共查询到20条相似文献,搜索用时 171 毫秒
1.
2.
3.
4.
5.
蚁群算法在土壤质地高光谱预测建模中的应用 总被引:1,自引:0,他引:1
为提高土壤质地高光谱预测模型精度,以巢湖流域177个土样光谱为基础数据源,运用蚁群算法选择特征波长,结合BP神经网络构建土壤质地光谱预测模型,并与全光谱构建的光谱预测模型进行比较。结果表明,运用蚁群算法选择特征波长构建的光谱预测模型精度优于全光谱构建的预测模型精度,土壤粉粒含量预测模型预测集决定系数R2为0.76,RPIQ为2.23,土壤砂粒含量预测模型预测集决定系数R2为0.72,RPIQ为1.94;全光谱土壤粉粒含量预测模型预测集R2为0.57,RPIQ为1.75,全光谱土壤砂粒含量预测模型预测集R2为0.48,RPIQ为1.82。运用蚁群算法选择光谱特征波长建模,减少了数据冗余,提高了预测模型精度。 相似文献
6.
7.
快速测量土壤剖面重金属含量是评估土壤重金属污染状况并选择相应修复技术的关键。为了探讨可见光-近红外光谱法(Visible and Near-Infrared Reflectance Spectroscopy,VNIR)预测原状土壤剖面重金属含量的潜力,以江西省两个典型工矿厂周边农田土壤为研究对象,共采集了19个深度约100 cm的完整土壤剖面样品,分别测定土壤剖面样品的VNIR数据及其Cu含量。采用偏最小二乘回归法(Partial Least Squares Regression,PLSR)、Cubist混合线性回归决策树(Cubist Regression Tree,Cubist)、高斯过程回归(Gaussian Process Regression,GPR)和支持向量机(Support Vector Machine Regression,SVM)方法研究不同光谱预处理方法对土壤Cu含量预测精度的影响。结果显示,Cubist、GPR和SVM这三种机器学习算法的预测精度普遍高于PLSR,其中一阶导数(First-Order Derivative,FD)预处理的SVM模型预测精度最高(R2=0.95,均方根误差为7.94 mg/kg,相对分析误差为4.34)。这表明利用VNIR和机器学习可以对原状土壤剖面Cu含量进行有效预测,为快速监测Cu及其他重金属含量的相关研究提供参考。 相似文献
8.
喀斯特峰丛洼地不同植被类型土壤微生物量碳氮磷和养分特征 总被引:1,自引:0,他引:1
9.
平原区土壤质地的反射光谱预测与地统计制图 总被引:3,自引:3,他引:3
基于地统计方法的土壤属性制图通常需要大量的采样与实验室测定。本研究提出利用可见光近红外(visible-nearinfrared spectroscopy,VNIR)光谱技术测定替代实验室测定,并与地统计方法相结合预测土壤质地的空间变异。通过建立砂粒(0.02 mm),粉粒(0.002~0.02 mm),黏粒(0.002 mm)含量的VNIR光谱预测模型,将模型预测得到的质地数据和建模点实测质地数据一同用于地统计分析和Kriging插值制图。以江苏北部黄淮平原地区为案例的研究结果表明,砂粒、粉粒、黏粒含量的预测值和实测值的均方根误差(RMSE)分别为8.67%、6.90%3、.51%,平均绝对误差(MAE)分别为6.46%、5.60%、3.05%,显示了较高的预测精度。研究为快速获取平原区土壤质地空间分布提供了新的可能的途径。 相似文献
10.
黑土养分含量的航空高光谱遥感预测 总被引:3,自引:3,他引:0
为监测黑龙江省黑土典型区土壤的养分元素含量,综合利用统计理论与光谱分析方法,研究建三江农场黑土土壤的3类养分含量与土壤光谱之间的关系,建立土壤全氮、有效磷、速效钾含量高光谱反演模型,实现土壤养分元素含量定量预测。对黑土土壤航空高光谱数据进行处理,应用偏最小二乘回归(PLSR)和BP神经网络方法分别建立土壤养分元素含量的高光谱定量反演模型,结果表明:全氮PLSR和BP神经网络预测模型的RPIQ值(样本观测值第三和第一四分位数之差与均方根误差的比值)分别为2.42和2.80;有效磷PLSR和BP神经网络模预测型的RPIQ值分别为0.83和1.67;速效钾PLSR和BP神经网络模型的RPIQ值分别为2.00和2.33。试验证明土壤全氮和速效钾的光谱定量预测模型具备较好的精度和预测能力。但有效磷的预测效果不是特别理想,仅可达到近似定量预测的要求;全氮、有效磷和速效钾的预测精度,BP神经网络建模相比偏最小二乘建模有更好的精度和预测能力,预测精度分别提高6.5%、10.1%和6.6%。 相似文献
11.
Combining global soil-spectral libraries with local calibration samples has the potential to provide improved visible and near-infrared (VNIR, 400–2500 nm) diffuse reflectance spectroscopy (DRS) soil characterization predictions than with either global or local calibrations alone. In this study, a geographically diverse “global” soil-spectral library with 4184 samples was augmented with up to 418 “local” calibration soil samples distributed across a 2nd-order Ugandan watershed to predict the amount of clay-size material (CLAY), soil organic carbon (SOC) and proportion of expansible 2:1 clays (termed “montmorillonite” or MT in the global library). Stochastic gradient boosted regression trees (BRT) were employed for model construction, with a variety of calibration and validation schemes tested. Using the global library combined with 13- and 14-fold cross-validation by local profile for CLAY and SOC, respectively, yielded dambo/upland RMSD values of 89/68 g kg− 1 for CLAY (N = 429/410) and 4.2/2.6 g kg− 1 for SOC (N = 272/105). These results were obtained despite the challenge of combining spectral libraries constructed using different spectroradiometers and laboratory reference measurements (total combustion vs. Walkley–Black, hydrometer vs. pipette). Using only the global library, a VNIR-derived index of MT content was significantly correlated with the square root of X-ray diffraction (XRD) MT peak intensity for local dambo soils (r2 = 0.52, N = 59, p < 0.0001), an acceptable result given the semi-quantitative nature of the reference XRD method. Though VNIR predictions did not approach laboratory precision, for soil-landscape modeling VNIR characterization worked remarkably well for clay mineralogy, was adequate for mapping dambo “depth to 35% clay”, and was insufficiently accurate for SOC mapping. 相似文献
12.
13.
Prediction of atrazine sorption coefficients in soils using mid-infrared spectroscopy and partial least-squares analysis 总被引:1,自引:0,他引:1
Kookana RS Janik LJ Forouzangohar M Forrester ST 《Journal of agricultural and food chemistry》2008,56(9):3208-3213
This study explored the potential of mid-infrared spectroscopy (MIR) with partial least-squares (PLS) analysis to predict sorption coefficients (Kd) of pesticides in soil. The MIR technique has the advantage of being sensitive to both the content and the chemistry of soil organic matter and mineralogy, the important factors in the sorption of nonionic pesticides. MIR spectra and batch Kd values of atrazine were determined on a set of 31 soil samples as reference data for PLS calibration. The samples, with high variability in soil organic carbon content (SOC), were chosen from 10 southern Australian soil profiles (A1, A2, B, and C in one case). PLS calibrations, developed for the prediction of Kd from the MIR spectra and reference Kd data, were compared with predictions from Koc-based indirect estimation using SOC content. The reference Kd data for the 31 samples ranged from 0.31 to 5.48 L/kg, whereas Koc ranged from 30 to 680 L/kg. Both coefficients generally increased with total SOC content but showed a relatively poor coefficient of determination (R2 = 0.53; P > 0.0001) and a high standard error of prediction (SEP =1.22) for the prediction of Kd from Koc. This poor prediction suggested that total SOC content alone could explain only half of the variation in Kd. In contrast, the regression plot of PLS predicted versus measured Kd resulted in an improved correlation, with R2 = 0.72 ( P > 0.0001) and standard error of cross-validation (SECV) = 0.63 for three PLS factors. With the advantages of MIR-PLS in mind, (i) more accurate prediction of Kd, (ii) an ability to reflect the nature and content of SOC as well as mineralogy, and (iii) high repeatability and throughput, it is proposed that MIR-PLS has the potential for an improved and rapid assessment of pesticide sorption in soils. 相似文献
14.
长期秸秆还田显著降低褐土底层有机碳储量 总被引:2,自引:0,他引:2
[目的]秸秆还田作为一种有效的培肥方式,对土壤固碳效果显著,但对于深层土壤有机碳的影响还存在不确定性.分析不同秸秆还田方式下褐土剖面土壤有机碳(SOC)储量变化,为褐土区秸秆还田措施优化和固碳减排等提供科学依据.[方法]长期秸秆还田试验开始于1992年,采用裂区设计,主区为化肥春季和秋季施用,副区为4个秸秆还田处理:秸... 相似文献
15.
16.
【目的】揭示广东罗浮山不同海拔高度土壤颗粒组成分形维数特征的分布规律。【方法】在广东罗浮山不同海拔高度的10个土壤采样点挖掘剖面,采集各发生层土壤,测定了土壤颗粒组成、有机碳(SOC)、全铁(Fet)、游离铁(Fed)、无定形铁(Feo)、阳离子交换量(CEC)等理化性质,分析了土壤颗粒分形维数与海拔、土壤颗粒分布及化学性质之间的相关关系。【结果】随着土层深度的增加,土壤颗粒分形维数先增加后减小;随着海拔的升高,土壤黏粒含量、颗粒分形维数均呈减小趋势,且与海拔高度均呈极显著相关关系;随土壤质地的变细,分形维数平均值由2.7601上升到了2.8954,即分形维数随土壤质地的变细而增大;颗粒分形维数与砂粒呈极显著负相关关系,与黏粒呈极显著正相关关系;分形维数与SOC、Feo、Feo/Fed、CEC呈极显著或显著负相关关系,与Fet、Fed含量表现为极显著正相关关系;通径分析表明Fet、Fe 相似文献
17.
18.
Mid‐infrared spectroscopy (MIRS) is a well‐established analytical tool for qualitative and quantitative analysis of soil samples. However, effects of soil sample grinding procedures on the prediction accuracy of MIR models and on qualitative spectral information have not been well investigated and, in consequence, not standardized up to now. Further, the effects of soil sample selection on the accuracy of MIR prediction models has not been quantified yet. This study investigated these effects by using 180 well‐characterized soil samples that were ground for different times (0, 2 or 4 minutes) and then used for MIR measurements. To study the impact of sample preparation, soil spectra were subjected to principal component analyses (PCA), multiple regression and partial least square (PLS) analysis. The results indicate that the prediction accuracy of MIR models for soil organic carbon (SOC) and pH and the qualitative spectral information were better overall for lightly ground (2 minutes) soil samples compared with intensively (4 minutes) or unground soil samples. Whereas the grinding procedure did not show any effect on spectra of clay minerals, spectral information for quartz and for SOC was modified. Even though it is difficult to recommend a global standardized soil sample grinding procedure for MIR measurements because of different mill types available within laboratories, we highly recommend using an internally standardized grinding procedure. Moreover, we show that neither land use nor soil sampling depth influences the prediction of the SOC content. However, sand and clay content substantially affect the score vectors used by the PLS algorithm to predict the SOC content. Thus, we recommend using soil samples similar in texture for more precise SOC calibration models for MIR spectroscopy. 相似文献
19.
长期施肥下三种旱作土壤有机碳含量及其矿化势比较研究 总被引:1,自引:0,他引:1