可见光—近红外光谱估算三江源区不同土壤全氮含量

近年来可见光—近红外反射光谱已被广泛应用于估算土壤全氮含量,为大范围区域土壤全氮含量获取提供了一种快速、有效的方法。基于实验室测定的三江源区146个表层土壤(0~30cm)样品的反射光谱数据(350~2 500nm)与全氮含量数据;利用偏最小二乘回归(PLSR)和反向传播神经网络(BPNN)两种模型方法与光谱反射率(REF)及其4种数学预处理变换相结合,分别建立分土壤类型样本和总体样本全氮估算模型;评估利用可见光—近红外光谱技术预测三江源区土壤全氮含量的能力。结果表明:BPNN模型的R2cal、R2val及验证RPD的平均值分别为0.87、0.81与2.28;而PLSR模型则相应为0.75、0.72和1.95;表明BPNN模型预测能力整体上要优于PLSR模型。BPNN与光谱各种形式的结合均具有良好、或接近良好预测全氮的能力;而PLSR与REF、倒数对数(Log(1/R))及波段深度(BD)的结合仅少部分具有良好估算能力、大部分则为粗略估算能力,一阶微分(FDR)和二阶微分(SDR)估算精度均较低,尤其是SDR(R20.5,RPD=1.10~1.27)均不具备估算能力。总体样本所建模型稳定性好于分土壤类型,分土壤类型建模差异性明显;此外,总体来看,BPNN模型比PLSR建模精度高、模型稳定性好,但PLSR模型可操作性强于BPNN模型。     

三江源区不同土壤类型有机质含量高光谱反演

近年来高光谱遥感技术被广泛运用于土壤有机质含量反演的研究中。基于三江源区玉树县和玛多县采集的146个土壤样品的室内ASD FieldSpec 4实测光谱数据及4种变换形式,利用偏最小二乘回归(PLSR)和人工神经网络(ANN)建立土壤有机质含量高光谱预测模型。结果表明:ANN模型反演土壤有机质含量的整体精度高于PLSR模型,总均方根误差均在17.51以下;但是,不同土壤类型的最佳反演模型及指标却有所差异:高山草甸土和沼泽土的最佳反演模型和指标均为ANN模型和BD指标,模型总均方根误差分别为10.29和3.29;高山草原土的最佳反演模型是PLSR模型,最佳指标是REF指标,模型总均方根误差为5.59;山地草甸土的最佳反演模型为〖JP2〗PLSR模型,最佳指标为BD指标,模型总均方根误差为4.68。研究发现,利用ANN模型和PLSR模型都能较好地预测三江源区4种土壤类型的有机质含量,而波段深度则是该区域的最佳反演指标。〖JP〗
     

GA-PLS方法提取土壤水盐光谱特征的精度分析

光谱定量遥感已成为土壤盐渍化大尺度调查的有效手段之一,但黄河三角洲地区盐渍化土壤的光谱响应特征尚未明确。以黄河三角洲野外测定土壤体积含水率、电导率为例,应用遗传偏最小二乘法(GA-PLS)在小样本集条件下提取盐渍土壤的水分-盐分的光谱响应特征,利用蒙特卡罗方法随机模拟结果表明:在不同土壤水盐含量条件下,GA-PLS方法所提取的光谱特征具有鲁棒性,含水率模型稳定在23个波段变量,即响应特征为365~425,500~515,720~740,755~765与955~965 nm;土壤电导率模型的特征集数目为20个波段变量,特征为370~385,405~425\,500~535,650~660,755~760与1 030~1 050 nm。实验在不同预处理模型下,GA-PLS算法所建立水盐光谱模型较PLSR模型均显示出更高的精度。其中,包络线预处理方法与GA-PLS算法相结合效果最优,其水分光谱模型测试集拟合精度(R²),预测残差平方和(PRSS)与残差预测方差(RPD)分别为0.88,9.36与15.80;土壤光谱模型测试集精度R²,PRSS与RPD分别为0.71,15.68与13.76。     

基于特征筛选结合PSO-BPNN和GA-BPNN算法的土壤重金属高光谱定量反演

以连州地区土壤重金属含量为研究对象,分析包括土壤原始光谱在内的经过数学变换后的光谱数据与重金属含量之间的相关性,再采用VISSA-IRIV算法进行光谱特征提取,分别建立偏最小二乘回归(PLSR)、BP神经网络(BPNN)、粒子群优化BP神经网络、遗传算法优化BP神经网络模型,对比获取土壤重金属元素Cr、Cu含量最优反演模型。结果表明：VISSA-IRIV算法实现了对光谱数据的高效降维;BPNN模型预测效果明显优于PLSR模型;经过优化的BP神经网络模型反演精度和稳定性得到了极大地提升,其中Cr、Cu元素的最佳反演模型组合分别为FD-GABPNN(R²=0.87、RMSE=13.82、RPD=2.95)、SNV-FD-PSO-BPNN(R²=0.92、RMSE=4.25、RPD=3.41)。该研究对土壤重金属含量的准确、快速分析提供了一种有效的方法,对实现土壤重金属污染治理具有重要的现实意义。     

褐潮土的光谱特性及用土壤反射率估算有机质含量的研究

本文通过ASDFR便携式光谱仪对132个风干土壤样品的光谱反射率进行了实验室测定。根据土样光谱反射率变化,获得了褐潮土土壤剖面的不同诊断层反射光谱特征。结果表明,在400～1200nm范围之间,土壤有机质含量与土壤光谱反射率有较好的相关性。利用导数光谱方法建立了预测土壤有机质含量的方程,提出了预测北京地区褐潮土有机质光谱的最佳波段。在波长447nm处采用反射率和A值(反射率倒数的对数)所建立的预测方程的预测精度较高。采用反射率的一阶微分建立的预测方程的最佳波段在516nm处。而A值一阶微分光谱在615nm处相关性最好。作为一项参考指标用光谱分析法评价土壤中有机质含量,以期对精准农业中土壤养分或肥力的预测具有一定的指导作用。     

吐鲁番盆地葡萄园土壤重金属铅含量高光谱估算

土壤重金属铅污染作为现代工矿业发展的产物,已逐渐入侵到农业生产和农产品中。高光谱技术由于具有宏观、快速、高效的特点已成为土壤重金属监测的重要手段。以新疆吐鲁番盆地葡萄园土壤Pb元素为研究对象,分析土壤原始光谱在内的15种光谱变换下的土壤光谱反射率数据与土壤Pb含量的关系,构建土壤Pb含量偏最小二乘回归（PLSR）模型和地理加权重回归（GWR）模型,对比分析并探讨运用土壤高光谱估算葡萄园土壤Pb含量的可行性。结果表明：土壤原始光谱反射率通过光谱变换能有效增强葡萄园土壤Pb元素的光谱特征及模型估算精度,其中,平方根二阶微分（SRSD）变换的PLSR模型和GWR模型估算能力最优。采用GWR模型比PLSR模型更好的解释葡萄园土壤重金属Pb含量高光谱估算。从模型稳定性和精确性来看,在平方根二阶微分变换中GWR模型R²从PLSR模型的0.262提高至0.866, 平方根误差减少了1.009。采用GWR模型可有效提高估算葡萄园土壤Pb含量的精度,为中国葡萄园基地土壤重金属污染以及土壤环境安全研究提供有益借鉴。     

水稻叶片氮含量反演偏最小二乘模型设计

针对高光谱偏最小二乘模型(PLSR)反演作物氮含量时易出现数据冗余和模型复杂的问题,尝试结合波段深度分析和遗传算法(GA)建立水稻氮含量PLSR反演模型。基于去包络线处理的水稻高光谱数据(350nm~750nm),选取波段深度(BD)、波段深度比(BDR)、归一化面积波段深度(BNA)和归一化面积波段指数(NBDI)4种波段深度指数分别建立BDA-PLSR模型,进而采用遗传算法波段选择选取最适宜波段深度指数建立GA-PLSR模型,并将GA-PLSR模型与BDA-PLSR模型进行对比。结果显示,基于BNA的GA-PLSR模型在反演水稻氮含量中获得了最佳的结果(Adj.R2=0.67,RMSEP=0.20,RPD=1.84)。研究证明,利用波段深度分析建立的PLSR模型能一定程度上解决数据冗余问题,进一步采用遗传算法进行波段选择能更有效挖掘光谱信息,提高模型精度。     

一种基于分段偏最小二乘模型的土壤重金属遥感反演方法

土壤中重金属由于其毒性而成为最有害的环境污染物之一,利用遥感进行土壤重金属检测和分布制图是目前最为高效的手段。采用哨兵二号（Sentinel-2）多光谱影像与实测样品光谱数据,对山西省铜矿峪铜矿尾矿库及其周边农田土壤的铜（Cu）含量进行估算,利用68个土壤样品的反射光谱,优选出适合土壤铜含量预测的波段,结合分段偏最小二乘法（Piecewise Partial Least Squares Regression,P-PLSR）,对土壤铜含量进行估算,将模型用于Sentinel-2影像获得了Cu含量的空间分布。通过P-PLSR对实测样品光谱建模反演Cu含量的决定系数（R²）为0.89,预测偏差比（RPD）为2.82;利用Sentinel-2多光谱影像获得了该区域Cu元素含量空间分布,其Cu含量的估算精度R²为0.74,RPD为1.73,Cu含量高值区空间分布与尾矿库关系密切。Sentinel-2多光谱数据具有高空间分辨率（10、20和60 m）、高时间分辨率和幅宽大（290 km）等优势,通过敏感波段选择并建立反演模型,可实现大范围土壤环境制图。     

裸土表层含水量高光谱遥感的最佳波段选择

在自然状况下，对裸土进行人为干湿处理，利用ASD PRO FR2500地物光谱仪测得土壤在350nm～2500nm反射光谱并适时采取表层土，利用烘干法测得土壤体积含水量。依据土壤湿度与土壤光谱反射率之间的相关关系，得出土壤含水量与土壤光谱反射率的非线性方程。利用该方程和光谱反射率值进行土壤水分反演，通过对反演结果的误差分析，结合光谱反射率与体积含水量的指数回归分析，笔认为采用1950nm～2250nm波段的光谱反射率估测土壤含水量效果较好。     

水稻叶片氮含量反演偏最小二乘模型设计

针对高光谱偏最小二乘模型（PLSR）反演作物氮含量时易出现数据冗余和模型复杂的问题,尝试结合波段深度分析和遗传算法（GA）建立水稻氮含量PLSR反演模型。基于去包络线处理的水稻高光谱数据（350nm～750nm）,选取波段深度（BD）、波段深度比（BDR）、归一化面积波段深度（BNA）和归一化面积波段指数（NBDI）4种波段深度指数分别建立BDA PLSR模型,进而采用遗传算法波段选择选取最适宜波段深度指数建立GA PLSR模型,并将GA PLSR模型与BDA PLSR模型进行对比。结果显示,基于BNA的GA PLSR模型在反演水稻氮含量中获得了最佳的结果（Adj.R2=0.67,RMSEP=0.20,RPD=1.84）。研究证明,利用波段深度分析建立的PLSR模型能一定程度上解决数据冗余问题,进一步采用遗传算法进行波段选择能更有效挖掘光谱信息,提高模型精度。     

Predicting C3 and C4 grass nutrient variability using in situ canopy reflectance and partial least squares regression

The use of hyperspectral data to estimate forage nutrient content can be a challenging task, considering the multicollinearity problem, which is often caused by high data dimensionality. We predicted some variability in the concentration of limiting nutrients such as nitrogen (N), crude protein (CP), moisture, and non-digestible fibres that constrain the intake rate of herbivores. In situ hyperspectral reflectance measurements were performed at full canopy cover for C3 and C4 grass species in a montane grassland environment. The recorded spectra were resampled to 13 selected band centres of known absorption and/or reflectance features, WorldView-2 band settings, and to 10 nm-wide bandwidths across the 400–2500 nm optical region. The predictive accuracy of the resultant wavebands was assessed using partial least squares regression (PLSR) and an accompanying variable importance (VIP) projection. The results indicated that prediction accuracies ranging from 66% to 32% of the variance in N, CP, moisture, and fibre concentrations can be achieved using the spectral-only information. The red, red-edge, and shortwave infrared (SWIR) wavelength regions were the most sensitive to all nutrient variables, with higher VIP values. Moreover, the PLSR model constructed based on spectra resampled around the 13 preselected band centres yielded the highest sensitivity to the predicted nutrient variables. The results of this study thus suggest that the use of the spectral resampling technique that uses only a few but strategically selected band centres of known absorption or reflectance features is sufficient for forage nutrient estimation.     

Using the orthogonal projections methods for predicting rice (Oryza sativa L.) yield with canopy reflectance data

Predicting crop yield in-season over large areas before harvest is an important topic in agricultural decision-making. This study compares the performance of partial least squares regression (PLSR) for predicting rice yield (Oryza sativa L.) using different signal correction methods on canopy reflectance spectral data. These signal correction methods include the standard normal variate (SNV) transformation, multiplicative scatter correction (MSC), orthogonal signal correction algorithm with leave-one-out cross-validation (OSC(CV)), and orthogonal projections to latent structures (O-PLS). Data were acquired over a wavelength range of 350–1100 nm. However, the influence of the intra-variance based on measured dates appeared in the original spectra. Using these pre-processing methods effectively reduced the influence of noise and increased the performance of the final PLSR model. Although SNV and MSC had good predictive ability, they could not clearly identify intra-variance effects. Conversely, the PLSR models with OSC and O-PLS were based on only one component, and could be interpreted in terms of crop parameters. Moreover, the Y-orthogonal component of O-PLS clearly identified intra-variance based on measured dates and provided superior modelling ability. The results of this study show that the O-PLS method is a useful tool for correction and interpretation when constructing a PLSR model for predicting rice yield in-season using canopy reflectance data.     

Soil Heavy Metals Estimation based on Hyperspectral in Urban Residential

To explore the possibility of using soil spectral reflectance to estimate soil heavy metal content in urban residential area，this study chooses 30 soil samples of Cu，Pb and Zn in Minhang Residential area，Shanghai Province.Through the spectral factor transform to highlight its eigenvalues，constructed Multiple Linear Stepwise Regression(MLSR) model and Partial Least Squares Regression(PLSR) model based on spectral reflectance of soil heavy metals.The results show that the reciprocal first-order and the logarithmic first-order differential transformation can effectively enhance the heavy metal soil spectral characteristics.The best characteristic bands of Cu，Pb and Zn are 1 042.7 nm、706.84 nm and 1 404.8 nm.In terms of model stability and accuracy，PLSR model is better than MLSR model.The RMSE of Cu and Zn were only about 10% of the mean value of heavy metals in the study area，and the accuracy of the model was high.Compared with Cu and Zn，the R2 of Pb is between 0.64~0.88 which with higher model stability.By preprocessing the spectral data，the partial least-squares regression can effectively improve the accuracy of estimating the heavy metal content in urban residential areas. 〖WTHZ〗Key words:〖WT〗 Urban residential area;Soil heavy metals;Hyperspectral;Multivariate Linear Stepwise Regression(MLSR) model;Partial Least Squares Regression(PLSR) model 〖HT〗〖ST〗〖HJ〗〖WT〗〖JP〗〖LM〗     

Nitrogen detection with hyperspectral normalized ratio indices across multiple plant species

The main focus of recent studies relating vegetation leaf chemistry with remotely sensed data is the prediction of chlorophyll and nitrogen content using indices based on a combination of bands from the red and infrared wavelengths. The use of high spectral resolution data offers the opportunity to select the optimal wavebands for predicting plant chemical properties. In order to test the optimal band combinations for predicting nitrogen content, normalized ratio indices were calculated for all wavebands between 350 and 2200 nm for five different species. The correlation between these indices and the nitrogen content of the samples was calculated and compared between species. The results show a strong correlation between individual normalized ratio indices and the nitrogen content for different species. The spectral regions that are most effective for predicting nitrogen content are, for each individual species, different from the normalized difference vegetation index (NDVI) spectral region. By combining the areas of maximum correlation it was possible to determine the optimal spectral regions for predicting leaf nitrogen content across species. In a cross‐species situation, normalized ratio indices using the combination of reflectance at 1770 nm and at 693 nm may give the best relation to nitrogen content for individual species.     

土壤重金属Cu含量遥感反演的波段选择与最佳光谱分辨率研究

高光谱数据以其高光谱分辨率和多而连续的光谱波段为预测土壤重金属污染提供了有力工具,但波段选择方法与光谱分辨率的影响不容忽视。利用实验室测定的181个土壤光谱样本数据,利用逐步回归法进行土壤Cu含量反演的波段选择,进而利用偏最小二乘方回归PLSR方法建模,分析了波段数对Cu含量反演的影响;此外,采用高斯响应函数重采样方法,探讨了光谱分辨率降低对反演精度的影响。实验表明,预测重金属元素Cu含量的最佳波段数为10个,模型可决系数R2=0.7523,拟合均方根误差RMSE=0.4699;预测Cu含量的最佳光谱采样间隔为32 nm,R2=0.7028,RMSE=0.5147。该结果可能为将来设计低廉实用的高光谱卫星传感器提供指标论证,为模拟卫星传感器波段预测土壤重金属含量提供理论依据。     

Estimation of heavy-metal contamination in soil using reflectance spectroscopy and partial least-squares regression

Lead (Pb) poisoning from anthropogenic sources continues to threaten the health of urban children. Mapping Pb distribution on a large scale is imperative to identify hotspots and reduce Pb poisoning. To assess the feasibility of using reflectance spectroscopy to map soil Pb and other heavy metal abundance, the relationship between surface soil metal concentrations and hyperspectral reflectance measurements was examined via partial least-squares regression (PLSR) modelling. Soil samples were taken from four study sites. Metal concentrations were determined by inductively coupled plasma-atomic-emission spectrometry (ICP-AES) analysis, and reflectance was measured with an ASD (Analytical Spectral Devices) field spectrometer covering the spectral region of 350–2500 nm. Pb displayed an exponential decrease as a function of distance from the roadway, demonstrating the depositional patterns from leaded gas combustion which remain on the landscape 20 years after the phase-out of leaded gasoline. Calibration samples were used to derive the PLSR algorithm, and validation samples assessed the model's predictive ability. The correlation coefficients between the lab-determined abundance and the abundance predicted from PLSR calibration for all metals except copper were at or above 0.970, with the correlation coefficient for Pb the highest of all metals (0.992). Manganese, zinc and Pb had significant coefficients of determination (0.808, 0.760 and 0.746, respectively) for the validation samples. These results suggest that Pb and other heavy metal concentrations can be retrieved from spectral reflectance at high accuracy. Reflectance spectroscopy thus has potential to map the spatial distribution of Pb abundance with the aim of improving children's health in an urban environment.     

Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN)

In this paper the possibility of predicting salt concentrations in soils from measured reflectance spectra is studied using partial least squares regression (PLSR) and artificial neural network (ANN). Performance of these two adaptive methods has been compared in order to examine linear and non-linear relationship between soil reflectance and salt concentration.Experiment-, field- and image-scale data sets were prepared consisting of soil EC measurements (dependent variable) and their corresponding reflectance spectra (independent variables). For each data set, PLSR and ANN predictive models of soil salinity were developed based on soil reflectance data. The predictive accuracies of PLSR and ANN models were assessed against independent validation data sets not included in the calibration or training phase.The results of PLSR analyses suggest that an accurate to good prediction of EC can be made based on models developed from experiment-scale data (R² > 0.81 and RPD (ratio of prediction to deviation) > 2.1) for soil samples salinized by bischofite and epsomite minerals. For field-scale data sets, the PLSR predictive models provided approximate quantitative EC estimations (R² = 0.8 and RPD = 2.2) for grids 1 and 6 and poor estimations for grids 2, 3, 4 and 5. The salinity predictions from image-scale data sets by PLSR models were very reliable to good (R² between 0.86 and 0.94 and RPD values between 2.6 and 4.1) except for sub-image 2 (R² = 0.61 and RPD = 1.2).The ANN models from experiment-scale data set revealed similar network performances for training, validation and test data sets indicating a good network generalization for samples salinized by bischofite and epsomite minerals. The RPD and the R² between reference measurements and ANN outputs of theses models suggest an accurate to good prediction of soil salinity (R² > 0.92 and RPD > 2.3). For the field-scale data set, prediction accuracy is relatively poor (0.69 > R² > 0.42). The ANN predictive models estimating soil salinity from image-scale data sets indicate a good prediction (R² > 0.86 and RPD > 2.5) except for sub-image 2 (R² = 0.6 and RPD = 1.2).The results of this study show that both methods have a great potential for estimating and mapping soil salinity. Performance indexes from both methods suggest large similarity between the two approaches with PLSR advantages. This indicates that the relation between soil salinity and soil reflectance can be approximated by a linear function.