施保克1000 mg/L为砂糖桔较理想的杀菌剂,3~5℃为其适宜的贮藏温度。     

基于NIR及PLS-PCR-SVR预测森林土壤有机碳含量

森林土壤有机碳含量是表征林地土壤营养状况的重要指标,该文建立了土壤有机碳含量的近红外光谱定标模型,并比较了偏最小二乘法（PLS）、支持向量机回归（SVR）、主成分回归（PCR）3种建模方法及Savitzky-Golay平滑＋多元散射校正、Savitzky-Golay平滑＋一阶导数、Savitzky-Golay平滑＋二阶导数、Savitzky-Golay平滑＋多元散射校正＋一阶导数、Savitzky-Golay平滑＋多元散射校正＋二阶导数5种光谱预处理方法对土壤有机碳含量定标模型精度的影响,同时进行了波段优选。结果表明：当光谱区域为1 380～1 450 nm,1 800～1 950 nm,2 050～2 300 nm,光谱数据采用Savitzky-Golay平滑＋多元散射校正＋一阶导数预处理,采用PLS的建模方法,主成分数为8时,建立的校正模型预测效果最佳。校正模型的R、RMSE、SEC分别为0.805 2、0.512 2、0.512 5;预测模型的R、RMSE、SEP分别为0.768 1、0.514 3、0.514 6。因此,利用近红外光谱技术可以实现土壤有机碳含量的快速估测,为林区实时、大面积、快速测定森林土壤有机碳含量提供了技术可行性。     

近红外在线检测技术在人参提取物生产中的应用

采用比色法和近红外漫反射、液体透射在线检测技术,分别测定93个不同产地、不同年生人参原材料固体样品和558个人参提取液样品的总皂苷含量和近红外光谱,结合偏最小二乘回归法,建立样品总皂苷含量与近红外光谱之间的数学模型。采用内部交叉检验对模型进行评价。评价结果显示:内部交叉检验的决定系数R2>0.95,交叉检验均方差(RMSECV)值分别为0.071 6和0.032 7,相对分析误差(RPD)分别为2.83和3.97。模型评价数据均有较好的表现,原材料、提取液检验样品近红外测定结果与化学参考值之间无显著性差异,近红外检测技术可以应用于人参原材料固体样品和人参提取液样品中总皂苷含量的快速测定。     

基于电子鼻多传感器融合的茶叶存储时间识别

借助电子鼻检测存储60、120、180、240、300、360 d的黄山毛峰茶香气信息,根据电子鼻各传感器响应曲线变化特点,选取出1组能够表征不同香气信息的基本特征变量,分别采用主成分回归(PCR)、偏最小二乘回归(PLS)和BP神经网络(BPNN)方法,建立茶叶存储时间的预测模型。测试样本集对3种预测模型的检验结果表明:PCR、PLS、BPNN模型的预测标准误差分别为10.05、6.04、3.21d;最大预测相对误差分别为11.03%、7.02%、5.89%;平均预测相对误差分别为6.73%、4.74%、3.62%;预测值与实际值之间的决定系数R2分别为0.862、0.896、0.987。3种模型都能较好地对茶叶存储时间进行预测,相比较而言,BPNN模型性能最优,PLS模型性能优于PCR模型。     

基于近红外光谱技术的保水剂吸水倍率快速测定新方法

[目的]基于近红外光谱技术,研究保水剂吸水倍率的快速测定新方法。[方法]通过近红外光谱技术结合偏最小二乘法,对9种聚丙烯酰胺型保水剂的吸水倍率进行研究.[结果]保水剂样品光谱数据采用一阶导数法预处理后,应用PLS法建模预测效果最佳。真值与预测值的决定系数达99．55％,模型预测准确率都在96％以上,可应用于生产实践。[结论]应用近红外光谱技术结合PLS法可以准确预测出保水剂的吸水倍率,是一种快速、无损、环保的新方法。