首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 62 毫秒
1.
Carbon 13 nuclear magnetic resonance spectroscopy (13C NMR) is a powerful technique for studying the structure and turnover of soil organic matter, but is time consuming and expensive. It is therefore worth seeking swifter and cheaper methods. Diffuse reflectance FT‐IR spectroscopy (DRIFT), along with partial least squares (PLS) algorithms, provides statistical models to quantify soil properties, such as contents of C, N and clay. I have applied DRIFT?PLS to quantify soil organic C species, as measured by solid state 13C NMR spectroscopy, for several bulk soils and physical soil fractions. Calibration and prediction models for organic C and for particular NMR regions, namely alkyl C, O?alkyl C and carboxyl C, attained R2 values of between 0.94 and 0.98 (calibration) and 0.70–0.93 (cross‐validation). The prediction of unknown soil samples, after pre‐selection by statistical indices, confirmed the applicability of DRIFT?PLS. The prediction of aromatic C failed, probably because of superimposition of aromatic bands by signals from minerals. Results from fractions of particulate organic matter suggest that the chemical homogeneity of the material hampers the quantification of its constituting C species by DRIFT?PLS. For alkyl C, prediction of carbon species by DRIFT?PLS was better than direct peak‐area quantification in the IR spectra, but advantageous in parts only compared with a linear model correlating C species with soil C contents. In conclusion, DRIFT?PLS calibrated with NMR data provides quantitative information on the composition of soil organic matter and can therefore complement structural studies by its application to large numbers of samples. However, it cannot replace the information provided by more specific methods. The actual potential of DRIFT?PLS lies in its capacity to predict unknown samples, which is helpful for classification and identification of environmental outliers or benchmarks.  相似文献   

2.
Agricultural, environmental and ecological modeling requires soil cation exchange capacity (CEC) that is difficult to measure. Pedotransfer functions (PTFs) are thus routinely applied to predict CEC from easily measured physicochemical properties (e.g., texture, soil organic matter, pH). This study developed the support vector machines (SVM)‐based PTFs to predict soil CEC based on 208 soil samples collected from A and B horizons in Qingdao City, Shandong Province, China. The database was randomly split into calibration and validation datasets in proportions of 3:1 using the bootstrap method. The optimal SVM parameters were searched by applying the genetic algorithm (GA). The performance of SVM models was compared to those of multiple stepwise regression (MSR) and artificial neural network (ANN) models. Results show that the accuracy of CEC predicted by SVM improves considerably over those predicted by MSR and ANN. The performance of SVM for B horizon (R2 = 0.85) is slightly better than that for A horizon (R2 = 0.81). The SVM is a powerful approach in the simulation of nonlinear relationship between CEC and physicochemical properties of widely distributed samples from different soil horizons. Sensitivity analysis was also conducted to explore the influence of each input parameter on the CEC predictions by SVM. The clay content is the most sensitive parameter, followed by soil organic matter and pH, while sand content has the weakest influence. This suggests that clay is the most important predictor for predicting CEC of both soil horizons.  相似文献   

3.
The development of accurate calibration models for selected soil properties is a crucial prerequisite for successful implementation of visible and near infrared (Vis‐NIR) spectroscopy for soil analysis. This paper compares the performance of calibration models developed for individual farms with that of general models valid for three farms in three European countries. Fresh soil samples collected from farms in the Czech Republic, Germany and Denmark were scanned with a fibre‐type Vis‐NIR spectrophotometer. After dividing spectra into calibration (70%) and validation (30%) sets, spectra in the calibration set were subjected to partial least squares regression (PLSR) with leave‐one‐out cross‐validation to establish calibration models of soil properties. Except for the Czech Republic farm, individual farm models provided successful calibration for total carbon (TC), total nitrogen (TN) and organic carbon (OC), with coefficients of determination (R2) of 0.85–0.93 and 0.74–0.96 and residual prediction deviations (RPD) of 2.61–3.96 and 2.00–4.95 for the cross‐validation and independent validation respectively. General calibration models gave improved prediction accuracies compared with models of farms in the Czech Republic and Germany, which was attributed to larger ranges in the variation of soil properties in general models compared with those in individual farm models. The results revealed that larger standard deviations (SDs) and wider variation ranges have resulted in larger R2 and RPD, but also larger root mean square errors of prediction (RMSEP). Therefore, a compromise solution, which also results in small RMSEP values, should be found when selecting soil samples for Vis‐NIR calibration to cover a wide variation range.  相似文献   

4.
Visible–near infrared (vis–NIR) spectroscopy can be used to estimate soil properties effectively using spectroscopic calibrations derived from data contained in spectroscopic databases. However, these calibrations cannot be used with proximally sensed (field) spectra because the spectra in these databases are recorded in the laboratory and are different to field spectra. Environmental factors, such as the amount of water in the soil, ambient light, temperature and the condition of the soil surface, cause the differences. Here, we investigated the use of direct standardization (DS) to remove those environmental factors from field spectra. We selected 104 sensing (sampling) sites from nine paddy fields in Zhejiang province, China. At each site, vis–NIR spectra were recorded with a portable spectrometer. The soils were also sampled to record their spectra under laboratory conditions and to measure their soil organic matter (SOM) content. The resulting data were divided into training and validation sets. A subset of the corresponding field and laboratory spectra in the training set (the transfer set) was used to derive the DS transfer matrix, which characterizes the differences between the field and laboratory spectra. Using DS, we transferred the field spectra of the validation samples so that they acquired the characteristics of spectra that were measured in the laboratory. A partial least squares regression (PLSR) of SOM on the laboratory spectra of the training set was then used to predict both the original field spectra and the DS‐transferred field spectra. The assessment statistics of the predictions were improved from R2 = 0.25 and RPD = 0.35 to R2 = 0.69 and RPD = 1.61. We also performed independent predictions of SOM on the DS‐transferred field spectra with a PLSR derived using the Chinese soil spectroscopic database (CSSD), which was developed in the laboratory. The R2 and RPD values of these predictions were 0.70 and 1.79, respectively. Predictions of SOM with the DS‐transferred field spectra were more accurate than those treated with external parameter orthogonalisation (EPO), and more accurate than predictions made by spiking. Our results show that DS can effectively account for the effects of water and environmental factors on field spectra and improve predictions of SOM. DS is conceptually straightforward and allows the use of calibrations made with laboratory‐measured spectra to predict soil properties from proximally sensed (field) spectra, without needing to recalibrate the models.  相似文献   

5.
Reflectance spectra (400 to 1700 nm) of single wheat kernels collected using the Single Kernel Characterization System (SKCS) 4170 were analyzed for wheat grain hardness using partial least squares (PLS) regression. The wavelengths (650 to 700, 1100, 1200, 1380, 1450, and 1670 nm) that contributed most to the ability of the model to predict hardness were related to protein, starch, and color differences. Slightly better prediction results were observed when the 550–1690 nm region was used compared with 950–1690 nm region across all sample sizes. For the 30‐kernel mass‐averaged model, the hardness prediction for 550–1690 nm spectra resulted in a coefficient of determination (R2) = 0.91, standard error of cross validation (SECV) = 7.70, and relative predictive determinant (RPD) = 3.3, while the 950–1690 nm had R2 = 0.88, SECV = 8.67, and RPD = 2.9. Average hardness of hard and soft wheat validation samples based on mass‐averaged spectra of 30 kernels was predicted and compared with the SKCS 4100 reference method (R2 = 0.88). Compared with the reference SKCS hardness classification, the 30‐kernel (550–1690 nm) prediction model correctly differentiated (97%) between hard and soft wheat. Monte Carlo simulation technique coupled with the SKCS 4100 hardness classification logic was used for classifying mixed wheat samples. Compared with the reference, the prediction model correctly classified mixed samples with 72–100% accuracy. Results confirmed the potential of using visible and near‐infrared reflectance spectroscopy of whole single kernels of wheat as a rapid and nondestructive measurement of bulk wheat grain hardness.  相似文献   

6.
Methods to quantify organic carbon (OC) in soil fractions of different stabilities often involve time-consuming physical and chemical treatments. The aim of the present study was to test a more rapid alternative, which is based on the spectroscopic analysis of bulk soils in the mid-infrared region (4000-400 cm−1), combined with partial least-squares regression (PLS). One hundred eleven soil samples from arable and grassland sites across Switzerland were separated into fractions of dissolved OC, particulate organic matter (POM), sand and stable aggregates, silt and clay particles, and oxidation resistant OC. Measured contents of OC in each fraction were then correlated by PLS with infrared spectra to obtain prediction models. For every prediction model, 100 soil spectra were used in the PLS calibration and the residual 11 spectra for validation of the models. Correlation coefficients (r) between measured and PLS-predicted values ranged between 0.89 and 0.97 for OC in different fractions. By combining different fractions to one labile, one stabilized and one resistant fraction, predictions could even be improved (r=0.98, standard error of prediction=16%). Based on these statistical parameters, we conclude that mid-infrared spectroscopy in combination with PLS is an appropriate and very fast tool to quantify OC contents in different soil fractions.  相似文献   

7.
This study aims to assess the performance of a low‐cost, micro‐electromechanical system‐based, near infrared spectrometer for soil organic carbon (OC) and total carbon (TC) estimation. TC was measured on 151 soil profiles up to the depth of 1 m in NSW, Australia, and from which a subset of 24 soil profiles were measured for OC. Two commercial spectrometers including the AgriSpecTM (ASD) and NeoSpectraTM (Neospectra) with spectral wavelength ranges of 350–2,500 and 1,300–2,500 nm, respectively, were used to scan the soil samples, according to the standard contact probe protocol. Savitzky–Golay smoothing filter and standard normal variate (SNV) transformation were performed on the spectral data for noise reduction and baseline correction. Three calibration models, including Cubist tree model, partial least squares regression (PLSR) and support vector machine (SVM), were assessed for the prediction of soil OC and TC using spectral data. A 10‐fold cross‐validation analysis was performed for evaluation of the models and devices accuracies. Results showed that Cubist model predicts OC and TC more accurately than PLSR and SVM. For OC prediction, Cubist showed R2 = 0.89 (RMSE = 0.12%) and R2 = 0.78 (RMSE = 0.16%) using ASD and NeoSpectra, respectively. For TC prediction, Cubist produced R2 = 0.75 (RMSE = 0.45%) and R2 = 0.70 (RMSE = 0.50%) using ASD and NeoSpectra, respectively. ASD performed better than NeoSpectra. However, the low‐cost NeoSpectra predictions were comparable to the ASD. These finding can be helpful for more efficient future spectroscopic prediction of soil OC and TC with less costly devices.  相似文献   

8.
Visible and near infrared spectroscopy (vis‐NIRS) may be useful for an estimation of soil properties in arable fields, but the quality of results are often variable depending on the applied chemometric approach. Partial least squares regression (PLSR) may be replaced by approaches which employ supervised learning methods or variable selection procedures in order to increase the proportion of informative wavelengths used in the estimation procedure, to reduce the noise of the spectra and to find the best fitting solution. Objectives were (1) to compare the usefulness of PLSR with either PLSR combined with a genetic algorithm (GA‐PLSR) or support vector machine regression (SVMR) for an estimation of soil organic carbon (SOC), total nitrogen (N), pH, cation exchange capacity (CEC) and soil texture for surface soils (0–5 cm, n = 144) of an arable field in Bangalore (India) and (2) to test and optimize different calibration strategies for GA‐PLSR for an improved estimation of soil properties. PLSR was useful for an estimation of SOC, N, sand and clay. In the cross‐validation (n = 96), accuracies of estimated soil properties generally decreased in the order GA‐PLSR > SVMR > PLSR. However, the order of estimation accuracies for the random validation sample (n = 48) changed to SVMR > GA‐PLSR > PLSR for SOC, N, pH, and CEC, whereas for clay the order changed to SVMR > PLSR > GA‐PLSR. A sequential procedure, which used the most frequently selected wavelengths of the GA‐PLSR runs, proved to be useful for an improved estimation of SOC and N. Overall, SVMR especially improved estimations of SOC and clay, whereas GA‐PLSR was particularly useful for SOC and N and it was the only approach which successfully estimated CEC in cross‐validation and validation.  相似文献   

9.
This paper reports the development and evaluation of a field technique for in situ measurement of root density using a portable spectroradiometer. The technique was evaluated at two sites in permanent pasture on contrasting soils (an Allophanic and a Fluvial Recent soil) in the Manawatu region, New Zealand. Using a modified soil probe, reflectance spectra (350–2500 nm) were acquired from horizontal surfaces at three depths (15, 30 and 60 mm) of an 80‐mm diameter soil core, totalling 108 samples for both soils. After scanning, 3‐mm soil slices were taken at each depth for root density measurement and soil carbon (C) and nitrogen (N) analysis. The two soils exhibited a wide range of root densities from 1.53 to 37.03 mg dry root g−1 soil. The average root density in the Fluvial soil (13.21 mg g−1) was twice that in the Allophanic soil (6.88 mg g−1). Calibration models, developed using partial least squares regression (PLSR) of the first derivative spectra and reference data, were able to predict root density on unknown samples using a leave‐one‐out cross‐validation procedure. The root density predictions were more accurate when the samples from the two soil types were separated (rather than grouped) to give sub‐populations (n = 54) of spectral data with more similar attributes. A better prediction of root density was achieved in the Allophanic soil (r2 = 0.83, ratio prediction to deviation (RPD ) = 2.44, root mean square error of cross‐validation (RMSECV ) = 1.96 mg g −1) than in the Fluvial soil (r2 = 0.75, RPD = 1.98, RMSECV = 5.11 mg g −1). It is concluded that pasture root density can be predicted from soil reflectance spectra acquired from field soil cores. Improved PLSR models for predicting field root density can be produced by selecting calibration data from field data sources with similar spectral attributes to the validation set. Root density and soil C content can be predicted independently, which could be particularly useful in studies examining potential rates of soil organic matter change.  相似文献   

10.
This paper reports the use of visible/near‐infrared reflectance spectroscopy (Vis‐NIRS) to predict pasture root density. A population of varying grass root densities was created by growing Moata ryegrass (Lolium multiflorum Lam.) for 72 days in pots of Ramiha silt loam (Allophanic) and Manawatu fine sandy loam (Recent Fluvial) (60 pots for each soil) differentially fertilized with nitrogen (N) and phosphorus (P) in a glass house experiment. At harvest, the reflectance spectra (350–2500 nm) from flat sectioned horizontal soil slices (1.3 cm depth), taken from 57 selected pots, were recorded using a portable spectroradiometer (ASD FieldSpec Pro, Boulder, CO). Root densities within each of the soil slices were measured using a wet sieving technique. A large variation in root densities (0.46–5.02 mg dry root cm?3) was obtained from the glass house experiment as plant growth responded to the different soils and rates of N and P fertilizer treatment. Pots of the Manawatu soil contained greater ryegrass root densities (1.76–5.02 mg dry root cm?3) than pots of the Ramiha soil (0.46–3.84 mg dry root cm?3). Each soil had visually distinct reflectance spectra in the range 470–2440 nm, but different root masses produced relatively small differences in reflectance spectra. The first two principal components (PC1 and PC2) of a principal component analysis of the first derivative of the spectral reflectance accounted for 71.3% of the spectral variance and clearly separated the Ramiha and Manawatu soils. PC1, which accounted for 58.4% of the spectral variance, was also well correlated to root density. Partial least squares regression (PLSR) of the first derivative of the 10 nm spaced spectral data against measured root densities produced calibration models that allowed quantitative estimates of root densities (without removing outlier, r2 cross‐validation = 0.78, ratio of prediction to deviation (RPD) = 2.14, root mean squares error of cross‐validation (RMSECV) = 0.60 mg cm?3; with removing outliers, r2 cross‐validation = 0.85, RPD = 2.63, RMSECV = 0.47 mg cm?3). The study indicated that spectral reflectance measurement has the potential to quantify root density in soils.  相似文献   

11.
A study was conducted to investigate methods of improving a near-infrared transmittance spectroscopy (NITS) amylose calibration that could serve as a rapid, nondestructive alternative to traditional methods for determining amylose content in corn. Calibrations were developed using a set of genotypes possessing endosperm mutations in single- and double-mutant combinations ranging in starch-amylose content (SAC) from -8.5 to 76%, relative to a standard curve. The influence of three factors were examined including comparing calibrations made against SAC versus grain amylose content (GAC), developing calibrations using partial least squares (PLS) analysis versus artificial neural networking (ANN), and using all samples in the calibrations set versus using progressively narrower ranges of SAC or GAC in the calibration set. Grain samples were divided into calibration and validation sets for PLS analysis while samples used in ANN were assigned to a training set, test set, and validation set. Performance statistics of the validation sets that were considered were the coefficient of determination (R), the standard error of prediction (SEP), and the ratio of the standard deviation of amylose values to the SEP (RPD), which were used to compare all NITS models. The study revealed an NITS prediction model for SAC (R = 0.96, SEP = 5.1%, RDP = 3.8) of similar precision to the best GAC model (R = 0.96, SEP = 2.7%, RPD = 3.5). Narrowing the amylose range of the calibration set generally did not improve performance statistics except for PLS models for SAC in which a decrease in SEP values was observed. In one model, the SEP improved while R and RPD remained constant (R = 0.94, SEP = 4.2%, RPD = 2.8) when samples with SAC values <20% were removed from the calibration set. Although the NITS amylose calibrations in this study are of limited precision, they may be useful when a rough screening method is needed for SAC. For example, NITS may be useful to detect severe contamination during transport and storage of specialty grains or to aid breeders when selecting for amylose content from large numbers of grain samples.  相似文献   

12.
  相似文献   

13.
Raindrop energy disintegrates soil aggregates and rearranges soil particles to form a structural crust on the upper soil layer. The structural crust affects the physical properties of the soil, which can be observed by significant colour changes on the soil surface. Spectral differences observed in the structural crust are caused by rearrangement of the soil surface texture, mainly an increase in the clay fraction. Previous studies conducted on crusted soils using reflectance spectroscopy were limited to a certain soil type or area and seemed to be strongly dependent on the small range of soil types. In the current study, the influence of raindrop energy on the NIR‐SWIR spectral reflectance (1200–2400 nm) of heterogeneous soils was evaluated and used in combination with partial least squares (PLS) regression to construct a model that correlates the infiltration rate (IR) with its reflectance. Four soils from Israel and three soils from the USA were studied to provide a single data set. A relatively small root mean square error of cross‐validation (RMSECV) of 15.2% was found. A ratio of prediction to deviation (RPD) value of 1.98 indicates a promising generic model. Additionally, PLS models were run on different combinations of soil types (RPD values ranging between 2.4 and 3.2). For all models, whether all soils were run in one cross‐validation data set, or run for different combinations of soils, the best assessment of IR was achieved when using reduced wavelength range (selected wavelengths based on Martens’ significance test selection). These results allowed us to conclude that a generic approach aimed at assessing the structural crust for a variety of soils is feasible. A generic model using the suggested spectral approach has the potential to provide NIR‐SWIR spectral soil IR predictions with either a local or global data base of soils worldwide and may contribute to improved protection of crusted soils from erosion or water loss by runoff.  相似文献   

14.
We used the specific surface area (SSA), the cation exchange capacity (CEC) and the content of dithionite‐extractable iron (Fed) to predict the content of organic carbon in illitic clay fractions of topsoils from loess. We determined SSA (BET‐N2 method) and CEC of clay fractions after removing organic C or reducing oxides or both. The CEC and the SSA of the carbon‐ and oxide‐free clay fraction explained 56% and 54% of the variation in C content, respectively. The Fed content of the clay fractions was strongly and negatively related to the C content, and with the SSA of the carbon‐free clay fraction it predicted C content almost completely (R2 = 0.96). The results indicate that the amount of cations adhering to the silicate clay minerals and the size of the silicate mineral surface area are important properties of the mineral phase for the storage potential of C. The reason for the negative relation between iron oxides and C content remains unclear.  相似文献   

15.
Many national and regional databases of soil properties and associated estimates of soil carbon stock consider organic, but not inorganic carbon (IC). Any future change in soil carbon stock resulting from the formation of pedogenic carbonates will be difficult to set in context because historical measurements or estimates of IC concentration and stock may not be available. In their article describing a database of soil carbon for the United Kingdom published in this journal, Bradley et al. [Soil Use and Management (2005) vol. 21, 363–369] only consider data for organic carbon (OC), despite the occurrence of IC‐bearing calcareous soils across a substantial part of southern England. Robust techniques are required for establishing IC concentrations and stocks based on available data. We present linear regression models (R2 between 0.8 and 0.88) to estimate IC in topsoil based on total Ca and Al concentrations for soils over two groups of primary, carbonate‐bearing parent materials across parts of southern and eastern England. By applying the regression models to geochemical survey data across the entire area (18 165 km2), we estimate IC concentrations on a regular 500‐m grid by ordinary kriging. Using bulk density data from across the region, we estimate the total IC stock of soil (0–30 cm depth) in this area to be 186 MtC. This represents 15.5 and 5.5% of the estimated total soil carbon stock (OC plus IC) across England and the UK, respectively, based on the data presented by Bradley et al. [Soil Use and Management (2005) vol. 21, 363–369]. Soil geochemical data could be useful for estimating primary IC stocks in other parts of the world.  相似文献   

16.
No‐tillage management can increase soil surface layer organic C (OC) levels compared with conventional tillage. The mechanisms underlying this increase in highly weathered tropical soils, such as Ferralsols, are not well established. The objective of this study was therefore to evaluate the influence of mineralogy on aggregation and the apportionment of OC across aggregate size fractions in a Brazilian Ferralsol under native vegetation (NV) and no‐tillage management for 10 (NT10) or 20 (NT20) yrs. Under native vegetation, soil OC generally increased with increasing aggregate size while, in response to changing management, soil OC increased in the order NT10 (8.8 g/kg) < NT20 (12.7 g/kg) < NV (19.1 g/kg). There were no significant differences in the mineralogy of the clay size fractions among the three treatments, with the notable exception of the CBD‐extractable Fe oxide fraction (FeCBD). The FeCBD fraction comprises various pedogenic Fe(hydr)oxides and increased from NT10 (33.9 g/kg) to NT20 (64.2 g/kg). The OC/FeCBD mass ratio within aggregates increased in the order NT10 <  NT20 <  NV while R2 values for OC and FeCBD occurrence follow this same trend, with the NT10 soil showing a weaker correlation (R2 = 0.178) compared with the NV soil (R2 = 0.533). We propose that formation of organo‐Fe(III) oxide associations is promoted with implementation of NT management and the consequent reduction in macroaggregate turnover. The development of the OC‐Fe(III) oxide associations and their evolution over time within aggregates to more thermodynamically stable entities will strongly influence the long‐term preservation of soil OC.  相似文献   

17.
The roles of fine-earth materials in the cation exchange capacity (CEC) of especially homogenous units of the kaolinitic and oxyhydroxidic tropical soils are still unclear. The CEC (pH 7) of some coarse-textured soils from southeastern Nigeria were related to their total sand, coarse sand (CS), fine sand (FS), silt, clay, and organic-matter (OM) contents before and after partitioning the dataset into topsoils and subsoils and into very-low-, low-, and moderate-/high-stability soils. The soil-layer categories showed similar CEC values; the stability categories did not. The CEC increased with decreasing CS but with increasing FS. Silt correlated negatively with the CEC, except in the moderate- to high-stability soils. Conversely, clay and OM generally impacted positively on the CEC. The best-fitting linear CEC function (R2, 68%) was attained with FS, clay, and OM with relative contributions of 26, 38, and 36%, respectively. However, more reliable models were attained after partitioning by soil layer (R2, 71–76%) and by soil stability (R2, 81–86%). Notably FS's contribution to CEC increased while clay's decreased with increasing soil stability. Clay alone satisfactorily modeled the CEC for the very-low-stability soils, whereas silt contributed more than OM to the CEC of the moderate- to high-stability soils. These results provide new evidence about the cation exchange behavior of FS, silt, and clay in structurally contrasting tropical soils.  相似文献   

18.
为更好地研究利用光谱反映的土壤重金属信息，实现具有多重金属复合污染问题的铅锌矿区土壤重金属含量高光谱快速估测，该研究以河北省某铅锌矿区为例，首先对研究区土壤的Cu、Cr、Ni、Zn、Cd、Pb污染状况进行了评价分析，其次基于实验室高光谱数据，组合变换光谱、特征变量和反演算法形成不同反演策略，通过各反演策略下的重金属反演精度比较，定量分析不同光谱预处理、特征选择和建模算法的优劣与适应性，构建最优反演模型。研究结果表明：1）研究区土壤Cr、Ni清洁程度较好，其余Cu、Zn、Cd、Pb均有不同程度污染；参比当地土壤背景值，区域内梅罗综合污染指数均值29.7，为重度污染，潜在生态风险因子均值1330.3，处于高生态风险状态；2）光谱预处理可以增强土壤重金属信息表达。其中，光谱微分效果较好，但易受噪声影响，而多元散射校正、标准正态变量、倒数对数变换可以进行光谱去噪，提升处理效果；3）特征选择方法中，相关系数法选择特征波段数目多，不同重金属反演R2 差异较大；Boruta法选择特征波段数目少，不同重金属反演R2 差异较小；4）BPNN、XGBoost可以较好描述重金属含量与光谱的非线性关系，相较于其他算法具有更好表现，分别实现了Cr、Ni、Zn和Pb、Cd的最优反演，SVMR实现了Cu的最优反演。研究表明，不同的光谱预处理、特征选择与建模算法对于土壤重金属含量的反演均具有较大影响，选择合适的处理、建模算法可以有效提升反演精度。该研究为进一步实现高效、准确、大范围遥感监测铅锌矿区土壤重金属污染状况提供参考依据。  相似文献   

19.
We investigated the use of piecewise direct standardization (PDS) to remove the effects of water and other environmental factors from proximally sensed (field) visible–near infrared (vis–NIR) spectra. Our hypothesis was that the PDS‐standardized field spectra can be used to predict soil carbon effectively with calibrations derived from existing spectroscopic databases of spectra recorded in the laboratory on dried, ground and sieved samples. In our experiments we used field spectra recorded in situ with a portable spectrometer at 124 sites in 11 paddy fields in Zhejiang Province, China. We sampled the soil at these same sites, recorded their spectra in the laboratory and measured their soil organic carbon (SOC) contents with a conventional laboratory technique. Two‐thirds of the samples were used to relate the laboratory spectra to SOC by partial least squares regression (PLSR), and the remaining one‐third was used as an independent validation dataset. We selected a representative set of samples from corresponding field and laboratory spectra that we could use as the PDS transfer set. Piecewise direct standardization was used to relate each wavelength in the laboratory spectra to the corresponding wavelength and its neighbours in the field spectra. The field spectra of the validation samples were then corrected with PDS so that they acquired the characteristics of the spectra measured under laboratory conditions. The approach was evaluated by (i) quantifying the similarity between the PDS‐standardized spectra and their corresponding laboratory spectra, (ii) measuring the accuracy of their SOC predictions on the independent validation dataset and (iii) comparing these results with those of direct standardization (DS). Both PDS and DS led to considerable improvements in the predictions of SOC (R2 = 0.71, R2 = 0.60, respectively), compared with those with original field spectra (R2 = 0.03). However, fewer transfer samples were needed with PDS to obtain similar results.  相似文献   

20.
This work aimed to evaluate the potential of mid‐infrared reflectance spectroscopy (MIRS) to predict soil organic and inorganic carbon contents with a 2086‐sample set representative of French topsoils (0–30 cm). Ground air‐dried samples collected regularly using a 16 × 16‐km grid were analysed for total (dry combustion) and inorganic (calcimeter) carbon; organic carbon was calculated by difference. Calibrations of MIR spectra with partial least square regressions were developed with 10–80% of the set and five random selections of samples. Comparisons between samples with contrasting organic or inorganic carbon content and regression coefficients of calibration equations both showed that organic carbon was firstly associated with a wide spectral region around 2500–3500 cm?1 (which was a reflection of its complex nature), and inorganic carbon with narrow spectral bands, especially around 2520 cm?1. Optimal calibrations for both organic and inorganic carbon were achieved by using 20% of the total set: predictions were not improved much by including more of the set and were less stable, probably because of atypical samples. At the 20% rate, organic carbon predictions over the validation set (80% of the total) yielded mean R2, standard error of prediction (SEP) and RPD (ratio of standard deviation to SEP) of 0.89, 6.7 g kg?1 and 3.0, respectively; inorganic carbon predictions yielded 0.97, 2.8 g kg?1 and 5.6, respectively. This seemed appropriate for large‐scale soil inventories and mapping studies but not for accurate carbon monitoring, possibly because carbonate soils were included. More work is needed on organic carbon calibrations for large‐scale soil libraries.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号