基于可见近红外光谱检测土壤养分及仪器开发
|
摘要
实施精细农业需要清晰地了解土壤的空间变异特性以及实时的营养状况,数字农业的发展也对土壤养分的测定迫切地提出了精确的时间和效率上的要求。土壤有机质、全氮、碱解氮、速效磷和速效钾是植物健康成长所必须的营养成分,这些土壤指标参数是土壤养分管理和测土配方施肥的重要对象,目前这些指标检测实验室和土肥站一直沿用常规检测方法。这些检测方法需要昂贵的检测设备和对检测人员要求较高,且存在指标检测效率低,检测样品数量小和成本高等问题,是实施精细农业管理的一个重要障碍因素。光谱分析技术作为一种快速、无损、简便的绿色测量方法和分析技术,在土壤养分的测定方面扮演着越来越重要的角色。近红外光谱检测技术具有一系列的优点,如快速、无需样品制备和成本低等优点。近红外光谱能够反映土壤如有机质和全氮等养分信息,使得近红外光谱检测技术在农业与农业环境检测中得到了广泛应用,近红外光谱检测能力主要依靠其对C-H、0-H和N-H功能键的能量吸收进而反映相应土壤养分含量等信息。土壤有机质、氮、磷、钾是农作物生长的主要养分,是土壤养分管理和测土配方施肥的重要对象,随着测土配方施肥技术的大规模推广,迫切需要一种低成本、可靠的土壤养分快速检测方法。
本文比较研究了多种不同建模方法对土壤养分检测效果,将获得的原始光谱数据用于进行主成分分析(PCA)得到的前6个主成分(PCs)和偏最小二乘回归(PLSR)建模得到的6个潜变量(LVs),分别作为BP传播神经网络(BPNN)和最小二乘支持向量机(LS-SVM)的输入,共建立了6个模型,分别为PCR、PLSR、BPNN-PCs、BPNN-LVs、LS-SVM-PCs和LS-SVM-LVs,对这些建模方法对预测的土壤有机质、碱解氮、速效磷和速效钾含量的结果进行评价,从中筛选出最佳模型。在预测土壤有机质、碱解氮、速效磷和速效钾时,LS-SVM-LVs模型优于PCR、PLSR、 BPNN-PCs、BPNN-LVs和LS-SVM-PCs模型。用LS-SVM-LVs模型得到的有机质、碱解氮、速效磷和速效钾预测集的决定系数和预测误差分别为0.8734,0.8310,0.7801,07353和2.92,16.49,4.97,13.42。
本文采用的光谱预处理包括标准正态变换(SNV),多元散射校正(MSC)和SG(Savitzky Golay)平滑结合一阶导数,以消除系统噪声和外部干扰,分别应用偏最小二乘回归(PLSR)和最小二乘支持向量机(LS-SVM)方法建立校正模型,LS-SVM回归方法规避了高维数据处理时须面对的众多问题,较好地解决了非线性和高维数等现实问题。最小二乘支持向量机(LS-SVM)输入分别包括主成分分析得到的主成分(PCs)、 PLSR建模得到的潜在变量(LVs)和由PLSR模型回归系数得到有效波长(EWs)。结果表明,三种输入的LS-SVM模型都优于PLS模型,其中EWs-LS-SVM模型最佳,碱解氮(N)的决定系数(R2)和预测均方误差RMSEP分别0.82和17.2,速效钾(K)为0.72和15.0。
由于采用原始光谱建模分析,数据量大,波长数多,本文探讨了多种特征波长提取方法,也称特征变量提取方法,如连续投影算法、遗传算法、无信息变量消除算法和有效波长提取方法等,并应用这些特征波长替代原始光谱进行建模分析,如为了提高模型分析方法的预测精度,研究了消除无信息建模变量对模型稳定性的影响,原始光谱平滑后采用蒙特卡罗无信息变量消除(Monte Carlo Uninformative Variables Elimination,MC-UVE)方法对土壤碱解氮(N)和速效钾(K)的建模变量进行筛选,应用偏最小二乘(PLS)方法建立校正模型。对于碱解氮(N)模型,采用MC-UVE-PLS方法,建模变量减少为210,碱解氮(N)的决定系数(R2)和预测均方误差RMSEP分别0.86和17.1。对于速效钾(K)的预测模型,采用MC-UVE方法后,建模变量减少为150,模型的预测决定系数为0.78,预测均方根误差为15.4。结果表明,利用可见光和短波近红外光谱(VIS/SW-NIR)(325-1075nm)结合MC-UVE方法可以有效的选择建模变量,能提高模型的稳定性,可以作为一个精确的土壤理化性质的测定方法。
遗传算法在分析测量土壤碱解氮(N)和速效钾(K)含量的应用情况,根据遗传算法优化结果提取到的特征波长替代原始光谱数据作为输入,应用最小二乘支持向量机(LS-SVM)方法建立校正模型,预测结果优于偏最小二乘(PLS)建模。应用遗传算法优化后建模变量由原来的751个全谱变量减少到17个特征变量,大大简化了模型复杂度,并提高了模型预测精度。碱解氮(N)的决定系数(R2)和预测均方误差RMSEP分别0.81和17.8,速效钾(K)为0.71和15.6。表明应用遗传算法提取特征波长,将提取到的特征波长作为LS-SVM模型的输入,建立预测模型,这种方法也可以作为一个精确的土壤理化性质的测定方法。
应用连续投影算法提取特征波长的方法,也是采用LS-SVM建模。分析过程是将原始光谱经平滑结合一阶微分预处理后,然后采集连续投影算法确定特征波长,作为建模集和预测集的光谱输入数据。发现采用基于连续投影算法得到的特征波长为输入的最小二乘支持向量机模型优于偏最小二乘回归法模型,连续投影算法从大量原始光谱数据中提取少数几列数据,高度概括了绝大多数样品光谱数据的有用信息,避免了信息重叠,同时去除了冗余信息,简化了模型。有机质的决定系数和预测均方误差分别0.8602和2.98,速效钾为0.7305和15.78。
对于土壤全氮养分,应用留一法交互验证偏最小二乘回归模型(PLSR)对三个不同地区土壤样本光谱数据(三个独立模型)和所有土壤样本光谱数据(通用模型)分别建立全氮预测模型,三个地区土壤样本全氮独立预测集的决定系数(R2)分别为0.81,0.70,0.31,剩余预测偏差(RPD)分别为3.01,2.09,1.08,均方根预测误差(RMSEP)为0.06,0.03,0.03,通用模型独立预测集的决定系数(R2)为0.72,剩余预测偏差(RPD)为2.23,均方根预测误差(RMSEP)为0.05。研究发现,全氮理化值分布区间越大,R2和RPD也越大,故通用模型检测结果优于汪家和昌东两个地区,且样本理化值标准偏差(standard deviation,SD)越大,模型决定系数(R2)和剩余预测偏差(RPD)也越大,但是模型的均方根预测误差(RMSEP)也越大。因此,建模选择样本时,应确保模型的均方根预测误差(RMSEP)值较小的条件下,应尽量选择理化值分布区间大的样本用于建模,这样得到的模型达到最优。
本文研究开发了一款应用近红外光谱分析技术、基于USB4000的便携式土壤养分(有机质)含量测定仪。便携式测定仪器由软件和硬件两部分组成。软件部分包括基于JAVA语言开发的土壤有机质含量检测软件以及USB4000底层驱动程序；硬件部分包括光源驱动电路、光纤、winCE开发板、便携式电源、触摸液晶显示电路和仪器机箱等组成。光源信号通过入射光纤传输到被测土壤表面,经过土壤发生漫反射,通过反射光纤传输到USB4000光谱仪得到土壤反射率值,软件系统获取这些反射率数据进行处理、显示、存储等处理,并土壤有机质含量结果显示在液晶显示屏上。
It is necessary for precision agriculture to understand the spatial-temporal variability and real-time nutritional status of soil. And the digital agriculture also requests that the soil nutrition detection should be timely and effective. Soil organic matter (OM), total nitrogen (TN), available nitrogen (N), available phosphorus (P), available potassium (K) are the main nutrients for crop growth, soil nutrient management and soil testing important objects. Conventional detection methods of these parameters are adopted by many laboratories and soil fertilizer manage station, these methods require expensive testing equipment and complex manual and have many disadvantages such as low efficiency, few samples and high cost problem, which hold back soil fertility management and the development of precision agriculture management. With large-scale promotion of fertilization technology, it is urgent for a low-cost and reliable method to rapidly detect soil nutrients. As a rapid, convenient, nondestructive and green technique, spectroscopy analysis becomes more and more important in the area of soil nutrition detecting. Near infrared spectroscopy technique offers a quick analysis, little sample preparation requirement, and low cost. They are highly sensitive to both organic and inorganic components of the soil, making their use in the agricultural and environmental sciences particularly appropriate. The analytical abilities of visible near infrared spectrum (Vis/NIRS) depend on the repetitive and broad absorption of Vis/NIRS light by C-H, O-H and N-H bonds.
Soil organic matter (OM), nitrogen (N), phosphorus (P) and potassium (K) are the main nutrients for crop growth, soil nutrient management and soil testing important objects. With large-scale promotion of fertilization technology, it is urgent for a low-cost and reliable method to rapidly detect soil nutrients.
Different calibration methods were used to detect the soil nutrition based on near infrared spectrum technology. Near infrared diffuse reflectance spectroscopy data of soil samples was used for the principal component analysis (PCA) to get the first six principal components (PCs), and PLSR mold was built to get six latent variables (LVs), respectively. PCR, PLSR, BPNN-PCs, BPNN-LVs, LS-SVM-PCs and LS-SVM-LVs modeling methods were built to predict the content of soil organic matter, available nitrogen, available P and available K. These modeling methods were evaluated respectively and selected the best model. The results showed that all LS-SVM-LVs models outperformed PCR, PLSR, BPNN-PCs, BPNN-LVs and LS-SVM-PCs models. The best predictions were obtained with LS-SVM-LVs model for OM (R2=0.8734and RMSEP=2.92), N (R2=0.7801and RMSEP=16.49), P (R2=0.7801and RMSEP=4.97) and K (R2=0.7353and RMSEP=13.42). The near-infrared diffuse reflectance spectroscopy based on LS-SVM combined with PLSR can be used for the measurement of soil organic matter, available N, available P and available K.
Near infrared diffuse reflectance spectroscopy was investigated for measurement accuracy of soil properties, namely, available nitrogen (N) and available potassium (K). Three types of pretreatments including standard normal variate (SNV), multiplicative scattering correction (MSC) and Savitzky-Golay smoothing+first derivative were adopted to eliminate the system noises and external disturbances. Then partial least squares (PLS) and least squares-support vector machine (LS-SVM) models analysis were implemented for calibration models, LS-SVM regression preferably solved the practical issues such as non-linearity, multi-dimension and so on. Simultaneously, the performance of least squares-support vector machine (LS-SVM) models was compared with three kinds of inputs, including PCA (PCs), latent variables (LVs), and effective wavelengths (EWs). The results indicated that all LS-SVM models outperformed PLS models. The performance of the model was evaluated by the determination coefficient (R2), RMSEP. The optimal EWs-LS-SVM models were achieved, and the determination coefficient (R2), RMSEP was0.82,17.2for N and0.72,15.0for K, respectively. The results indicated that visible and near infrared spectroscopy (Vis/NIRS)(325-1075nm) combined with LS-SVM could be utilized as a precision method for the determination of soil properties.
For the reason that using the raw spectra data has many drawbacks such as big data, too many wavelength, So this research studied some selecting characteristic wavelengths way to choose characteristic wavelength or characteristic variables, these ways includegenetic algorithm (GA), successive projections algorithm (SPA),uninformative variable elimination (UVE) and effective wavelengths (EWs) and so on. In order to improve the predictive precision, and eliminate the influence of uninformative variables for model robustness, Monte carlo uninformative variables elimination (MC-UVE) methods were proposed for variable selection in available nitrogen (N) and available potassium (K) spectral modeling.Partial least squares (PLS) models analysis were implemented for calibration models.The modeling variable number was reduced to210from751for available nitrogen (N) calibration model and150for available potassium (K) calibration model. The performance of the model was evaluated by the determination coefficient (R2), RMSEP. The optimal MC-UVE-PLS models were achieved, and the determination coefficient (R2), RMSEP were0.86,17.1for N and0.78,15.4for K, respectively.The results indicated that visible and near infrared spectroscopy (Vis/NIRS)(325-1075nm) combined with MC-UVE could be utilized as a precision method for the determination of soil properties.
The calibration was optimized by genetic algorithm (GA) in the wavelength range of325-1075nm. After optimizations, the sample number of calibration set decreased from751to17, then least squares-support vector machine (LS-SVM) models analysis were implemented for calibration models. Simultaneously, the performance of least squares-support vector machine (LS-SVM) models was compared with PLS models. The results indicated that LS-SVM models outperformed PLS models. The performance of the models was evaluated by the determination coefficient (R2), RMSEP. The optimal GA-LS-SVM models were achieved, and the determination coefficient (R2), RMSEP was0.81,17.8for N and0.71,15.6for K, respectively.The results indicated that visible and near infrared spectroscopy (Vis/NIRS)(325-1075nm) combined with LS-SVM based on GA could be utilized as a precision method for the determination of soil properties.
Successive projections algorithm (SPA) based on NIR was investigated in this study for measurement of soil organic matter (OM) and available potassium (K). Four types of pretreatments including smoothing, SNV, MSC and SG smoothing+first derivative were adopted to eliminate the system noises and external disturbances. Then partial least squares regression (PLSR) and least squares-support vector machine (LS-SVM) models analysis were implemented for calibration models. The LS-SVM model was built by using characteristic wavelength based on successive projections algorithm (SPA). Simultaneously, the performance of LS-SVM models was compared with PLSR models. The results indicated that LS-SVM models using characteristic wavelength as inputs based on SPA outperformed PLSR models. The optimal SPA-LS-SVM models were achieved, and the determination coefficient (R2), RMSEP were0.8602,2.98for OM and0.7305,15.78for K, respectively.
Spectra in the calibration set were subjected to partial least squares regression (PLSR) to establish calibration models of soil properties. Except for the Wangjia farm, individual farm models provided successful calibration result for total nitrogen (TN) with coefficient of determination (R2) of0.82-0.88and0.72-0.82and residual prediction deviation (RPD) of2.62-3.27and2.02-3.07for the calibration dataset and independent validation respectively. General calibration models gave improved prediction accuracies compared with models of farms in the Wangjia and Changdong, which was attributed to larger ranges in the variation of soil properties in general models compared with those in individual farm models. The results showed that larger standard deviations (SDs) and wider variation ranges have resulted in larger R2and RPD, meanwhile larger root mean square errors of prediction (RMSEP).Therefore, a compromise solution, which also results in small RMSEP values, soil samples should be selected for calibration to cover a wide variation range.
The soil organic matter detection instrument was based on NIRS technology including USB4000optical spectrum instrument. The instrument consisted of two parts, software section and hardware section. The software section included soil organic matter detection software based on JAVE language and USB4000driven program. The hardware section included lamp source driven circuit, Y type optical fiber, win CE development board, portable power, and touch liquid crystal display circuit and instrument box. Incident light signals was transmit through optical fiber to the measured soil surface, diffuse reflection data was caused from the soil surface through reflection optical fiber transmission to the USB4000spectrometer to obtain soil reflectance value, the software system for processing, display, storage and other processing.
本文比较研究了多种不同建模方法对土壤养分检测效果,将获得的原始光谱数据用于进行主成分分析(PCA)得到的前6个主成分(PCs)和偏最小二乘回归(PLSR)建模得到的6个潜变量(LVs),分别作为BP传播神经网络(BPNN)和最小二乘支持向量机(LS-SVM)的输入,共建立了6个模型,分别为PCR、PLSR、BPNN-PCs、BPNN-LVs、LS-SVM-PCs和LS-SVM-LVs,对这些建模方法对预测的土壤有机质、碱解氮、速效磷和速效钾含量的结果进行评价,从中筛选出最佳模型。在预测土壤有机质、碱解氮、速效磷和速效钾时,LS-SVM-LVs模型优于PCR、PLSR、 BPNN-PCs、BPNN-LVs和LS-SVM-PCs模型。用LS-SVM-LVs模型得到的有机质、碱解氮、速效磷和速效钾预测集的决定系数和预测误差分别为0.8734,0.8310,0.7801,07353和2.92,16.49,4.97,13.42。
本文采用的光谱预处理包括标准正态变换(SNV),多元散射校正(MSC)和SG(Savitzky Golay)平滑结合一阶导数,以消除系统噪声和外部干扰,分别应用偏最小二乘回归(PLSR)和最小二乘支持向量机(LS-SVM)方法建立校正模型,LS-SVM回归方法规避了高维数据处理时须面对的众多问题,较好地解决了非线性和高维数等现实问题。最小二乘支持向量机(LS-SVM)输入分别包括主成分分析得到的主成分(PCs)、 PLSR建模得到的潜在变量(LVs)和由PLSR模型回归系数得到有效波长(EWs)。结果表明,三种输入的LS-SVM模型都优于PLS模型,其中EWs-LS-SVM模型最佳,碱解氮(N)的决定系数(R2)和预测均方误差RMSEP分别0.82和17.2,速效钾(K)为0.72和15.0。
由于采用原始光谱建模分析,数据量大,波长数多,本文探讨了多种特征波长提取方法,也称特征变量提取方法,如连续投影算法、遗传算法、无信息变量消除算法和有效波长提取方法等,并应用这些特征波长替代原始光谱进行建模分析,如为了提高模型分析方法的预测精度,研究了消除无信息建模变量对模型稳定性的影响,原始光谱平滑后采用蒙特卡罗无信息变量消除(Monte Carlo Uninformative Variables Elimination,MC-UVE)方法对土壤碱解氮(N)和速效钾(K)的建模变量进行筛选,应用偏最小二乘(PLS)方法建立校正模型。对于碱解氮(N)模型,采用MC-UVE-PLS方法,建模变量减少为210,碱解氮(N)的决定系数(R2)和预测均方误差RMSEP分别0.86和17.1。对于速效钾(K)的预测模型,采用MC-UVE方法后,建模变量减少为150,模型的预测决定系数为0.78,预测均方根误差为15.4。结果表明,利用可见光和短波近红外光谱(VIS/SW-NIR)(325-1075nm)结合MC-UVE方法可以有效的选择建模变量,能提高模型的稳定性,可以作为一个精确的土壤理化性质的测定方法。
遗传算法在分析测量土壤碱解氮(N)和速效钾(K)含量的应用情况,根据遗传算法优化结果提取到的特征波长替代原始光谱数据作为输入,应用最小二乘支持向量机(LS-SVM)方法建立校正模型,预测结果优于偏最小二乘(PLS)建模。应用遗传算法优化后建模变量由原来的751个全谱变量减少到17个特征变量,大大简化了模型复杂度,并提高了模型预测精度。碱解氮(N)的决定系数(R2)和预测均方误差RMSEP分别0.81和17.8,速效钾(K)为0.71和15.6。表明应用遗传算法提取特征波长,将提取到的特征波长作为LS-SVM模型的输入,建立预测模型,这种方法也可以作为一个精确的土壤理化性质的测定方法。
应用连续投影算法提取特征波长的方法,也是采用LS-SVM建模。分析过程是将原始光谱经平滑结合一阶微分预处理后,然后采集连续投影算法确定特征波长,作为建模集和预测集的光谱输入数据。发现采用基于连续投影算法得到的特征波长为输入的最小二乘支持向量机模型优于偏最小二乘回归法模型,连续投影算法从大量原始光谱数据中提取少数几列数据,高度概括了绝大多数样品光谱数据的有用信息,避免了信息重叠,同时去除了冗余信息,简化了模型。有机质的决定系数和预测均方误差分别0.8602和2.98,速效钾为0.7305和15.78。
对于土壤全氮养分,应用留一法交互验证偏最小二乘回归模型(PLSR)对三个不同地区土壤样本光谱数据(三个独立模型)和所有土壤样本光谱数据(通用模型)分别建立全氮预测模型,三个地区土壤样本全氮独立预测集的决定系数(R2)分别为0.81,0.70,0.31,剩余预测偏差(RPD)分别为3.01,2.09,1.08,均方根预测误差(RMSEP)为0.06,0.03,0.03,通用模型独立预测集的决定系数(R2)为0.72,剩余预测偏差(RPD)为2.23,均方根预测误差(RMSEP)为0.05。研究发现,全氮理化值分布区间越大,R2和RPD也越大,故通用模型检测结果优于汪家和昌东两个地区,且样本理化值标准偏差(standard deviation,SD)越大,模型决定系数(R2)和剩余预测偏差(RPD)也越大,但是模型的均方根预测误差(RMSEP)也越大。因此,建模选择样本时,应确保模型的均方根预测误差(RMSEP)值较小的条件下,应尽量选择理化值分布区间大的样本用于建模,这样得到的模型达到最优。
本文研究开发了一款应用近红外光谱分析技术、基于USB4000的便携式土壤养分(有机质)含量测定仪。便携式测定仪器由软件和硬件两部分组成。软件部分包括基于JAVA语言开发的土壤有机质含量检测软件以及USB4000底层驱动程序；硬件部分包括光源驱动电路、光纤、winCE开发板、便携式电源、触摸液晶显示电路和仪器机箱等组成。光源信号通过入射光纤传输到被测土壤表面,经过土壤发生漫反射,通过反射光纤传输到USB4000光谱仪得到土壤反射率值,软件系统获取这些反射率数据进行处理、显示、存储等处理,并土壤有机质含量结果显示在液晶显示屏上。
It is necessary for precision agriculture to understand the spatial-temporal variability and real-time nutritional status of soil. And the digital agriculture also requests that the soil nutrition detection should be timely and effective. Soil organic matter (OM), total nitrogen (TN), available nitrogen (N), available phosphorus (P), available potassium (K) are the main nutrients for crop growth, soil nutrient management and soil testing important objects. Conventional detection methods of these parameters are adopted by many laboratories and soil fertilizer manage station, these methods require expensive testing equipment and complex manual and have many disadvantages such as low efficiency, few samples and high cost problem, which hold back soil fertility management and the development of precision agriculture management. With large-scale promotion of fertilization technology, it is urgent for a low-cost and reliable method to rapidly detect soil nutrients. As a rapid, convenient, nondestructive and green technique, spectroscopy analysis becomes more and more important in the area of soil nutrition detecting. Near infrared spectroscopy technique offers a quick analysis, little sample preparation requirement, and low cost. They are highly sensitive to both organic and inorganic components of the soil, making their use in the agricultural and environmental sciences particularly appropriate. The analytical abilities of visible near infrared spectrum (Vis/NIRS) depend on the repetitive and broad absorption of Vis/NIRS light by C-H, O-H and N-H bonds.
Soil organic matter (OM), nitrogen (N), phosphorus (P) and potassium (K) are the main nutrients for crop growth, soil nutrient management and soil testing important objects. With large-scale promotion of fertilization technology, it is urgent for a low-cost and reliable method to rapidly detect soil nutrients.
Different calibration methods were used to detect the soil nutrition based on near infrared spectrum technology. Near infrared diffuse reflectance spectroscopy data of soil samples was used for the principal component analysis (PCA) to get the first six principal components (PCs), and PLSR mold was built to get six latent variables (LVs), respectively. PCR, PLSR, BPNN-PCs, BPNN-LVs, LS-SVM-PCs and LS-SVM-LVs modeling methods were built to predict the content of soil organic matter, available nitrogen, available P and available K. These modeling methods were evaluated respectively and selected the best model. The results showed that all LS-SVM-LVs models outperformed PCR, PLSR, BPNN-PCs, BPNN-LVs and LS-SVM-PCs models. The best predictions were obtained with LS-SVM-LVs model for OM (R2=0.8734and RMSEP=2.92), N (R2=0.7801and RMSEP=16.49), P (R2=0.7801and RMSEP=4.97) and K (R2=0.7353and RMSEP=13.42). The near-infrared diffuse reflectance spectroscopy based on LS-SVM combined with PLSR can be used for the measurement of soil organic matter, available N, available P and available K.
Near infrared diffuse reflectance spectroscopy was investigated for measurement accuracy of soil properties, namely, available nitrogen (N) and available potassium (K). Three types of pretreatments including standard normal variate (SNV), multiplicative scattering correction (MSC) and Savitzky-Golay smoothing+first derivative were adopted to eliminate the system noises and external disturbances. Then partial least squares (PLS) and least squares-support vector machine (LS-SVM) models analysis were implemented for calibration models, LS-SVM regression preferably solved the practical issues such as non-linearity, multi-dimension and so on. Simultaneously, the performance of least squares-support vector machine (LS-SVM) models was compared with three kinds of inputs, including PCA (PCs), latent variables (LVs), and effective wavelengths (EWs). The results indicated that all LS-SVM models outperformed PLS models. The performance of the model was evaluated by the determination coefficient (R2), RMSEP. The optimal EWs-LS-SVM models were achieved, and the determination coefficient (R2), RMSEP was0.82,17.2for N and0.72,15.0for K, respectively. The results indicated that visible and near infrared spectroscopy (Vis/NIRS)(325-1075nm) combined with LS-SVM could be utilized as a precision method for the determination of soil properties.
For the reason that using the raw spectra data has many drawbacks such as big data, too many wavelength, So this research studied some selecting characteristic wavelengths way to choose characteristic wavelength or characteristic variables, these ways includegenetic algorithm (GA), successive projections algorithm (SPA),uninformative variable elimination (UVE) and effective wavelengths (EWs) and so on. In order to improve the predictive precision, and eliminate the influence of uninformative variables for model robustness, Monte carlo uninformative variables elimination (MC-UVE) methods were proposed for variable selection in available nitrogen (N) and available potassium (K) spectral modeling.Partial least squares (PLS) models analysis were implemented for calibration models.The modeling variable number was reduced to210from751for available nitrogen (N) calibration model and150for available potassium (K) calibration model. The performance of the model was evaluated by the determination coefficient (R2), RMSEP. The optimal MC-UVE-PLS models were achieved, and the determination coefficient (R2), RMSEP were0.86,17.1for N and0.78,15.4for K, respectively.The results indicated that visible and near infrared spectroscopy (Vis/NIRS)(325-1075nm) combined with MC-UVE could be utilized as a precision method for the determination of soil properties.
The calibration was optimized by genetic algorithm (GA) in the wavelength range of325-1075nm. After optimizations, the sample number of calibration set decreased from751to17, then least squares-support vector machine (LS-SVM) models analysis were implemented for calibration models. Simultaneously, the performance of least squares-support vector machine (LS-SVM) models was compared with PLS models. The results indicated that LS-SVM models outperformed PLS models. The performance of the models was evaluated by the determination coefficient (R2), RMSEP. The optimal GA-LS-SVM models were achieved, and the determination coefficient (R2), RMSEP was0.81,17.8for N and0.71,15.6for K, respectively.The results indicated that visible and near infrared spectroscopy (Vis/NIRS)(325-1075nm) combined with LS-SVM based on GA could be utilized as a precision method for the determination of soil properties.
Successive projections algorithm (SPA) based on NIR was investigated in this study for measurement of soil organic matter (OM) and available potassium (K). Four types of pretreatments including smoothing, SNV, MSC and SG smoothing+first derivative were adopted to eliminate the system noises and external disturbances. Then partial least squares regression (PLSR) and least squares-support vector machine (LS-SVM) models analysis were implemented for calibration models. The LS-SVM model was built by using characteristic wavelength based on successive projections algorithm (SPA). Simultaneously, the performance of LS-SVM models was compared with PLSR models. The results indicated that LS-SVM models using characteristic wavelength as inputs based on SPA outperformed PLSR models. The optimal SPA-LS-SVM models were achieved, and the determination coefficient (R2), RMSEP were0.8602,2.98for OM and0.7305,15.78for K, respectively.
Spectra in the calibration set were subjected to partial least squares regression (PLSR) to establish calibration models of soil properties. Except for the Wangjia farm, individual farm models provided successful calibration result for total nitrogen (TN) with coefficient of determination (R2) of0.82-0.88and0.72-0.82and residual prediction deviation (RPD) of2.62-3.27and2.02-3.07for the calibration dataset and independent validation respectively. General calibration models gave improved prediction accuracies compared with models of farms in the Wangjia and Changdong, which was attributed to larger ranges in the variation of soil properties in general models compared with those in individual farm models. The results showed that larger standard deviations (SDs) and wider variation ranges have resulted in larger R2and RPD, meanwhile larger root mean square errors of prediction (RMSEP).Therefore, a compromise solution, which also results in small RMSEP values, soil samples should be selected for calibration to cover a wide variation range.
The soil organic matter detection instrument was based on NIRS technology including USB4000optical spectrum instrument. The instrument consisted of two parts, software section and hardware section. The software section included soil organic matter detection software based on JAVE language and USB4000driven program. The hardware section included lamp source driven circuit, Y type optical fiber, win CE development board, portable power, and touch liquid crystal display circuit and instrument box. Incident light signals was transmit through optical fiber to the measured soil surface, diffuse reflection data was caused from the soil surface through reflection optical fiber transmission to the USB4000spectrometer to obtain soil reflectance value, the software system for processing, display, storage and other processing.
引文
[1]沈掌泉,卢必慧,单英杰,等.基于变量选择的偏最小二乘回归法和田间行走式近红外光谱进行土壤碳含量测定研究[J].光谱学与光谱分析.2013(07)：1775-1780.
[2]田永超,张娟娟,姚霞,等.基于近红外光声光谱的土壤有机质含量定量建模方法[J].农业工程学报.2012(1)：145-152.
[3]刘磊，沈润平,丁国香.基于高光谱的土壤有机质含量估算研究[J].光谱学与光谱分析.2011(3)：762-766.
[4]高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤全氮近红外特征波长的选取[J].光谱学与光谱分析.2009(11)：2951-2954.
[5]王艳艳.基于不同土质土壤的光谱特性及快速分析仪的研究[D].浙江大学,2007.
[6]李颉.土壤养分的近红外光谱快速分析系统开发与实验研究[D].中国农业机械化科学研究院,2011.
[7]李庆波.近红外光谱分析中若干关键技术的研究[D].天津大学,2003.
[8]刘蓉.近红外光谱分析中模型优化方法的初步研究[D].天津大学,2003.
[9]武子玉.矿物近红外光谱信息提取及应用研究[D].吉林大学,2005.
[10]Liang X Y, Li X Y, Lei T W, et al. Study of sample temperature compensation in the measurement of soil moisture content[J]. Measurement.2011,44(10):2200-2204.
[11]Summers D, Lewis M, Ostendorf B, et al. Visible near-infrared reflectance spectroscopy as a predictive indicator of soil properties[J]. Ecological Indicators.2011,11(1):123-131.
[12]B Kuang A M M. Calibration of visible and near infrared spectroscopy for soil analysis at the field scale on three European farms[J]. European Journal of Soil Science.2011,62:629-636.
[13]Chang C W, Laird D A, Mausbach M J, et al. Near-infrared reflectance spectroscopy-principal components regression analyses of soil properties[J]. Soil Science Society of America Journal.2001,65(2): 480-490.
[14]Mouazen A M, Kuang B, De Baerdemaeker J, et al. Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy[J]. Geoderma.2010,158(1-2SI):23-31.
[15]Bernard G. Barthes D A N. Determination of potential denitrification in arange of tropical topsoils using near infrared reflectance spectroscopy(NIRS)[J]. AppliedSoilEcology.2010,46:81-89.
[16]Rossel R, Behrens T. Using data mining to model and interpret soil diffuse reflectance spectra[J]. Geoderma.2010,158(1-2SI):46-54.
[17]Bilgili A V, van Es H M, Akbas F, et al. Visible-near infrared reflectance spectroscopy for assessment of soil properties in a semi-arid area of Turkey[J]. Journal of Arid Environments.2010,74(2):229-238.
[1 8]李颉,张小超,苑严伟,等.北京典型耕作土壤养分的近红外光谱分析[J].农业工程学报.2012(02)：176-179.
[19]O'Rourke S M, Holden N M. Determination of Soil Organic Matter and Carbon Fractions in Forest Top Soils using Spectral Data Acquired from Visible-Near Infrared Hyperspectral lmages[J]. Soil Science Society of America Journal.2012,76(2):586-596.
[20]Cecillon L, Certini G, Lange H, et al. Spectral fingerprinting of soil organic matter composition[JJ. Organic Geochemistry.2012,46:127-136.
[21]Chen H Z, Pan T, Chen J M, et al. Waveband selection for NIR spectroscopy analysis of soil organic matter based on SG smoothing and MWPLS methods[J]. Chemometrics and Intelligent Laboratory Systems. 2011,107(1):139-146.
[22]Hummel J W, Sudduth K A, Hollinger S E. Soil moisture and organic matter prediction of surface and subsurface soils using an NIR soil sensor[J]. Computers and Electronics in Agriculture.2001,32(2): 149-165.
[23]Bendor E, Inbar Y, Chen Y. The reflectance spectra of organic matter in the visible near-infrared and short wave infrared region (400-2500 nm) during a controlled decomposition process[J]. REMOTE SENSING OF ENVIRONMENT.1997,61(1):1-15.
[24]Kuang B Y, Mouazen A M. Non-biased prediction of soil organic carbon and total nitrogen with vis-NIR spectroscopy, as affected by soil moisture content and texture[J]. BIOSYSTEMS ENGINEERING. 2013,114(3):249-258.
[25]Yang X M, Xie H T, Drury C F, et al. Determination of organic carbon and nitrogen in particulate organic matter and particle size fractions of Brookston clay loam soil using infrared spectroscopy[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(2):177-188.
[26]Vohland M, Besold J, Hill J, et al. Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy [J]. Geoderma.2011, 166(1):198-205.
[27]Nocita M, Kooistra L, Bachmann M, et al. Predictions of soil surface and topsoil organic carbon content through the use of laboratory and field spectroscopy in the Albany Thicket Biome of Eastern Cape Province of South Africa[J]. Geoderma.2011,167-68:295-302.
[28]Stumpe B, Weihermuller L, Marschner B. Sample preparation and selection for qualitative and quantitative analyses of soil organic carbon with mid-infrared reflectance spectroscopy [J]. European Journal of Soil Science.2011,62(6):849-862.
[29]Mcdowell M L, Bruland G L, Deenik J L, et al. Soil total carbon analysis in Hawaiian soils with visible, near-infrared and mid-infrared diffuse reflectance spectroscopy [J]. GEODERMA.2012,189: 312-320.
[30]Sarkhot D V, Grunwald S, Ge Y, et al. Comparison and detection of total and available soil carbon fractions using visible/near infrared diffuse reflectance spectroscopy[J]. Geoderma.2011,164(1-2):22-32.
[31]Vohland M, Emmerling C. Determination of total soil organic C and hot water-extractable C from VIS-NIR soil reflectance with partial least squares regression and spectral feature selection techniques[J]. European Journal of Soil Science.2011,62(4):598-606.
[32]Klaus V H, Kleinebecker T, Boch S, et al. NIRS meets Ellenberg's indicator values:Prediction of moisture and nitrogen values of agricultural grassland vegetation by means of near-infrared spectral characteristics[J]. Ecological Indicators.2012,14(1):82-86.
[33]Shi T Z, Cui L J, Wang J J, et al. Comparison of multivariate methods for estimating soil total nitrogen with visible/near-infrared spectroscopy[J]. PLANT AND SOIL.2013,366(1-2):363-375.
[34]Aitkenhead M J, Coull M C, Towers W, et al. Predicting soil chemical composition and other soil parameters from field observations using a neural network[J]. Computers and Electronics in Agriculture. 2012,82:108-116.
[35]H. Yang B K A M. Quantitative analysis of soil nitrogen and carbon at a farm scale using visible and near infrared spectroscopy coupled with wavelength reduction[J]. European Journal of Soil Science.2012, 63:410-420.
[36]Yang H, Kuang B, Mouazen A M. Quantitative analysis of soil nitrogen and carbon at a farm scale using visible and near infrared spectroscopy coupled with wavelength reduction[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(3):410-420.
[37]Piekarczyk J, Kazmierowski C, Krolewicz S. Relationships between soil properties of the abandoned fields and spectral data derived from the advanced spaceborne thermal emission and reflection radiometer (ASTER)[J]. Advances in Space Research.2012,49(2):280-291.
[38]Xie Xian-Li P X S B. Visible and Near-Infrared Diffuse Reflectance Spectroscopy for Prediction of Soil Properties near a Copper Smelter[J]. Pedosphere.2012,22(3):351-366.
[39]Rossel R, Webster R. Predicting soil properties from the Australian soil visible-near infrared spectroscopic database[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(6):848-860.
[40]Dong Y W, Yang S Q, Xu C Y, et al. Determination of Soil Parameters in Apple-Growing Regions by Near-and Mid-Infrared Spectroscopy[J]. PEDOSPHERE.2011,21(5):591-602.
[41]宋海燕.基于光谱技术的土壤、作物信息获取及其相互关系的研究[D].浙江大学,2006.
[42]Shao Y N, He Y. Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research.2011,49(2):166-172.
[43]占细雄.光栅分光型乙醇汽油近红外光谱分析关键技术研究[D].吉林大学,2008.
[44]李民赞,郑立华,安晓飞,等.土壤成分与特性参数光谱快速检测方法及传感技术[J].农业机械学报.2013(03)：73-87.
[45]李民赞,潘娈,郑立华,等.基于近红外漫反射测量的便携式土壤有机质测定仪的开发[J].光谱学与光谱分析.2010(4)：1146-1150.
[46]杨玮,Sigrimis Nick,李民赞.基于多光谱图像分析的温室黄瓜叶片营养元素检测与诊断[J].光谱学与光谱分析.2010(1)：210-213.
[47]车艳双,李民赞,郑立华,等.基于GPS和PDA的移动智能农田信息采集系统开发[J].农业工程学报.2010(S2)：109-114.
[48]郑立华,李民赞,孙红.基于近红外光谱的土壤参数快速分析系统[J].光谱学与光谱分析.2009(10)：2633-2636.
[49]郑立华,李民赞，潘娈,等.近红外光谱小波分析在土壤参数预测中的应用[J].光谱学与光谱分析.2009(6)：1549-1552.
[50]冀荣华,吴才聪,李民赞,等.基于远程通讯的农田信息管理系统设计与实现[J].农业工程学报.2009(S2)：165-169.
[51]郑立华,李民赞,潘娈,等.基于近红外光谱技术的土壤参数BP神经网络预测[J].光谱学与光谱分析.2008(5)：1160-1164.
[52]孙建英,李民赞,唐宁,等.东北黑土的光谱特性及其与土壤参数的相关性分析[J].光谱学与光谱分析.2007(8)：1502-1505.
[53]孙建英,李民赞,郑立华,等.基于近红外光谱的北方潮土土壤参数实时分析[J].光谱学与光谱分析.2006(3)：426-429.
[54]岑益郎,宋韬,何勇,等.基于可见/近红外漫反射光谱的土壤有机质含量估算方法研究[J].浙江大学学报(农业与生命科学版).2011(3).
[55]蒋璐璐,张瑜,王艳艳,等.基于光谱技术的土壤养分快速测试方法研究[J].浙江大学学报(农业与生命科学版).2010(4)：445-450.
[56]韩瑞珍,宋韬,何勇.基于可见/近红外光谱的士壤有机质含量预测[J].中国科学：信息科学.2010(S1)：111-116.
[57]宋韬,鲍一丹,何勇.利用光谱数据快速检测士壤含水量的方法研究[J].光谱学与光谱分析.2009(3)：675-677.
[58]袁石林,马天云,宋韬,等.土壤中全氮与总磷含量的近红外光谱实时检测方法[J].农业机械学报.2009(S1)：150-153.
[59]袁石林,马天云,宋韬,等.土壤中全氮与总磷含量的近红外光谱实时检测方法[J].农业机械学报.2009(S1)：150-153.
[60]宋海燕,何勇.近红外光谱法分析土壤中磷,钾含量及pH值的研究[J].山西农业大学学报：自然科学版.2008,28(3)：275-278.
[61]朱登胜,吴迪,宋海燕,等.应用近红外光谱法测定土壤的有机质和pH值[J].农业工程学报.2008(6)：196-199.
[62]宋海燕,何勇.基于OSC和PLS的土壤有机质近红外光谱测定[J].农业机械学报.2007(12)： 113-115.
[63]鲍一丹,何勇,方慧,等.十壤的光谱特征及氮含量的预测研究[J].光谱学与光谱分析.2007(1)：62-65.
[64]李颉,张小超,苑严伟,等.北京典型耕作土壤养分的近红外光谱分析[J].农业工程学报.2012(2)：176-179.
[65]卢艳丽,白由路,王磊，等.黑上土壤中全氮含量的高光谱预测分析[J].农业工程学报.2010(1)：256-261.
[66]卢艳丽,白由路,杨俐苹,等.基于主成分回归分析的土壤有机质高光谱预测与模型验证[J].植物营养与肥料学报.2008(6)：1076-1082.
[67]卢艳丽,白山路,杨俐苹,等.基于高光谱的土壤有机质含量预测模型的建立与评价[J].中国农业科学.2007(9)：1989-1995.
[68]陈民森.近红外光谱扣除背景误差的研究[D].天津大学,2005.
[69]邹婷婷.支持向量机回归—近红外光谱法用于药物无损非破坏定量分析的研究[D].吉林大学,2008.
[70]窦英.人工神经网络—近红外光谱法用于药物无损非破坏定量分析的研究[Dl.吉林大学,2006.
[1]郝勇,孙旭东,王豪.基于改进连续投影算法的光谱定量模型优化[J].江苏大学学报(自然科学版).2013(1)：49-53.
[2]吴迪,吴洪喜,蔡景波,等.基于无信息变量消除法和连续投影算法的可见-近红外光谱技术自虾种分类方法研究[J].红外与毫米波学报.2009(6)：423-427.
[3]刘飞,张帆,方慧,等.连续投影算法在油菜叶片氨基酸总量无损检测中的应用[J].光谱学与光谱分析.2009(11)：3079-3083.
[4]吴迪,金春华,何勇.基于连续投影算法的光谱主成分组合优化方法研究[J].光谱学与光谱分 析.2009(10)：2734-2737.
[5]吴迪,吴洪喜,蔡景波,等.基于无信息变量消除法和连续投影算法的可见-近红外光谱技术白虾种分类方法研究[J].红外与毫米波学报.2009(6)：423-427.
[6]成忠,张立庆,刘赫扬,等.连续投影算法及其在小麦近红外光谱波长选择中的应用[J].光谱学与光谱分析.2010(4)：949-952.
[7]高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤全氮近红外特征波长的选取[J].光谱学与光谱分析.2009(11)：2951-2954.
[8]钱海波,孙来军,王乐凯,等.基于连续投影算法的小麦湿面筋近红外校正模型优化[J].中国农学通报.2011(18)：51-56.
[9]刘雪梅,柳建设.基于MC-UVE的土壤碱解氮和速效钾近红外光谱检测[J].农业机械学报.2013(03)：88-91.
[10]郝勇,孙旭东,潘圆媛,等.蒙特卡罗无信息变量消除方法用于近红外光谱预测果品硬度和表面色泽的研究[J].光谱学与光谱分析.20１](5)：1225-1229.
[11]刘雪梅,章海亮.基于遗传算法近红外光谱检测土壤养分的研究[J].灌溉排水学报.2013(02)：138-141.
[12]马世榜,汤修映,徐杨,等.可见/近红外光谱结合遗传算法无损检测牛肉pH值[J].农业工程学报.2012(18)：263-268.
[13]刘振华,赵英时.基于遗传算法的不同光照条件下植被和土壤组分温度反演[J].农业工程学报.2012(01)：161-166.
[14]孙珂,陈圣波.基于遗传算法综合Terra/Aqua MODIS热红外数据反演地表组分温度[J].红外与毫米波学报.2012(05)：462468.
[15]陈天恩,董静,陈立平,等.县域农田土壤采样布局多目标优化分析模型[J].农业工程学报.2012(23)：67-73.
[16]杨海清,姚建松,何勇.基于反射光谱技术的植物叶片SPAD值预测建模方法研究[J].光谱学与光谱分析.2009(06]：1607-1610.
[171史波林，庆兆坤,籍保平,等.应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究[J].光谱学与光谱分析.2009(03)：665-670.
[18]王加华,韩东海.基于遗传算法的苹果糖度近红外光谱分析[J].光谱学与光谱分析.2008(10)：2308-2311.
[19]邹小波,赵杰文.用遗传算法快速提取近红外光谱特征区域和特征波长[J].光学学报.2007(07)：1316-1321.
[20]祝诗平,王一鸣,张小超,等.基于遗传算法的近红外光谱谱区选择方法[J].农业机械学报.2004(05)：152-156.
[21]卢艳丽,白由路,杨俐苹,等.基于主成分回归分析的土壤有机质高光谱预测与模型验证[J].植物营养与肥料学报.2008(6)：1076-1082.
[22]宋海燕,何勇.基于OSC和PLS的土壤有机质近红外光谱测定[J].农业机械学报.2007(12)：113-115.
[23]Shao Y N, He Y. Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research.2011,49(2):166-172.
[24]陈双双.基于光谱和多源波谱成像技术的植物灰霉病快速识别的方法研究[D].浙江大学,2012.
[25]余凡,赵英时,李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报.2012(03)：283-288.
[26]韩瑞珍,宋韬,何勇.基于可见/近红外光谱的土壤有机质含量预测[J].中国科学：信息科学.2010(S1)：111-116.
[27]张娟娟,田永超,朱艳,等.不同类型土壤的光谱特征及其有机质含量预测[J].中国农业科学.2009(9)：3154-3163.
[28]朱继文,刘丹丹.基于高光谱数据的土壤含盐量BP神经网络模型研究[J].东北农业大学学报.2009(10)：115-118.
[29]张淑娟,王凤花,张海红,等.基于主成分分析和BP神经网络的十壤养分近红外光谱检测[J].山西农业大学学报(自然科学版).2009(6)：483-487.
[30]郑立华，李民赞,潘娈,等.基于近红外光谱技术的十壤参数BP神经网络预测[J].光谱学与光谱分析.2008(5)：1160-1164.
[31]Wu D, Yang H, Chen X, et al. Application of image texture for the sorting of tea categories using multi-spectral imaging technique and support vector machine[J]. Journal of Food Engineering.2008.88(4): 474-483.
[1]刘雪梅,柳建设.基于LS-SVM建模方法近红外光谱检测土壤速效N和速效K的研究[J].光谱学与光谱分析.2012(11)：3019-3023.
[2]杨莲.受控实验下沿着水分梯度止相互作用和负相互作用间平衡的变化[D].兰州大学,2007.
[3]刘雪梅,章海亮.基于近红外光谱的不同建模方法检测土壤有机质和速效P含量的研究[J].西北农林科技大学学报(自然科学版).2013(04)：52-56.
[4]刘雪梅.近红外漫反射光谱检测土壤有机质和速效N的研究[J].中国农机化学报.2013(02)：202-206.
[5]田永超,张娟娟,姚霞,等.基于近红外光声光谱的土壤有机质含量定量建模方法[J].农业工程学报.2012(1)：145-152.
[6]刘炜,常庆瑞,郭曼,等.不同尺度的微分窗口下土壤有机质的一阶导数光谱响应特征分析[J].红外与毫米波学报.2011(4)：316-321.
[7]刘磊，沈润平,丁国香.基于高光谱的土壤有机质含量估算研究[J].光谱学与光谱分析.2011(3)：762-766.
[8]岑益郎,宋韬,何勇,等.基于可见/近红外漫反射光谱的土壤有机质含量估算方法研究[J].浙江大学学报(农业与生命科学版).2011(3).
[9]王淼,解宪丽,周睿,等.基于可见光-近红外漫反射光谱的红壤有机质预测及其最优波段选择[J].土壤学报.2011(5)：1083-1089.
[10]徐明星,周生路,丁卫,等.苏北沿海滩涂地区土壤有机质含量的高光谱预测[J].农业工程学报.2011(2)：219-223.
[11]刘炜,常庆瑞,郭曼,等.土壤导数光谱小波去噪与有机质吸收特征提取[J].光谱学与光谱分析.2011(1)：100-104.
[12]李民赞,潘娈,郑立华,等.基于近红外漫反射测量的便携式土壤有机质测定仪的开发[J].光谱学与光谱分析.2010(4)：1146-1150.
[13]韩瑞珍,宋韬,何勇.基于可见/近红外光谱的土壤有机质含量预测[J].中国科学：信息科学.2010(S1)：111-116.
[14]Shi T Z, Cui L J, Wang J J, et al. Comparison of multivariate methods for estimating soil total nitrogen with visible/near-infrared spectroscopy[J]. PLANT AND SOIL.2013,366(1-2):363-375.
[15]Xue S, Zhao Q L, Wei L L, et al. Fluorescence spectroscopic characterization of dissolved organic matter fractions in soils in soil aquifer treatment[J]. ENVIRONMENTAL MONITORING AND ASSESSMENT.2013,185(6):4591-4603.
[16]Collins A L, Williams L J, Zhang Y S, et al. Catchment source contributions to the sediment-bound organic matter degrading salmonid spawning gravels in a lowland river, southern England[J]. SCIENCE OF THE TOTAL ENVIRONMENT.2013,456:181-195.
[17]O'Rourke S M, Holden N M. Determination of Soil Organic Matter and Carbon Fractions in Forest Top Soils using Spectral Data Acquired from Visible-Near Infrared Hyperspectral Images[J]. Soil Science Society of America Journal.2012,76(2):586-596.
[18]Cecillon L, Certini G, Lange H, et al. Spectral fingerprinting of soil organic matter composition[J]. Organic Geochemistry.2012,46:127-136.
[19]Yang X M, Xie H T, Drury C F, et al. Determination of organic carbon and nitrogen in particulate organic matter and particle size fractions of Brookston clay loam soil using infrared spectroscopy[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(2):177-188.
[20]Chen H Z, Pan T, Chen J M, et al. Waveband selection for NIR spectroscopy analysis of soil organic matter based on SG smoothing and MWPLS methods[J]. Chemometrics and Intelligent Laboratory Systems.2011,107(1):139-146.
[21]郑立华,李民赞,潘娈,等.近红外光谱小波分析在土壤参数预测中的应用[J].光谱学与光谱分析.2009(6)：1549-1552.
[22]Cozzolino D, Moron A. Potential of near-infrared reflectance spectroscopy and chemometrics to predict soil organic carbon fractions[J]. Soil & Tillage Research.2006,85(1-2):78-85.
[23]Hummel J W, Sudduth K A, Hollinger S E. Soil moisture and organic matter prediction of surface and subsurface soils using an NIR soil sensor[J]. Computers and Electronics in Agriculture.2001, 32(2):149-165.
[24]Bendor E, Inbar Y, Chen Y. The reflectance spectra of organic matter in the visible near-infrared and short wave infrared region (400-2500 nm) during a controlled decomposition process[J]. REMOTE SENSING OF ENVIRONMENT.1997,61(1):1-15.
[25]郝勇,孙旭东,王豪.基于改进连续投影算法的光谱定量模型优化[J].江苏大学学报(自然科学版).2013(1)：49-53.
[26]李水芳,单杨,尹永,等.基于连续投影算法的油菜蜜近红外光谱真伪鉴别的研究[J].食品工业科技.2012(4)：89-91.
[27]吴迪,吴洪喜,蔡景波,等.基于无信息变量消除法和连续投影算法的可见-近红外光谱技术白虾种分类方法研究[J].红外与毫米波学报.2009(6)：423-427.
[28]刘飞,张帆,方慧，等.连续投影算法在油菜叶片氨基酸总量无损检测中的应用[J].光谱学与光谱分析.2009(11)：3079-3083.
[29]刘磊,沈润平,丁国香.基于高光谱的土壤有机质含量估算研究[J].光谱学与光谱分析.2011(03)：762-766.
[30]刘雪梅,章海亮.基于DPLS和LS-SVM的梨品种近红外光谱识别[J].农业机械学报.2012(9)：160-164.
[31]吴迪,曹芳,冯水娟,等.基于支持向量机算法的红外光谱技术在奶粉蛋白质含量快速检测中的应用[J].光谱学与光谱分析.2008(05)：1071-1075.
[1]张雪莲,李晓娜,武菊英,等.不同类型土壤全氮的近红外光谱技术测定研究[J].光谱学与光谱分析.2010(4)：906-910.
[2]高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤全氮近红外特征波长的选取[J].光谱学与光谱分析.2009(11)：2951-2954.
[3]袁石林,马天云,宋韬,等.土壤中全氮与总磷含量的近红外光谱实时检测方法[J].农业机械学报.2009(S1)：150-153.
[4]陈鹏飞,刘良云,王纪华,等.近红外光谱技术实时测定土壤中全氮及磷含量的初步研究[J].光谱学与光谱分析.2008(2)：295-298.
[5]刘雪梅,柳建设.基于LS-SVM建模方法近红外光谱检测土壤速效N和速效K的研究[J].光谱学与光谱分析.2012(11)：3019-3023.
[6]刘雪梅,章海亮.基于DPLS和LS-SVM的梨品种近红外光谱识别[J].农业机械学报.2012(9)：160-164.
[7]Shao Y N, He Y. Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research.2011,49(2):166-172.
[8]Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration[J]. AnalyTica Chimica ACTA.2009,648(1): 77-84.
[9]郝勇,孙旭东,潘圆媛,等.蒙特卡罗无信息变量消除方法用于近红外光谱预测果品硬度和表面色泽的研究[J].光谱学与光谱分析.2011(5)：1225-1229.
[10]宋海燕,何勇.基于OSC和PLS的土壤有机质近红外光谱测定[J].农业机械学报.2007(12)：113-1]5.
[11]刘雪梅,章海亮.基于DPLS和LS-SVM的梨品种近红外光谱识别[J].农业机械学报.2012(09)：160-164.
[12]刘雪梅,柳建设.基于MC-UVE的土壤碱解氮和速效钾近红外光谱检测[J].农业机械学报.2013,44(3)：86-90.
[13]刘雪梅,章海亮.基于遗传算法近红外光谱检测土壤养分的研究[J].灌溉排水学报.2013(02)：138-141.
[14]马世榜,汤修映,徐杨,等.可见/近红外光谱结合遗传算法无损检测牛肉pH值[J].农业工程学报.2012(18)：263-268.
[15]刘振华,赵英时.基于遗传算法的不同光照条件下植被和土壤组分温度反演[J].农业工程学报.2012(01)：161-166.
[16]余凡,赵英时,李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报.2012(03)：283-288.
[17]孙珂,陈圣波.基于遗传算法综合Terra/Aqua MODIS热红外数据反演地表组分温度[J].红外与毫米波学报.2012(05)：462-468.
[18]陈天恩,董静,陈立平,等.县域农田土壤采样布局多目标优化分析馍型[J].农业工程学报.2012(23)：67-73.
[19]候钰荣.伊犁绢蒿生理生态适应性的研究[D].新疆农业大学,2010.
[20]杨海清,姚建松,何勇.基于反射光谱技术的植物叶片SPAD值预测建模方法研究[J].光谱学与光谱分析.2009(06)：1607-1610.
[21]史波林,庆兆砷,籍保平,等.应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究[J].光谱学与光谱分析.2009(03)：665-670.
[22]杨志玲.药用石蒜不同居群遗传多样性及驯化繁育技术[D].中国林业科学研究院,2009.
[23]王加华,韩东海.基于遗传算法的苹果糖度近红外光谱分析[J].光谱学与光谱分析.2008(10)：2308-2311.
[24]邹小波,赵杰文.用遗传算法快速提取近红外光谱特征区域和特征波长[J].光学学报.2007(07)：1316-1321.
[25]祝诗平,王一鸣,张小超,等.基于遗传算法的近红外光谱谱区选择方法[J].农业机械学报.2004(05)：152-156.
[l]刘雪梅,柳建设.基于MC-UVE的土壤碱解氮和速效钾近红外光谱检测[J].农业机械学报.2013,44(3)：86-90.
[2]刘雪梅,章海亮.基于遗传算法近红外光谱检测土壤养分的研究[J].灌溉排水学报.2013(02)：138-141.
[3]刘雪梅,柳建设.基于LS-SVM建模方法近红外光谱检测土壤速效N和速效K的研究[J].光谱学与光谱分析.2012(11)：3019-3023.
[4]陈红艳,赵庚星,李希灿,等.小波分析用于土壤速效钾含量高光谱估测研究[J].中国农业科学.2012(07)：1425-1431.
[5]郭志新,梁亮,何见.一种林地土壤氮磷钾含量快速测定的新方法[J].中国农学通报.2011(2)：61-65.
[6]宋海燕,何勇.近红外光谱法分析土壤中磷,钾含量及pH值的研究[J].山西农业大学学报：自然科学版.2008,28(3)：275-278.
[7]李伟,张书慧,张倩,等.近红外光谱法快速测定土壤碱解氮、速效磷和速效钾含量[J].农业工程学报.2007,23(1)：55-59.
[8]郝勇,孙旭东,潘圆媛,等.蒙特卡罗无信息变量消除方法用于近红外光谱预测果品硬度和表面色泽的研究[J].光谱学与光谱分析.2011(05)：1225-1229.
[2]田永超,张娟娟,姚霞,等.基于近红外光声光谱的土壤有机质含量定量建模方法[J].农业工程学报.2012(1)：145-152.
[3]刘磊，沈润平,丁国香.基于高光谱的土壤有机质含量估算研究[J].光谱学与光谱分析.2011(3)：762-766.
[4]高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤全氮近红外特征波长的选取[J].光谱学与光谱分析.2009(11)：2951-2954.
[5]王艳艳.基于不同土质土壤的光谱特性及快速分析仪的研究[D].浙江大学,2007.
[6]李颉.土壤养分的近红外光谱快速分析系统开发与实验研究[D].中国农业机械化科学研究院,2011.
[7]李庆波.近红外光谱分析中若干关键技术的研究[D].天津大学,2003.
[8]刘蓉.近红外光谱分析中模型优化方法的初步研究[D].天津大学,2003.
[9]武子玉.矿物近红外光谱信息提取及应用研究[D].吉林大学,2005.
[10]Liang X Y, Li X Y, Lei T W, et al. Study of sample temperature compensation in the measurement of soil moisture content[J]. Measurement.2011,44(10):2200-2204.
[11]Summers D, Lewis M, Ostendorf B, et al. Visible near-infrared reflectance spectroscopy as a predictive indicator of soil properties[J]. Ecological Indicators.2011,11(1):123-131.
[12]B Kuang A M M. Calibration of visible and near infrared spectroscopy for soil analysis at the field scale on three European farms[J]. European Journal of Soil Science.2011,62:629-636.
[13]Chang C W, Laird D A, Mausbach M J, et al. Near-infrared reflectance spectroscopy-principal components regression analyses of soil properties[J]. Soil Science Society of America Journal.2001,65(2): 480-490.
[14]Mouazen A M, Kuang B, De Baerdemaeker J, et al. Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy[J]. Geoderma.2010,158(1-2SI):23-31.
[15]Bernard G. Barthes D A N. Determination of potential denitrification in arange of tropical topsoils using near infrared reflectance spectroscopy(NIRS)[J]. AppliedSoilEcology.2010,46:81-89.
[16]Rossel R, Behrens T. Using data mining to model and interpret soil diffuse reflectance spectra[J]. Geoderma.2010,158(1-2SI):46-54.
[17]Bilgili A V, van Es H M, Akbas F, et al. Visible-near infrared reflectance spectroscopy for assessment of soil properties in a semi-arid area of Turkey[J]. Journal of Arid Environments.2010,74(2):229-238.
[1 8]李颉,张小超,苑严伟,等.北京典型耕作土壤养分的近红外光谱分析[J].农业工程学报.2012(02)：176-179.
[19]O'Rourke S M, Holden N M. Determination of Soil Organic Matter and Carbon Fractions in Forest Top Soils using Spectral Data Acquired from Visible-Near Infrared Hyperspectral lmages[J]. Soil Science Society of America Journal.2012,76(2):586-596.
[20]Cecillon L, Certini G, Lange H, et al. Spectral fingerprinting of soil organic matter composition[JJ. Organic Geochemistry.2012,46:127-136.
[21]Chen H Z, Pan T, Chen J M, et al. Waveband selection for NIR spectroscopy analysis of soil organic matter based on SG smoothing and MWPLS methods[J]. Chemometrics and Intelligent Laboratory Systems. 2011,107(1):139-146.
[22]Hummel J W, Sudduth K A, Hollinger S E. Soil moisture and organic matter prediction of surface and subsurface soils using an NIR soil sensor[J]. Computers and Electronics in Agriculture.2001,32(2): 149-165.
[23]Bendor E, Inbar Y, Chen Y. The reflectance spectra of organic matter in the visible near-infrared and short wave infrared region (400-2500 nm) during a controlled decomposition process[J]. REMOTE SENSING OF ENVIRONMENT.1997,61(1):1-15.
[24]Kuang B Y, Mouazen A M. Non-biased prediction of soil organic carbon and total nitrogen with vis-NIR spectroscopy, as affected by soil moisture content and texture[J]. BIOSYSTEMS ENGINEERING. 2013,114(3):249-258.
[25]Yang X M, Xie H T, Drury C F, et al. Determination of organic carbon and nitrogen in particulate organic matter and particle size fractions of Brookston clay loam soil using infrared spectroscopy[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(2):177-188.
[26]Vohland M, Besold J, Hill J, et al. Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy [J]. Geoderma.2011, 166(1):198-205.
[27]Nocita M, Kooistra L, Bachmann M, et al. Predictions of soil surface and topsoil organic carbon content through the use of laboratory and field spectroscopy in the Albany Thicket Biome of Eastern Cape Province of South Africa[J]. Geoderma.2011,167-68:295-302.
[28]Stumpe B, Weihermuller L, Marschner B. Sample preparation and selection for qualitative and quantitative analyses of soil organic carbon with mid-infrared reflectance spectroscopy [J]. European Journal of Soil Science.2011,62(6):849-862.
[29]Mcdowell M L, Bruland G L, Deenik J L, et al. Soil total carbon analysis in Hawaiian soils with visible, near-infrared and mid-infrared diffuse reflectance spectroscopy [J]. GEODERMA.2012,189: 312-320.
[30]Sarkhot D V, Grunwald S, Ge Y, et al. Comparison and detection of total and available soil carbon fractions using visible/near infrared diffuse reflectance spectroscopy[J]. Geoderma.2011,164(1-2):22-32.
[31]Vohland M, Emmerling C. Determination of total soil organic C and hot water-extractable C from VIS-NIR soil reflectance with partial least squares regression and spectral feature selection techniques[J]. European Journal of Soil Science.2011,62(4):598-606.
[32]Klaus V H, Kleinebecker T, Boch S, et al. NIRS meets Ellenberg's indicator values:Prediction of moisture and nitrogen values of agricultural grassland vegetation by means of near-infrared spectral characteristics[J]. Ecological Indicators.2012,14(1):82-86.
[33]Shi T Z, Cui L J, Wang J J, et al. Comparison of multivariate methods for estimating soil total nitrogen with visible/near-infrared spectroscopy[J]. PLANT AND SOIL.2013,366(1-2):363-375.
[34]Aitkenhead M J, Coull M C, Towers W, et al. Predicting soil chemical composition and other soil parameters from field observations using a neural network[J]. Computers and Electronics in Agriculture. 2012,82:108-116.
[35]H. Yang B K A M. Quantitative analysis of soil nitrogen and carbon at a farm scale using visible and near infrared spectroscopy coupled with wavelength reduction[J]. European Journal of Soil Science.2012, 63:410-420.
[36]Yang H, Kuang B, Mouazen A M. Quantitative analysis of soil nitrogen and carbon at a farm scale using visible and near infrared spectroscopy coupled with wavelength reduction[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(3):410-420.
[37]Piekarczyk J, Kazmierowski C, Krolewicz S. Relationships between soil properties of the abandoned fields and spectral data derived from the advanced spaceborne thermal emission and reflection radiometer (ASTER)[J]. Advances in Space Research.2012,49(2):280-291.
[38]Xie Xian-Li P X S B. Visible and Near-Infrared Diffuse Reflectance Spectroscopy for Prediction of Soil Properties near a Copper Smelter[J]. Pedosphere.2012,22(3):351-366.
[39]Rossel R, Webster R. Predicting soil properties from the Australian soil visible-near infrared spectroscopic database[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(6):848-860.
[40]Dong Y W, Yang S Q, Xu C Y, et al. Determination of Soil Parameters in Apple-Growing Regions by Near-and Mid-Infrared Spectroscopy[J]. PEDOSPHERE.2011,21(5):591-602.
[41]宋海燕.基于光谱技术的土壤、作物信息获取及其相互关系的研究[D].浙江大学,2006.
[42]Shao Y N, He Y. Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research.2011,49(2):166-172.
[43]占细雄.光栅分光型乙醇汽油近红外光谱分析关键技术研究[D].吉林大学,2008.
[44]李民赞,郑立华,安晓飞,等.土壤成分与特性参数光谱快速检测方法及传感技术[J].农业机械学报.2013(03)：73-87.
[45]李民赞,潘娈,郑立华,等.基于近红外漫反射测量的便携式土壤有机质测定仪的开发[J].光谱学与光谱分析.2010(4)：1146-1150.
[46]杨玮,Sigrimis Nick,李民赞.基于多光谱图像分析的温室黄瓜叶片营养元素检测与诊断[J].光谱学与光谱分析.2010(1)：210-213.
[47]车艳双,李民赞,郑立华,等.基于GPS和PDA的移动智能农田信息采集系统开发[J].农业工程学报.2010(S2)：109-114.
[48]郑立华,李民赞,孙红.基于近红外光谱的土壤参数快速分析系统[J].光谱学与光谱分析.2009(10)：2633-2636.
[49]郑立华,李民赞，潘娈,等.近红外光谱小波分析在土壤参数预测中的应用[J].光谱学与光谱分析.2009(6)：1549-1552.
[50]冀荣华,吴才聪,李民赞,等.基于远程通讯的农田信息管理系统设计与实现[J].农业工程学报.2009(S2)：165-169.
[51]郑立华,李民赞,潘娈,等.基于近红外光谱技术的土壤参数BP神经网络预测[J].光谱学与光谱分析.2008(5)：1160-1164.
[52]孙建英,李民赞,唐宁,等.东北黑土的光谱特性及其与土壤参数的相关性分析[J].光谱学与光谱分析.2007(8)：1502-1505.
[53]孙建英,李民赞,郑立华,等.基于近红外光谱的北方潮土土壤参数实时分析[J].光谱学与光谱分析.2006(3)：426-429.
[54]岑益郎,宋韬,何勇,等.基于可见/近红外漫反射光谱的土壤有机质含量估算方法研究[J].浙江大学学报(农业与生命科学版).2011(3).
[55]蒋璐璐,张瑜,王艳艳,等.基于光谱技术的土壤养分快速测试方法研究[J].浙江大学学报(农业与生命科学版).2010(4)：445-450.
[56]韩瑞珍,宋韬,何勇.基于可见/近红外光谱的士壤有机质含量预测[J].中国科学：信息科学.2010(S1)：111-116.
[57]宋韬,鲍一丹,何勇.利用光谱数据快速检测士壤含水量的方法研究[J].光谱学与光谱分析.2009(3)：675-677.
[58]袁石林,马天云,宋韬,等.土壤中全氮与总磷含量的近红外光谱实时检测方法[J].农业机械学报.2009(S1)：150-153.
[59]袁石林,马天云,宋韬,等.土壤中全氮与总磷含量的近红外光谱实时检测方法[J].农业机械学报.2009(S1)：150-153.
[60]宋海燕,何勇.近红外光谱法分析土壤中磷,钾含量及pH值的研究[J].山西农业大学学报：自然科学版.2008,28(3)：275-278.
[61]朱登胜,吴迪,宋海燕,等.应用近红外光谱法测定土壤的有机质和pH值[J].农业工程学报.2008(6)：196-199.
[62]宋海燕,何勇.基于OSC和PLS的土壤有机质近红外光谱测定[J].农业机械学报.2007(12)： 113-115.
[63]鲍一丹,何勇,方慧,等.十壤的光谱特征及氮含量的预测研究[J].光谱学与光谱分析.2007(1)：62-65.
[64]李颉,张小超,苑严伟,等.北京典型耕作土壤养分的近红外光谱分析[J].农业工程学报.2012(2)：176-179.
[65]卢艳丽,白由路,王磊，等.黑上土壤中全氮含量的高光谱预测分析[J].农业工程学报.2010(1)：256-261.
[66]卢艳丽,白由路,杨俐苹,等.基于主成分回归分析的土壤有机质高光谱预测与模型验证[J].植物营养与肥料学报.2008(6)：1076-1082.
[67]卢艳丽,白山路,杨俐苹,等.基于高光谱的土壤有机质含量预测模型的建立与评价[J].中国农业科学.2007(9)：1989-1995.
[68]陈民森.近红外光谱扣除背景误差的研究[D].天津大学,2005.
[69]邹婷婷.支持向量机回归—近红外光谱法用于药物无损非破坏定量分析的研究[D].吉林大学,2008.
[70]窦英.人工神经网络—近红外光谱法用于药物无损非破坏定量分析的研究[Dl.吉林大学,2006.
[1]郝勇,孙旭东,王豪.基于改进连续投影算法的光谱定量模型优化[J].江苏大学学报(自然科学版).2013(1)：49-53.
[2]吴迪,吴洪喜,蔡景波,等.基于无信息变量消除法和连续投影算法的可见-近红外光谱技术自虾种分类方法研究[J].红外与毫米波学报.2009(6)：423-427.
[3]刘飞,张帆,方慧,等.连续投影算法在油菜叶片氨基酸总量无损检测中的应用[J].光谱学与光谱分析.2009(11)：3079-3083.
[4]吴迪,金春华,何勇.基于连续投影算法的光谱主成分组合优化方法研究[J].光谱学与光谱分 析.2009(10)：2734-2737.
[5]吴迪,吴洪喜,蔡景波,等.基于无信息变量消除法和连续投影算法的可见-近红外光谱技术白虾种分类方法研究[J].红外与毫米波学报.2009(6)：423-427.
[6]成忠,张立庆,刘赫扬,等.连续投影算法及其在小麦近红外光谱波长选择中的应用[J].光谱学与光谱分析.2010(4)：949-952.
[7]高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤全氮近红外特征波长的选取[J].光谱学与光谱分析.2009(11)：2951-2954.
[8]钱海波,孙来军,王乐凯,等.基于连续投影算法的小麦湿面筋近红外校正模型优化[J].中国农学通报.2011(18)：51-56.
[9]刘雪梅,柳建设.基于MC-UVE的土壤碱解氮和速效钾近红外光谱检测[J].农业机械学报.2013(03)：88-91.
[10]郝勇,孙旭东,潘圆媛,等.蒙特卡罗无信息变量消除方法用于近红外光谱预测果品硬度和表面色泽的研究[J].光谱学与光谱分析.20１](5)：1225-1229.
[11]刘雪梅,章海亮.基于遗传算法近红外光谱检测土壤养分的研究[J].灌溉排水学报.2013(02)：138-141.
[12]马世榜,汤修映,徐杨,等.可见/近红外光谱结合遗传算法无损检测牛肉pH值[J].农业工程学报.2012(18)：263-268.
[13]刘振华,赵英时.基于遗传算法的不同光照条件下植被和土壤组分温度反演[J].农业工程学报.2012(01)：161-166.
[14]孙珂,陈圣波.基于遗传算法综合Terra/Aqua MODIS热红外数据反演地表组分温度[J].红外与毫米波学报.2012(05)：462468.
[15]陈天恩,董静,陈立平,等.县域农田土壤采样布局多目标优化分析模型[J].农业工程学报.2012(23)：67-73.
[16]杨海清,姚建松,何勇.基于反射光谱技术的植物叶片SPAD值预测建模方法研究[J].光谱学与光谱分析.2009(06]：1607-1610.
[171史波林，庆兆坤,籍保平,等.应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究[J].光谱学与光谱分析.2009(03)：665-670.
[18]王加华,韩东海.基于遗传算法的苹果糖度近红外光谱分析[J].光谱学与光谱分析.2008(10)：2308-2311.
[19]邹小波,赵杰文.用遗传算法快速提取近红外光谱特征区域和特征波长[J].光学学报.2007(07)：1316-1321.
[20]祝诗平,王一鸣,张小超,等.基于遗传算法的近红外光谱谱区选择方法[J].农业机械学报.2004(05)：152-156.
[21]卢艳丽,白由路,杨俐苹,等.基于主成分回归分析的土壤有机质高光谱预测与模型验证[J].植物营养与肥料学报.2008(6)：1076-1082.
[22]宋海燕,何勇.基于OSC和PLS的土壤有机质近红外光谱测定[J].农业机械学报.2007(12)：113-115.
[23]Shao Y N, He Y. Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research.2011,49(2):166-172.
[24]陈双双.基于光谱和多源波谱成像技术的植物灰霉病快速识别的方法研究[D].浙江大学,2012.
[25]余凡,赵英时,李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报.2012(03)：283-288.
[26]韩瑞珍,宋韬,何勇.基于可见/近红外光谱的土壤有机质含量预测[J].中国科学：信息科学.2010(S1)：111-116.
[27]张娟娟,田永超,朱艳,等.不同类型土壤的光谱特征及其有机质含量预测[J].中国农业科学.2009(9)：3154-3163.
[28]朱继文,刘丹丹.基于高光谱数据的土壤含盐量BP神经网络模型研究[J].东北农业大学学报.2009(10)：115-118.
[29]张淑娟,王凤花,张海红,等.基于主成分分析和BP神经网络的十壤养分近红外光谱检测[J].山西农业大学学报(自然科学版).2009(6)：483-487.
[30]郑立华，李民赞,潘娈,等.基于近红外光谱技术的十壤参数BP神经网络预测[J].光谱学与光谱分析.2008(5)：1160-1164.
[31]Wu D, Yang H, Chen X, et al. Application of image texture for the sorting of tea categories using multi-spectral imaging technique and support vector machine[J]. Journal of Food Engineering.2008.88(4): 474-483.
[1]刘雪梅,柳建设.基于LS-SVM建模方法近红外光谱检测土壤速效N和速效K的研究[J].光谱学与光谱分析.2012(11)：3019-3023.
[2]杨莲.受控实验下沿着水分梯度止相互作用和负相互作用间平衡的变化[D].兰州大学,2007.
[3]刘雪梅,章海亮.基于近红外光谱的不同建模方法检测土壤有机质和速效P含量的研究[J].西北农林科技大学学报(自然科学版).2013(04)：52-56.
[4]刘雪梅.近红外漫反射光谱检测土壤有机质和速效N的研究[J].中国农机化学报.2013(02)：202-206.
[5]田永超,张娟娟,姚霞,等.基于近红外光声光谱的土壤有机质含量定量建模方法[J].农业工程学报.2012(1)：145-152.
[6]刘炜,常庆瑞,郭曼,等.不同尺度的微分窗口下土壤有机质的一阶导数光谱响应特征分析[J].红外与毫米波学报.2011(4)：316-321.
[7]刘磊，沈润平,丁国香.基于高光谱的土壤有机质含量估算研究[J].光谱学与光谱分析.2011(3)：762-766.
[8]岑益郎,宋韬,何勇,等.基于可见/近红外漫反射光谱的土壤有机质含量估算方法研究[J].浙江大学学报(农业与生命科学版).2011(3).
[9]王淼,解宪丽,周睿,等.基于可见光-近红外漫反射光谱的红壤有机质预测及其最优波段选择[J].土壤学报.2011(5)：1083-1089.
[10]徐明星,周生路,丁卫,等.苏北沿海滩涂地区土壤有机质含量的高光谱预测[J].农业工程学报.2011(2)：219-223.
[11]刘炜,常庆瑞,郭曼,等.土壤导数光谱小波去噪与有机质吸收特征提取[J].光谱学与光谱分析.2011(1)：100-104.
[12]李民赞,潘娈,郑立华,等.基于近红外漫反射测量的便携式土壤有机质测定仪的开发[J].光谱学与光谱分析.2010(4)：1146-1150.
[13]韩瑞珍,宋韬,何勇.基于可见/近红外光谱的土壤有机质含量预测[J].中国科学：信息科学.2010(S1)：111-116.
[14]Shi T Z, Cui L J, Wang J J, et al. Comparison of multivariate methods for estimating soil total nitrogen with visible/near-infrared spectroscopy[J]. PLANT AND SOIL.2013,366(1-2):363-375.
[15]Xue S, Zhao Q L, Wei L L, et al. Fluorescence spectroscopic characterization of dissolved organic matter fractions in soils in soil aquifer treatment[J]. ENVIRONMENTAL MONITORING AND ASSESSMENT.2013,185(6):4591-4603.
[16]Collins A L, Williams L J, Zhang Y S, et al. Catchment source contributions to the sediment-bound organic matter degrading salmonid spawning gravels in a lowland river, southern England[J]. SCIENCE OF THE TOTAL ENVIRONMENT.2013,456:181-195.
[17]O'Rourke S M, Holden N M. Determination of Soil Organic Matter and Carbon Fractions in Forest Top Soils using Spectral Data Acquired from Visible-Near Infrared Hyperspectral Images[J]. Soil Science Society of America Journal.2012,76(2):586-596.
[18]Cecillon L, Certini G, Lange H, et al. Spectral fingerprinting of soil organic matter composition[J]. Organic Geochemistry.2012,46:127-136.
[19]Yang X M, Xie H T, Drury C F, et al. Determination of organic carbon and nitrogen in particulate organic matter and particle size fractions of Brookston clay loam soil using infrared spectroscopy[J]. EUROPEAN JOURNAL OF SOIL SCIENCE.2012,63(2):177-188.
[20]Chen H Z, Pan T, Chen J M, et al. Waveband selection for NIR spectroscopy analysis of soil organic matter based on SG smoothing and MWPLS methods[J]. Chemometrics and Intelligent Laboratory Systems.2011,107(1):139-146.
[21]郑立华,李民赞,潘娈,等.近红外光谱小波分析在土壤参数预测中的应用[J].光谱学与光谱分析.2009(6)：1549-1552.
[22]Cozzolino D, Moron A. Potential of near-infrared reflectance spectroscopy and chemometrics to predict soil organic carbon fractions[J]. Soil & Tillage Research.2006,85(1-2):78-85.
[23]Hummel J W, Sudduth K A, Hollinger S E. Soil moisture and organic matter prediction of surface and subsurface soils using an NIR soil sensor[J]. Computers and Electronics in Agriculture.2001, 32(2):149-165.
[24]Bendor E, Inbar Y, Chen Y. The reflectance spectra of organic matter in the visible near-infrared and short wave infrared region (400-2500 nm) during a controlled decomposition process[J]. REMOTE SENSING OF ENVIRONMENT.1997,61(1):1-15.
[25]郝勇,孙旭东,王豪.基于改进连续投影算法的光谱定量模型优化[J].江苏大学学报(自然科学版).2013(1)：49-53.
[26]李水芳,单杨,尹永,等.基于连续投影算法的油菜蜜近红外光谱真伪鉴别的研究[J].食品工业科技.2012(4)：89-91.
[27]吴迪,吴洪喜,蔡景波,等.基于无信息变量消除法和连续投影算法的可见-近红外光谱技术白虾种分类方法研究[J].红外与毫米波学报.2009(6)：423-427.
[28]刘飞,张帆,方慧，等.连续投影算法在油菜叶片氨基酸总量无损检测中的应用[J].光谱学与光谱分析.2009(11)：3079-3083.
[29]刘磊,沈润平,丁国香.基于高光谱的土壤有机质含量估算研究[J].光谱学与光谱分析.2011(03)：762-766.
[30]刘雪梅,章海亮.基于DPLS和LS-SVM的梨品种近红外光谱识别[J].农业机械学报.2012(9)：160-164.
[31]吴迪,曹芳,冯水娟,等.基于支持向量机算法的红外光谱技术在奶粉蛋白质含量快速检测中的应用[J].光谱学与光谱分析.2008(05)：1071-1075.
[1]张雪莲,李晓娜,武菊英,等.不同类型土壤全氮的近红外光谱技术测定研究[J].光谱学与光谱分析.2010(4)：906-910.
[2]高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤全氮近红外特征波长的选取[J].光谱学与光谱分析.2009(11)：2951-2954.
[3]袁石林,马天云,宋韬,等.土壤中全氮与总磷含量的近红外光谱实时检测方法[J].农业机械学报.2009(S1)：150-153.
[4]陈鹏飞,刘良云,王纪华,等.近红外光谱技术实时测定土壤中全氮及磷含量的初步研究[J].光谱学与光谱分析.2008(2)：295-298.
[5]刘雪梅,柳建设.基于LS-SVM建模方法近红外光谱检测土壤速效N和速效K的研究[J].光谱学与光谱分析.2012(11)：3019-3023.
[6]刘雪梅,章海亮.基于DPLS和LS-SVM的梨品种近红外光谱识别[J].农业机械学报.2012(9)：160-164.
[7]Shao Y N, He Y. Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research.2011,49(2):166-172.
[8]Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration[J]. AnalyTica Chimica ACTA.2009,648(1): 77-84.
[9]郝勇,孙旭东,潘圆媛,等.蒙特卡罗无信息变量消除方法用于近红外光谱预测果品硬度和表面色泽的研究[J].光谱学与光谱分析.2011(5)：1225-1229.
[10]宋海燕,何勇.基于OSC和PLS的土壤有机质近红外光谱测定[J].农业机械学报.2007(12)：113-1]5.
[11]刘雪梅,章海亮.基于DPLS和LS-SVM的梨品种近红外光谱识别[J].农业机械学报.2012(09)：160-164.
[12]刘雪梅,柳建设.基于MC-UVE的土壤碱解氮和速效钾近红外光谱检测[J].农业机械学报.2013,44(3)：86-90.
[13]刘雪梅,章海亮.基于遗传算法近红外光谱检测土壤养分的研究[J].灌溉排水学报.2013(02)：138-141.
[14]马世榜,汤修映,徐杨,等.可见/近红外光谱结合遗传算法无损检测牛肉pH值[J].农业工程学报.2012(18)：263-268.
[15]刘振华,赵英时.基于遗传算法的不同光照条件下植被和土壤组分温度反演[J].农业工程学报.2012(01)：161-166.
[16]余凡,赵英时,李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报.2012(03)：283-288.
[17]孙珂,陈圣波.基于遗传算法综合Terra/Aqua MODIS热红外数据反演地表组分温度[J].红外与毫米波学报.2012(05)：462-468.
[18]陈天恩,董静,陈立平,等.县域农田土壤采样布局多目标优化分析馍型[J].农业工程学报.2012(23)：67-73.
[19]候钰荣.伊犁绢蒿生理生态适应性的研究[D].新疆农业大学,2010.
[20]杨海清,姚建松,何勇.基于反射光谱技术的植物叶片SPAD值预测建模方法研究[J].光谱学与光谱分析.2009(06)：1607-1610.
[21]史波林,庆兆砷,籍保平,等.应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究[J].光谱学与光谱分析.2009(03)：665-670.
[22]杨志玲.药用石蒜不同居群遗传多样性及驯化繁育技术[D].中国林业科学研究院,2009.
[23]王加华,韩东海.基于遗传算法的苹果糖度近红外光谱分析[J].光谱学与光谱分析.2008(10)：2308-2311.
[24]邹小波,赵杰文.用遗传算法快速提取近红外光谱特征区域和特征波长[J].光学学报.2007(07)：1316-1321.
[25]祝诗平,王一鸣,张小超,等.基于遗传算法的近红外光谱谱区选择方法[J].农业机械学报.2004(05)：152-156.
[l]刘雪梅,柳建设.基于MC-UVE的土壤碱解氮和速效钾近红外光谱检测[J].农业机械学报.2013,44(3)：86-90.
[2]刘雪梅,章海亮.基于遗传算法近红外光谱检测土壤养分的研究[J].灌溉排水学报.2013(02)：138-141.
[3]刘雪梅,柳建设.基于LS-SVM建模方法近红外光谱检测土壤速效N和速效K的研究[J].光谱学与光谱分析.2012(11)：3019-3023.
[4]陈红艳,赵庚星,李希灿,等.小波分析用于土壤速效钾含量高光谱估测研究[J].中国农业科学.2012(07)：1425-1431.
[5]郭志新,梁亮,何见.一种林地土壤氮磷钾含量快速测定的新方法[J].中国农学通报.2011(2)：61-65.
[6]宋海燕,何勇.近红外光谱法分析土壤中磷,钾含量及pH值的研究[J].山西农业大学学报：自然科学版.2008,28(3)：275-278.
[7]李伟,张书慧,张倩,等.近红外光谱法快速测定土壤碱解氮、速效磷和速效钾含量[J].农业工程学报.2007,23(1)：55-59.
[8]郝勇,孙旭东,潘圆媛,等.蒙特卡罗无信息变量消除方法用于近红外光谱预测果品硬度和表面色泽的研究[J].光谱学与光谱分析.2011(05)：1225-1229.