Estimating the Texture of Purple Soils Using Vis-NIR Spectroscopy and Optimized Conversion Models

Soil texture is an indicator of soil physical structure which delivers many ecological functions of soils such as thermal regime, plant growth, and soil quality. However, traditional methods for soil texture measurement are time-consuming and labor-intensive. This study attempts to explore an indirect method for rapid estimating the texture of three subgroups of purple soils (i.e. calcareous, neutral, and acidic). 190 topsoil (0 - 10 cm) samples were collected from sloping croplands in Tongnan and Beibei Districts of Chongqing Municipality in China. Vis-NIR spectrum was measured and processed, and stepwise multiple linear regression (SMLR), partial least squares regression (PLSR), and back propagation neural network (BPNN) models were constructed to inform the soil texture. The clay fractions ranged from 4.40% to 27.12% while sand fractions ranged from 0.34% to 36.57%, hereby soil samples encompass three textural classes (i.e. silt, silt loam, and silty clay loam). For the original spectrum, the texture of calcareous and neutral purple soils was not significantly correlated with spectral reflectance and linear models (SMLR and PLSR) exhibited low prediction accuracy. The correlation coefficients and the goodness-of-fits between soil texture and the transformed spectra of all soil groups increased by continuum-removal (CR), first-order differential (R'), and second-order differential (R") transformations. Among them, the R" had the best performance in terms of improving the correlation coefficients and the goodness-of-fits. For the calcareous purple soil, the SMLR exceeds PLSR and BPNN with a higher coefficient of determination (R2) and the ratio of performance to inter-quartile distance (RPIQ) values and lower root mean square error of validation (RMSEV), but for the neutral and acidic purple soils, the PLSR model has a better prediction accuracy. In summary, the linear methods (SMLR and PLSR) are more reliable in estimating the texture of the three purple soil groups when using Vis-NIR spectroscopy inversion.

Vis-NIR光谱模式识别结合SG平滑用于转基因甘蔗育种筛查

以Savitzky-Golay(SG)平滑筛选,主成分分析(PCA)分别结合有监督的线性判别分析(LDA)、无监督的系统聚类分析(HCA),应用于转基因甘蔗育种筛查的可见-近红外(Vis-NIR)无损检测。提出兼顾随机性、稳定性的定标、预测、检验框架;取田间种植处于伸长期甘蔗叶样品456个,具有Bt基因和Bar基因的转基因样品(阳)306个,非转基因样品(阴)150个;随机选取156个为检验集(阴性50、阳性106),余下为建模集(阴性100、阳性200,共300),建模集再随机划分为定标集(阴性50、阳性100,共150)、预测集(阴性50、阳性100,共150)共50次;扩充SG平滑点数,同时删除绝对值偏小的高阶导数模式,共264个平滑模式用于模型筛选;采用前3个主成分两两组合,再根据模型效果选出最优主成分组合;基于所有定标、预测集划分和SG平滑模式,建立SG-PCA-LDA和SG-PCA-HCA模型,根据平均预测效果优选参数,使模型具有稳定性;最后用检验集进行模型检验。经SG平滑后,PCA-LDA和PCA-HCA的建模精度、稳定性均显著改善;最优SG-PCA-LDA模型阳性、阴性样品检验识别率分别达到94.3%和96.0%;最优SG-PCA-HCA模型阳性、阴性样品检验识别率分别达到92.5%和98.0%。结果表明:Vis-NIR光谱模式识别结合SG平滑可用于转基因甘蔗叶的准确识别,提供了一种简便的转基因甘蔗育种筛查方法。

基于野外Vis-NIR光谱的土壤有机质预测与制图

利用野外实时快速获取的土壤光谱进行土壤有机质(SOM)预测与制图是精确农业与土壤遥感制图的必然需要,利用ASD FieldSpec Pro FR野外型光谱仪实时快速获取的光谱数据,去除噪声较大的边缘波段后,进行倒数的对数转换(Log(1/R))为吸收光谱。在分析吸收光谱和光谱指数与SOM关系的基础上,采用偏最小二乘回归法进行SOM的建模预测并借助地统计学方法进行SOM空间变异制图研究。结果表明,建模效果好的指标分别为特征波段(R2=0.91,RPD=3.28),归一化光谱指数(R2=0.90,RPD=3.08),特征波段与3个光谱指数组合(R2=0.87,RPD=2.67),全波段(R2=0.95,RPD=4.36)。光谱指标的克里格制图与实测SOM制图表现出相同的空间变异趋势,不同的指标均达到了较好的预测效果。

利用OSC算法消除土壤含水量变化对Vis-NIR光谱估算有机质的影响

【目的】快速、准确地监测土壤有机质对于精准农业的发展具有重要意义。可见光-近红外(visible and near-infrared,Vis-NIR)光谱技术在土壤属性估算、数字化土壤制图等方面应用较为广泛,然而,在田间进行光谱测量,易受土壤含水量(soil moisture,SM)、温度、土壤表面状况等因素的影响,导致光谱信息中包含大量干扰信息,其中,SM变化是影响光谱观测结果最为显著的因素之一。此研究的目的是探讨OSC算法消除其影响,提升Vis-NIR光谱定量估算土壤有机质(soil organic matter,SOM)的精度。【方法】以江汉平原公安县和潜江市为研究区域,采集217份耕层(0—20 cm)土壤样本,进行风干、研磨、过筛等处理,采用重铬酸钾-外加热法测定SOM;将总体样本划分为3个互不重叠的样本集:建模集S^0(122个样本)、训练集S^1(60个样本)、验证集S^2(35个样本);设计SM梯度试验(梯度间隔为4%),在实验室内获取S^1和S^2样本集的9个梯度SM(0%—32%)的土壤光谱数据;分析SM对土壤Vis-NIR光谱反射率的影响,采用外部参数正交化算法(external parameter orthogonalization,EPO)、正交信号校正算法(orthogonal signal correction,OSC)消除SM对土壤光谱的干扰;利用主成分分析(principal component analysis,PCA)的前两个主成分得分和光谱相关系数两种方法检验消除SM干扰前、后的效果;基于偏最小二乘回归(partial least squares regression,PLSR)方法建立EPO和OSC处理前、后的SOM估算模型,利用决定系数(coefficient of determination,R^2)、均方根误差(root mean square error,RMSE)和RPD(the ratio of prediction to deviation)3个指标比较PLSR、EPO-PLSR、OSC-PLSR模型的性能。【结果】土壤Vis-NIR光谱受SM的影响十分明显,随着SM的增加,土壤光谱反射率呈非线性降低趋势。OSC处理前的湿土光谱数据主成分得分散点相对分散,与干土光谱数据主成分得分空间的位置不重叠,不同SM梯度之间的光谱相关系数变化较大;OSC处理后的湿土光谱数据主成分得分空间的位置基本与干土光谱数据相重合,各样本光谱数据之间相似性很高,不同SM梯度之间的光谱相关系数变化较小。9个SM梯度的EPO-PLSR模型的验证平均R^2_(pre)、RPD分别为0.69、1.7。9个SM梯度的OSC-PLSR模型的验证平均R^2_(pre)、RPD分别为0.72、1.89,校正后的OSC-PLSR模型受SM的较小,有效提升SOM估算模型的精度和鲁棒性。【结论】OSC能够消除SM变化对土壤Vis-NIR光谱的影响,可为将来田间原位实时监测SOM信息提供一定的理论支撑。

基于正交信号校正的Vis-NIR光谱土壤质地预测

为提高基于VIS-NIR光谱的土壤质地预测精度,引入了正交信号校正(OSC)光谱预处理算法。分别用原始光谱、微分处理、OSC处理光谱,建立偏最小二乘回归(PLSR)模型。结果表明,OSC-PLSR模型验证精度高于其他两种方法所建模型,砂粒含量OSC-PLSR模型的RMSEp为5.94,粘粒含量OSC-PLSR模型RMSEp为1.25,相比PLSR模型,分别降低22.22%和9.42%。OSC算法在土壤质地的VIS-NIR反演中能有效消除不相关因素的影响,提高模型预测精度。

基于ArcGIS和Vis-NIR脐橙园土壤养分含量分布图预测研究

以赣南区某脐橙园土壤为研究对象,针对不用层土壤的全氮、全磷及有机质养分信息,采用傅里叶型近红外光谱仪和可见/近红外光谱检测装置不同参数配比下组合,采集土壤样品光谱。用化学方法测定养分真值,结合光谱预处理方法和化学计量学算法建立定量检测数学模型,选择出最优的仪器参数、最合适的预处理方法和算法,确定最终的数学模型。实验采样点的数量是有限的,要想得到整个研究区的养分分布数据就需要采用克里金插值法(Kriging)对这些采样点各养分进行插值,运用ArcGIS软件中的地统计分析模块功能,对采样点的土壤全氮、全磷及有机质的真实化学值和最优模型预测值进行克里金插值,得出采样区的土壤养分空间分布图。

土壤含水量对采用Vis-NIR光谱分析土壤质地的影响

Vis-NIR光谱应用于野外土壤质地分析时,其分析精度将受到土壤含水量的影响。该文旨在定量研究基于Vis-NIR光谱对土壤质地分析时,土壤含水量对精度的影响。在实验室条件下分别测定8种不同含水量状态下土壤样品（78个）的Vis-NIR光谱反射率,运用偏最小二乘回归（PLSR）分别建立不同含水量状态下土壤质地分析模型,每一模型分别分析8种不同含水量状态下验证集的土壤质地。结果表明,当土壤处于同一湿度状态时,各含水量状态下均可获得较好的结果,粘粒含量和砂粒含量最佳分析模型对应的含水量分别为150-200g/kg和200-250g/kg。当土壤含水量差异较大时,分析精度随着验证样本与建模样本水分含量的差异增大而急剧降低。研究认为,当土壤处于同一湿度状态时,可直接应用Vis-NIR光谱分析湿土的土壤质地,在土壤水分状态差异较大时,宜根据含水量建立分组分析模型。

基于Vis-NIR光谱的土壤质地BP神经网络预测

为快速、准确地获取土壤质地信息,提出了应用Vis-NIR光谱结合BP神经网络的建模方法。以河南封丘县的86个土壤样本为研究对象,以原始光谱和微分光谱主成分为输入变量,建立土壤粘粒和砂粒的BP神经网络预测模型,并将其预测结果与多元线性逐步回归模型进行比较。结果表明:基于原始光谱主成分的BP人工神经网络预测结果最好,优于多元逐步回归模型,预测粘粒和砂粒的RMSE分别为1.62和6.52。BP神经网络所建模型训练时间短、准确度也较高,能实现对土壤质地的高效预测。

基于灰色关联度和Vis-NIR的不同贮藏方式下番茄光谱特性分析

[目的]确定不同贮藏方式下,影响番茄样本定性判别的主要品质指标。[方法]本文采用可见近红外光谱技术分析了不同贮藏方式下番茄的光谱特性;引入主成分分析和灰色关联度分析方法对不同贮藏方式的番茄样本进行定性判别和贡献指标确定。[结果]不同贮藏方式下番茄的光谱特性有所不同,可用主成分分析提取的3个敏感波段1 927、1 401、1 222 nm(累积贡献率为98.92%)对其进行区分;与1 927 nm吸光度值关联度最大的为可滴定酸,与1 401 nm吸光度值关联度最大的为可溶性固形物,与1 222 nm吸光度值关联度最大的为可滴定酸。[结论]可滴定酸和可溶性固形物是影响其主成分分析的主要品质指标,也是影响上述不同贮藏方式下番茄样本分类的指标。该研究可为后续基于光谱技术的不同贮藏方式下番茄品质快速检测提供依据。

基于Vis-NIR光谱的不同水分状态下土壤有机质预测

以河南省封丘县的86个土壤样本为研究对象,测定9种不同含水量状态下的土壤光谱反射率,运用偏最小二乘回归（PLSR）建立不同含水量状态下的土壤有机质预测模型;运用0-50 g·kg^-1,200-250 g·kg^-1,400-450 g·kg^-1水分状态下3组模型进行交互预测,以研究含水量状态差异较大情况下,土壤含水量对有机质预测精度的影响。结果显示,建模样本与预测样本处于同一含水量状态下,土壤含水量对土壤有机质含量预测精度的影响不显著;当验证集样本与建模集样本间水分状态差异较大时,预测结果会出现较大误差。当土壤处于同一湿度状态时,可直接应用Vis-NIR光谱预测湿土的有机质;当土壤样本间水分差异较大时,可依据含水量状态建立分组模型,以提高Vis-NIR光谱预测有机质的精度。

基于vis-NIR光谱的Bootstrap-PLSR模型进行SOM预测精度评价

土壤有机质(SOM)是土壤肥力重要指标之一。快速,无损且准确地预测SOM含量对于保护和提升土壤肥力有重要作用。可见-近红外(vis-NIR)光谱结合偏最小二乘回归(PLSR)模型在土壤属性估测中广泛使用,目的是探讨通过Bootstrap抽样提高PLSR的预测能力和泛化能力。以江西、浙江和湖南三省水稻土为研究对象,采集了523个耕层(0~20 cm)土壤样本,比较偏最小二乘回归(PLSR)和Bootstrap-PLSR两种回归模型在估测SOM的精度和泛化能力;利用确定系数(R^2),均方根误差(RMSE)和性能指标(RPIQ,标准差与四分位间距离的比值)来评估预测的准确度,利用Bootstrap抽样后预测值的95%置信区间和实测值的分布情况、欠拟合和过拟合PLSR和Bootstrap-PLSR回归因子的差异来分析Bootstrap-PLSR模型的泛化能力和稳定性。研究表明:使用Bootstrap-PLSR预测的SOM含量的预测精度(R^2=0.76,RMSE=5.82,RPIQ=2.51)高于PLSR模型(R^2=0.72,RMSE=6.27,RPIQ=2.33)。Bootstrap抽样能够提高SOM含量中间部分的预测精度并且具有较强的建模稳定性,Bootstrap-PLSR具有较强的泛化能力且可以用来选择特征波段。

Estimating purple-soil moisture content using Vis-NIR spectroscopy

Soil moisture is essential for plant growth in terrestrial ecosystems.This study investigated the visible-near infrared(Vis-NIR)spectra of three subgroups of purple soils(calcareous,neutral,and acidic)from western Chongqing,China,containing different water contents.The relationship between soil moisture and spectral reflectivity(R)was analyzed using four spectral transformations,and estimation models were established for estimating the soil moisture content(SMC)of purple soil based on stepwise multiple linear regression(SMLR)and partial least squares regression(PLSR).We found that soil spectra were similar for different moisture contents,with reflectivity decreasing with increasing moisture content and following the order neutral>calcareous>acidic purple soil(at constant moisture content).Three of the four spectral transformations can highlight spectral sensitivity to SMC and significantly improve the correlation between the reflectance spectra and SMC.SMLR and PLSRmethods provide similar prediction accuracy.The PLSR-based model using a first-order reflectivity differential(R?)is more effective for estimating the SMC,and gave coefficient of determination(v2),root mean square errors of validation(RMSEV),and ratio of performance to inter-quartile distance(RPIQ)values of 0.946,1.347,and 6.328,respectively,for the calcareous purple soil,and 0.944,1.818,and 6.569,respectively,for the acidic purple soil.For neutral purple soil,the best prediction was obtained using the SMLR method with R?transformation,yieldingv2,RMSEV and RPIQ values of 0.973,0.888 and 8.791,respectively.In general,PLSR is more suitable than SMLR for estimating the SMC of purple soil.

Modeling method for SSC prediction in pomelo using Vis-NIRS with wavelength selection and latent variable updating

The aim of this study was in-line,rapid,and non-destructive detection for soluble solid content(SSC)in pomelos using visible and near-infrared spectroscopy(Vis-NIRS).However,the large size and thick rind of pomelo affect the stability of spectral acquisition and the biological variabilities affect the robustness of models.Given these issues,in this study,an efficient prototype in-line detection system in transmittance mode was designed and evaluated in comparison with an off-line detection system.Data from the years 2019 and 2020 were used for modeling and the external validation data were obtained by the inline detection system in 2021.The wavelength selection methods of changeable size moving window(CSMW),random frog(RF),and competitive adaptive reweighted sampling(CARS)were used to improve the prediction accuracy of partial least squares regression(PLSR)models.The best performance of internal prediction was obtained by CARS-PLSR and the determination coefficient of prediction(),root mean square error of prediction(RMSEP),and residual predictive deviation(RPD)were 0.958,0.204%,and 4.821,respectively.However,all models obtained large prediction biases in external validation.The latent variable updating(LVU)method was proposed to update models and improve the performance in external validation.Ten samples from the external validation set were randomly selected to update the models.Compared with the recalibration method,LVU could effectively modify the original models which matched the SSC range of the external validation set.The CSMW-PLSR models were more robust in external validations.The off-line model with LVU performed best with a root mean square error of validation(RMSEV)of 0.599%and the in-line model with recalibration obtained RMSEV of 0.864%.These results demonstrated the application potential of the transmittance Vis-NIRS for in-line rapid prediction of SSC in pomelos and the modeling and updating methods could be applied to samples with biological variabilities.

基于野外实测Vis-NIR光谱的土壤肥力估算研究——以湟水流域为例

为探讨野外实测光谱数据对土壤肥力的估算能力,采集青海省湟水流域表层0~20 cm土壤样品220份,同步测量其采样位置的野外实测光谱数据,实验室对土壤养分、机械组成含量以及pH值进行分析。基于上述数据,对野外实测光谱反射率进行多元散射校正(Multiplicative scatter correction,MSC)、SG-一阶导数变换(SG-First Derivative,SG-1st)预处理,采用稳定性竞争自适应重加权采样法(stability competitive adaptive reweighted sampling,SCARS)提取不同土壤养分、机械组成含量以及pH值的特征波段,以偏最小二乘回归(partial least squares regression,PLSR)模型对土壤全碳(TC)、有机质(OM)、全氮(TN)、碱解氮(AN)、pH、黏粒(clay)、粉粒(silt)、砂粒(sand)含量进行估算并对比分析,构建土壤养分含量、pH值以及机械组成含量的最优野外实测光谱估算模型。结果表明:通过MSC校正和SG-1st变换能够有效增强野外光谱特征;经SCARS选取的特征波段主要集中于近红外波段。基于野外实测光谱数据建立的PLSR模型能够对研究区土壤TC、OM、TN、AN含量以及pH值进行粗略估算;其中,对于TC、OM、TN含量及pH值而言,最佳估算模型为经SG-1st处理后的SCARS-PLSR模型,RPD值均达到1.70以上(RPD_(TC)=1.76;RPD_(OM)=1.82;RPD_(TN)=2.04;RPD_(pH)=1.89),RPIQ值均达到1.90以上(RPIQ_(TC)=1.91;RPIQ_(OM)=2.53;RPIQ_(TN)=2.98;RPIQ_(pH)=2.03);对于土壤AN含量而言,经MSC处理后的SCARS-PLSR模型最佳,其RPDAN值高达1.91,RPIQ值高达2.39。对土壤clay、silt以及sand含量野外光谱均无法估算,RPD值均在1.00左右,RPIQ值在1.20左右。

Construction of n-TiO_(2)/p-Ag_(2)O Junction on Carbon Fiber Cloth with Vis-NIR Photoresponse as a Filter-Membrane-Shaped Photocatalyst

The development of effective and reusable photocatalysts with broad-spectra activity has attracted attention.Herein,we have constructed n-TiO_(2)/p-Ag_(2)O junction on carbon fiber(CF)cloth as an efficient and recyclable photocatalyst.With CF cloth as the substrate,TiO_(2) nanorods(length:1-2μm)are prepared by a hydrothermal process,and the in-situ growth of Ag_(2)O nanoparticles(10-20 nm)is then realized by chemical bath deposition route.The flexible CF/TiO_(2)/Ag_(2)O cloth(area:4×4 cm^(2))shows a broad and strong photo-absorption(200-1000 nm).Under the illumination of visible-light(λ>400 nm),CF/TiO_(2)/Ag_(2)O cloth can efficiently eliminate 99.2%rhodamine B(RhB),99.4%acid orange 7(AO7),87.6%bisphenol A(BPA),and 89.5%hexavalent chromium(Cr^(6+))in 100 min,superior to CF/Ag_(2)O cloth(83.5%RhB,60.0%AO7,31.2%BPA and 41.8%Cr^(6+)).In particular,under the NIR-light illumination(980 nm laser),CF/TiO_(2)/Ag_(2)O cloth can remove 70.9%AO7 and 60.0%Cr^(6+) in 100 min,which are significantly higher than those by CF/Ag_(2)O cloth(19.8%AO7 and 18.9%Cr^(6+)).In addition,CF/TiO_(2)/Ag_(2)O cloth(diameter:10 cm),as a filter-membrane,can effectively wipe off 94.4%flowing RhB solution(rate:~1 L h^(−1))at 6th filtering/degrading grade.Thus,CF/TiO_(2)/Ag_(2)O cloth can be used as a Vis-NIR-responded filter-membrane-shaped photocatalyst with high-efficiency for purifying wastewater.

Lateral organic-inorganic hybrid Vis-NIR photodetectors based on GaN nanowires promoting photogenerated carriers transfer

The narrow bandgap of the low-energy near-infrared(NIR)polymer would lead to overlap between adjacent energy levels,which is a major barrier to the preparation of Vis-NIR polymer bulk hetero-junction(BHJ)photodetectors with small responsivity and photocurrent.In this study,a high-performance lateral inorganic-organic hybrid photodetector was constructed to eliminate this barrier by combining GaN nanowires(GaN-NWs)with PDPP3T:PC61BM-based BHJ.In stage one,high-quality GaN-NWs were synthesized by the catalyst-free CVD method.The mechanism for controlling GaN-NWs morphology by adjusting the NH3 flow rate was revealed.In stage two,the GaN-NWs with large electron mobility were used to accelerate the transfer of photogenerated carriers in the BHJ layer.Finally,compared with the BHJ device,the BHJ/GaN device demonstrated obvious improvements in responsivity and photocurrent at the wavelength between 400 and 1000 nm.The responsivity and photocurrent increased over 20-fold at the NIR band of 800e900 nm.Besides,owing to the energy level gradient effect,the BHJ/GaN device has a response speed of 7.8/<5.0 ms,which increases over three orders of magnitude than that of the GaN-NWs-based device(tr/tf:7.1/10.9 s).Therefore,the novel device structure proposed in this work holds great potential for preparing high-performance Vis-NIR photodetectors.

Rapidly and mildly transferring anatase phase of graphene-activated TiO2 to rutile with elevated Schottky barrier:Facilitating interfacial hot electron injection for Vis-NIR driven photocatalysis

Visible and even infrared(IR)light-initiated hot electrons of graphene(Gr)catalysts are a promising driven power for green,safe,and sustainable H2O2 synthesis and organic synthesis without the limitation of bandgap-dominated narrow light absorption to visible light confronted by conventional photocatalyst.However,the life time of photogenerated hot electrons is too short to be efficiently used for various photocatalytic reactions.Here,we proposed a straightforward method to prolong the lifetime of photogenerated hot electrons from graphene by tuning the Schottky barrier at Gr/rutile interface to facilitate the hot electron injection.The rational design of Gr-coated TiO2 heterojunctions with interface synergy-induced decrease in the formation energy of the rutile phase makes the phase transfer of TiO2 support proceed smoothly and rapidly via ball milling.The optimized Gr/rutile dyad could provide a H2O2 yield of 1.05 mM·g-1·h-1 under visible light irradiation(λ≥400 nm),which is 30 times of the state-of-the-art noble-metal-free titanium oxide-based photocatalyst,and even achieves a H2O2 yield of 0.39 mM·g-1·h-1 on photoexcitation by near-infrared-region light(~800 nm).

仿植被可见光-近红外反射光谱特征的分散染料印花织物制备及其性能

针对传统仿植被印染伪装织物易出现“同色异谱”现象、印染工序复杂的问题,通过分散染料直接印花方法制备了可精确模拟常见绿色植被可见光-近红外(Vis-NIR)反射光谱特征的印花织物。研究了染料种类及含量、染料复配种类及比例、织物规格及含水量对涤纶印花织物Vis-NIR反射光谱特征的影响。通过计算印花织物与叶片反射光谱间的欧氏距离、光谱角和光谱相关系数,分析其仿植被Vis-NIR伪装性能,并测试其色牢度性能。结果表明:以240 g/m^(2)机织本白涤纶织物为基布,分散蓝NP-SBG、分散橙30、分散深蓝HGL复配质量比为2.5:2.0:1.1,含水量为120.9%时制备的印花织物,其光谱反射率曲线与绿色植被Vis-NIR反射光谱相似,与万年青叶片光谱曲线的欧氏距离为0.346,光谱角在400~780 nm波段为0.169°、在780~1350 nm波段为0.009°、在1450~1780 nm波段为0.094°、在2000~2350 nm波段为0.107°,光谱相关系数为0.997,达到一级高光谱伪装要求;同时该印花织物的褪色牢度、沾色牢度、耐干摩擦色牢度、耐湿摩擦色牢度均为5级,色牢度性能优异。

Estimation of soil organic matter in the Ogan-Kuqa River Oasis, Northwest China, based on visible and near-infrared spectroscopy and machine learning

Visible and near-infrared(vis-NIR)spectroscopy technique allows for fast and efficient determination of soil organic matter(SOM).However,a prior requirement for the vis-NIR spectroscopy technique to predict SOM is the effective removal of redundant information.Therefore,this study aims to select three wavelength selection strategies for obtaining the spectral response characteristics of SOM.The SOM content and spectral information of 110 soil samples from the Ogan-Kuqa River Oasis were measured under laboratory conditions in July 2017.Pearson correlation analysis was introduced to preselect spectral wavelengths from the preprocessed spectra that passed the 0.01 level significance test.The successive projection algorithm(SPA),competitive adaptive reweighted sampling(CARS),and Boruta algorithm were used to detect the optimal variables from the preselected wavelengths.Finally,partial least squares regression(PLSR)and random forest(RF)models combined with the optimal wavelengths were applied to develop a quantitative estimation model of the SOM content.The results demonstrate that the optimal variables selected were mainly located near the range of spectral absorption features(i.e.,1400.0,1900.0,and 2200.0 nm),and the CARS and Boruta algorithm also selected a few visible wavelengths located in the range of 480.0–510.0 nm.Both models can achieve a more satisfactory prediction of the SOM content,and the RF model had better accuracy than the PLSR model.The SOM content prediction model established by Boruta algorithm combined with the RF model performed best with 23 variables and the model achieved the coefficient of determination(R2)of 0.78 and the residual prediction deviation(RPD)of 2.38.The Boruta algorithm effectively removed redundant information and optimized the optimal wavelengths to improve the prediction accuracy of the estimated SOM content.Therefore,combining vis-NIR spectroscopy with machine learning to estimate SOM content is an important method to improve the accuracy of SOM prediction in arid land.

基于可见-近红外光谱技术的水稻穗颈瘟染病程度分级方法研究

采用Vis-NIR技术对水稻穗颈瘟染病程度分级方法进行了研究。分别基于原始光谱,变量标准化(SNV)预处理后和多元散射校正(MSC)预处理后的光谱,应用无信息变量消除法(UVE)结合连续投影算法(SPA)对Vis-NIR光谱区进行有效波长的选择。选择后的波长作为输入变量建立最小二乘-支持向量机(LS-SVM)模型。结果表明SNV-UVE-SPA建立的LS-SVM模型预测效果最好。通过SNV-UVE-SPA从全波段600个波长中选择了6个最能够反应光谱信息的波长(459,546,569,590,775和981nm)。SNV-UVE-SPA-LS-SVM组合模型对预测集样本预测得到的确定系数(Rp2),预测集的预测标准差(RMSEP)和剩余预测偏差(RPD)分别达到了0.979,0.507和6.580。结果表明,采用Vis-NIR光谱技术对水稻穗颈瘟染病程度进行分级是可行的。通过UVE-SPA得到的有效波长能够很好地代替全波长。