关键词:
Estimation mechanism;Predictive model;Proximal soil sensing;Soil heavy metal;Spectral derivative
摘要:
Heavy metal contamination of peri-urban agricultural soil is detrimental to soil environmental quality and human health. A rapid assessment of soil pollution status is fundamental for soil remediation. Heavy metals can be monitored by visible and near-infrared spectroscopy coupled with chemometric models. First and second derivatives are two commonly used spectral preprocessing methods for resolving overlapping peaks. However, these methods may lose the detailed spectral information of heavy metals. Here, we proposed a fractional-order derivative (FOD) algorithm for preprocessing reflectance spectra. A total of 170 soil samples were collected from a typical peri-urban agricultural area in Wuhan City, Hubei Province. The reflectance spectra and lead (Pb) and zinc (Zn) concentrations of the samples were obtained in the laboratory. Two calibration methods, namely, partial least square regression and random forest (RF), were used to establish the relation between the spectral data and the two heavy metals. In addition, we aimed to explore the use of spectral estimation mechanism to predict the Pb and Zn concentrations. Three model evaluation parameters, namely, coefficient of determination (R(2)), root mean squared error, and ratio of performance to inter-quartile range (RPIQ), were used. Overall, the spectral reflectance decreased with the increase in Pb and Zn contents. The FOD algorithm gradually removed spectral baseline drifts and overlapping peaks. However, the spectral strength slowly decreased with the increase in fractional order. High fractional-order spectra underwent more spectral noises than low fractional-order spectra. The optimal prediction accuracies were achieved by the 0.25- and 0.5-order reflectance RF models for Pb (validation R(2)=0.82, RPIQ=2.49) and Zn (validation R(2)=0.83, RPIQ=2.93), respectively. A spectral detection of Pb and Zn mainly relied on their covariation with soil organic matter, followed by Fe. In summary, our results provided theoretical bases for the rapid investigation of Pb and Zn pollution areas in peri-urban agricultural soils.
作者机构:
[Nie Yan; Yu Lei; Yi Jun; Zhang Tao; Zhou Yong] Cent China Normal Univ, Hubei Prov Key Lab Anal & Simulat Geog Proc, Wuhan 430079, Hubei, Peoples R China.;[Nie Yan; Yu Lei; Yi Jun; Zhang Tao; Zhou Yong] Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Hubei, Peoples R China.;[Nie Yan; Yu Lei; Yi Jun; Zhang Tao; Zhou Yong] Cent China Normal Univ, Res Inst Sustainable Dev, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Yu Lei] C;Cent China Normal Univ, Hubei Prov Key Lab Anal & Simulat Geog Proc, Wuhan 430079, Hubei, Peoples R China.;Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Hubei, Peoples R China.;Cent China Normal Univ, Res Inst Sustainable Dev, Wuhan 430079, Hubei, Peoples R China.
摘要:
Accurate estimation of soil organic matter (SOM) is essential in understanding the spatial distribution of SOM to identify areas that need fertilization and the required grade of those fertilizers. Visible and near-infrared spectroscopy is a promising alternative to time consuming and costly conventional soil assessment methods. However, this approach is highly dependent on selecting suitable preprocessing strategies and data mining techniques for regression analysis. In this study, 2D correlation coefficients, including ratio, difference, and normalized difference indices, were introduced to select sensitive spectral parameters. The performance of extreme learning machine (ELM) was evaluated via comparison with that of support vector machine (SVM) for SOM estimation. A total of 257 soil samples were collected from Hubei Province, Central China, with SOM contents and reflectance spectra measured in the laboratory. Five spectral pretreatments, except for the raw spectra, were applied. SVM and ELM models were calibrated on spectral parameters selected by one-dimensional and 2D correlation coefficients and subsequently applied to predict SOM. Results showed that 2D correlation coefficient can effectively highlight the detailed SOM information compared with that of one-dimensional correlation coefficient. The ELM models yielded superior predictability relative to SVM models in all eight established models. The most excellent estimation accuracy was obtained by 2D ratio index and ELM (TRI-ELM) method, with an independent validation R-2 and a ratio of performance to interquartile range of 0.83 and 3.49, respectively. The SOM fertility levels of predicted SOM showed that TRI-ELM method presented the largest similarity to laboratory-measured SOM levels, and misclassified samples were all concentrated within one error level. In summary, our study indicates that the TRI-ELM model is a rapid, inexpensive, and relatively accurate method for identifying SOM fertility level. (c) 2018 Elsevier B.V. All rights reserved.
关键词:
Fuzzy k-means clustering;Normalized soil moisture index;Partial least square-support vector machine;Soil moisture;Soil organic matter;Visible and near-infrared spectroscopy
摘要:
Soil organic matter (SOM) is an important parameter of soil fertility, and visible and near-infrared (VIS-NIR) spectroscopy combined with multivariate modeling techniques have provided new possibilities to estimate SOM. However, the spectral signal is strongly influenced by soil moisture (SM) in the field. Interest in using spectral classification to predict soils in themoist conditions tominimize the influence of SMis growing. The objective of this study was to investigate the transferability of two approaches, SM-based clustermethod with known SM(classifying the VIS-NIR spectra into different SM clusters to develop models separately), the normalized soil moisture index (NSMI)-based cluster method with unknown SM(utilizing NSMI to indicate the SMand establish models separately), to predict SOM directly inmoist soil spectra. One hundred and twenty one soil sampleswere collected fromCentral China, and eight SM levels were obtained for each sample through rewetting experiments. Their reflectance spectra and SOMconcentrations were measured in the laboratory. Partial least square-support vector machine (PLS-SVM) was employed to construct SOMprediction models. Specifically, prediction models were developed for NSMI-based clusters with unknown SMdata. The models were assessed through three statistics in the processes of calibration and validation: the coefficient of determination (R<sup>2</sup>), root mean square error (RMSE) and the ratio of the performance to deviation (RPD). Results showed that the variable SMled to reduced VIS-NIR reflectance nonlinearly across the entire spectral range. NSMI was an effective spectral index to indicate the SM. Classifying the VIS-NIR spectra into different SMclusters in known SMstates could improve the performance of PLS-SVMmodels to acceptable prediction accuracies (R<sup>2</sup><inf>cv</inf>= 0.69-0.77, RPD = 1.79-2.08). The estimation of SOM, when using the NSMI-based cluster method with unknown SM(RPD = 1.95-2.04), was similar to the use of the SM-based cluster method with known SM (RPD = 1.79-2.08). The predictive results (RPD = 1.87-2.06) demonstrated that the NSMI-based cluster method has potential for application outside the laboratory for SOMprediction without knowing the SMexplicitly, and this method is also easy to carry out and only requires spectral information.<br/>
期刊:
Soil Science Society of America Journal,2018年82(5):1231-1242 ISSN:0361-5995
通讯作者:
Chen, Yiyun;Liu, Yanfang
作者机构:
[Hong, Yongsheng; Chen, Yiyun; Liu, Yanfang; Cheng, Hang; Liu, Yaolin; Liu, Yi] Wuhan Univ, Sch Resource & Environ Sci, Wuhan 430079, Hubei, Peoples R China.;[Hong, Yongsheng; Cheng, Hang; Chen, Yiyun] Chinese Acad Sci, State Key Lab Soil & Sustainable Agr, Nanjing 210008, Jiangsu, Peoples R China.;[Zhang, Yong] Anhui Univ Finance & Econ, Sch Publ Finance & Admin, Bengbu 233030, Peoples R China.;[Yu, Lei] Cent China Normal Univ, Sch Urban & Environ Sci, Wuhan 430079, Hubei, Peoples R China.;[Yu, Lei] Cent China Normal Univ, Key Lab Geog Proc Anal & Simulat Hubei Prov, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Chen, YY; Liu, YF] W;[Chen, Yiyun] C;Wuhan Univ, Sch Resource & Environ Sci, Wuhan 430079, Hubei, Peoples R China.;Chinese Acad Sci, State Key Lab Soil & Sustainable Agr, Nanjing 210008, Jiangsu, Peoples R China.
摘要:
Visible and near infrared (Vis-NIR) spectroscopy technique has been shown to be a cost-effective alternative for rapidly analyzing soil organic carbon (SOC). However, great challenges remain when applying a Vis-NIR model for SOC estimation developed in one study area to other study areas without further calibration. The scope of this study was to use spiking strategy to improve the transferability of Vis-NIR models between two study areas. Specifically, we explored the optimal spiking subset by adding different quantities of spiking samples to construct different-sized models, and the strategy of spiking with extra-weighting was used for comparison. Soil data was acquired in two independent study areas (WH area and HH area) in Hubei Province, Central China. The reflectance spectra and SOC contents were measured in the laboratory. Partial least squares regression (PLSR) was used for model calibration. The representativeness of the spiking samples was assessed through the absolute difference between the selected sample variance (s(2)) and the original variance (sigma(2)) in the principal component space derived from soil spectra. Results showed that the initial models yielded successful SOC predictions for the soil samples from the same area as the calibration samples, but failed in those samples from the other area. Spiking improved the model transferability between these two study areas. Approximately 33%/48% of the HH/WH calibration set was required as spiking samples in model calibrations and applications in the other area. Spiking with extra-weighting was of limited use in small-sized spectral libraries. The use of vertical bar s(2)-sigma(2)vertical bar is potentially effective in identifying the optimal spiking samples to improve model transferability between different small-sized study areas in the Vis-NIR assessments of SOC.
摘要:
【目的】快速、准确地监测土壤有机质对于精准农业的发展具有重要意义。可见光-近红外(visible and near-infrared,Vis-NIR)光谱技术在土壤属性估算、数字化土壤制图等方面应用较为广泛,然而,在田间进行光谱测量,易受土壤含水量(soil moisture,SM)、温度、土壤表面状况等因素的影响,导致光谱信息中包含大量干扰信息,其中,SM变化是影响光谱观测结果最为显著的因素之一。此研究的目的是探讨OSC算法消除其影响,提升Vis-NIR光谱定量估算土壤有机质(soil organic matter,SOM)的精度。【方法】以江汉平原公安县和潜江市为研究区域,采集217份耕层(0-20 cm)土壤样本,进行风干、研磨、过筛等处理,采用重铬酸钾-外加热法测定SOM;将总体样本划分为3个互不重叠的样本集:建模集S~0(122个样本)、训练集S~1(60个样本)、验证集S~2(35个样本);设计SM梯度试验(梯度间隔为4%),在实验室内获取S~1和S~2样本集的9个梯度SM(0%-32%)的土壤光谱数据;分析SM对土壤Vis-NIR光谱反射率的影响,采用外部参数正交化算法(external parameter orthogonalization,EPO)、正交信号校正算法(orthogonal signal correction,OSC)消除SM对土壤光谱的干扰;利用主成分分析(principal component analysis,PCA)的前两个主成分得分和光谱相关系数两种方法检验消除SM干扰前、后的效果;基于偏最小二乘回归(partial least squares regression,PLSR)方法建立EPO和OSC处理前、后的SOM估算模型,利用决定系数(coefficient of determination,R~2)、均方根误差(root mean square error,RMSE)和RPD(the ratio of prediction to deviation)3个指标比较PLSR、EPO-PLSR、OSC-PLSR模型的性能。【结果】土壤Vis-NIR光谱受SM的影响十分明显,随着SM的增加,土壤光谱反射率呈非线性降低趋势。OSC处理前的湿土光谱数据主成分得分散点相对分散,与干土光谱数据主成分得分空间的位置不重叠,不同SM梯度之间的光谱相关系数变化较大;OSC处理后的湿土光谱数据主成分得分空间的位置基本与干土光谱数据相重合,各样本光谱数据之间相似性很高,不同SM梯度之间的光谱相关系数变化较小。9个SM梯度的EPO-PLSR模型的验证平均R_(pre)~2、RPD分别为0.69、1.7。9个SM梯度的OSC-PLSR模型的验证平均R_(pre)~2、RPD分别为0.72、1.89,校正后的OSC-PLSR模型受SM的较小,有效提升SOM估算模型的精度和鲁棒性。【结论】OSC能够消除SM变化对土壤Vis-NIR光谱的影响,可为将来田间原位实时监测SOM信息提供一定的理论支撑。