应用集成BP神经网络进行田间土壤空间变异研究

以英国北爱尔兰Hayes的一块牧草地为研究区，将所有样点分为独立的训练和检验数据集，并在训练样点集的基础上设计了其他4种样点布局方案，以研究神经网络集成技术应用于田间土壤性质空间变异性的可能性。与广泛应用的克里格法的试验结果相比，集成BP神经网络的插值结果精度与之基本相当，尤其是在样点分布较稀疏和样点数较少的情况下，集成BP网络表现出明显的优势；由于神经网络集成方法对样本数据的分布没有任何要求，因此具有较广泛的应用前景和潜力，并在不符合克里格法对样本数据分布要求的情况下是一种可行的替代方法。     

Neural network ensemble residual kriging application for spatial variability of soil properties

High quality, agricultural nutrient distribution maps are necessary for precision management, but depend on initial soil sample analyses and interpolation techniques. To examine the methodologies for and explore the capability of interpolating soil properties based on neural network ensemble residual kriging, a silage field at Hayes, Northern Ireland, UK, was selected for this study with all samples being split into independent training and validation data sets. The training data set, comprised of five soil properties: soil pH, soil available P, soil available K, soil available Mg and soil available S,was modeled for spatial variability using 1) neural network ensemble residual kriging, 2) neural network ensemble and 3) kriging with their accuracies being estimated by means of the validation data sets. Ordinary kriging of the residuals provided accurate local estimates, while final estimates were produced as a sum of the artificial neural network (ANN) ensemble estimates and the ordinary kriging estimates of the residuals. Compared to kriging and neural network ensemble,the neural network ensemble residual kriging achieved better or similar accuracy for predicting and estimating contour maps. Thus, the results demonstrated that ANN ensemble residual kriging was an efficient alternative to the conventional geo-statistical models that were usually used for interpolation of a data set in the soil science area.     

基于BP神经网络插值的土壤全氮空间变异

大尺度土壤养分空间变异研究可以为土壤改良分区治理提供基础数据。寻求合适的取样数和插值方法是进行土壤养分空间变异研究的关键。以安徽省舒城县为例,共取得0～20cm土壤表层样品523个,土壤全氮的空间变异由BP神经网络插值方法在不同取样数条件下获得,通过与克里格插值法进行比较得出:样本数在100个时,神经网络插值的预测吻合度(G)比克里格插值高7.75%,均方根误差(RMSE)低0.1,总体精度优于克里格;样本数大于200时,神经网络插值和克里格插值精度基本相同,随着采样数量增加,两种方法的插值精度也在提高,并逐步趋于平稳。在大尺度土壤养分空间变异研究中,在小样本情况下,神经网络插值具有优势。     

紫色土丘陵地区农田土壤养分空间分布预测

为深入研究紫色土丘陵区农田土壤养分空间分布规律,在GIS技术的支持下,利用研究区450个土壤实测数据,结合地形因子和土地利用类型,运用多重线性回归构建了土壤养分预测模型,对养分的空间分布进行预测。结果表明,土壤有机质和碱解氮含量与地形因子之间的相关性较强,有效磷和速效钾含量与地形因子之间的相关性较弱。土壤水田和旱地中有机质、碱解氮和有效磷含量均值间的差异显著(P<0.01),速效钾之间不显著(P=0.34)。基于地形因子的土壤养分预测模型与基于地形因子和土地利用方式组合的土壤养分预测模型预测结果精度对比表明,在预测变量中增加土地利用类型对提高预测模型的拟合度和预测精度作用非常微小,且仅用地形因子预测土壤养分的空间分布更方便,因此选用该模型对验证集数据进行预测。以验证集数据进行预测结果与实测值进行比较,结果显示预测值与实测值之间的差异甚小,有机质、碱解氮、有效磷和速效钾的相对偏差分别为0.09、0.19、0.08和0.12,均方根误差分别为1.38、3.42、1.03和1.57,说明基于地形因子的土壤养分预测模型的精度较高,可以很好地预测土壤养分分布规律。该研究结果可为丘陵地区农田合理施肥提供理论依据。     

Spatial modeling of soil salinity using multiple linear regression,ordinary kriging and artificial neural network methods

Salinity as an important property of soil plays a major role in reducing the fertility in the world. Accurate information about the spatial change of soil salinity is essential for sustainable soil management and utilization in agriculture lands. For this purpose, 150 soil samples were collected from Dashte-e-Tabriz Iran and tested and soil salinity was estimated by land surface parameters including elevation, aspect, length of slope, wetness index, slope and normalized difference vegetation index as basic parameters. In order to model and predict the salinity, ordinary kriging (OK), artificial neural networks (ANN) and multiple linear regressions (MLR) were used. Accuracy of models was evaluated by the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE). Based on Pearson correlation, elevation, normalized difference vegetation and wetness indices were selected for soil salinity spatial modeling from six land surface parameters. The results showed that the ANN had the lowest RMSE and highest R2. The values of R2, RMSE and MAE were 0.36, 25.89 and 17.06 for regression and 0.56, 17.70 and 13.05 for OK and 0.69, 16.06 and 11.60 for ANN, respectively, which indicated more accuracy of ANN in comparison with MLR and OK.     

基于计算机视觉的番茄缺素神经网络识别

提出了采用不受植株叶片大小和背景影响的色调域平均百分率直方图来提取番茄叶片的颜色特征,用于识别番茄是否缺乏营养元素;提出了采用基于最大差分算子的色调域百分率直方图法、灰度－梯度共生矩阵法和小波分析法提取番茄缺素叶片的纹理特征,用于识别番茄缺何种营养元素;设计了番茄缺N、缺Fe、缺Mg的BP神经网络系统,综合识别结果为：正常中叶、正常新叶、缺铁新叶,缺氮中叶、缺镁中叶的识别准确率依次为95％、92.5％、92.5％、87％、87％。     

基于地形属性使用回归, 克里格和人工神经网络方法估算饱和导水率空间分布

Several methods,including stepwise regression,ordinary kriging,cokriging,kriging with external drift,kriging with varying local means,regression-kriging,ordinary artificial neural networks,and kriging combined with artificial neural networks,were compared to predict spatial variation of saturated hydraulic conductivity from environmental covariates.All methods except ordinary kriging allow for inclusion of secondary variables.The secondary spatial information used was terrain attributes including elevation,slope gradient,slope aspect,profile curvature and contour curvature.A multiple jackknifing procedure was used as a validation method.Root mean square error (RMSE) and mean absolute error (MAE) were used as the validation indices,with the mean RMSE and mean MAE used to judge the prediction quality.Prediction performance by ordinary kriging was poor,indicating that prediction of saturated hydraulic conductivity can be improved by incorporating ancillary data such as terrain variables.Kriging combined with artificial neural networks performed best.These prediction models made better use of ancillary information in predicting saturated hydraulic conductivity compared with the competing models.The combination of geostatistical predictors with neural computing techniques offers more capability for incorporating ancillary information in predictive soil mapping.There is great potential for further research and development of hybrid methods for digital soil mapping.     

基于RBF神经网络的土壤有机质空间变异研究方法

通过研究土壤性质的空间变异和空间插值方法,快速准确获取土壤性质的空间分布是精确农业和环境保护的基础。该文以四川眉山一块约40 km2的区域为试验区,采集表层土壤（0～20 cm）样点80个,利用径向基函数(RBF)神经网络建立空间坐标和邻近样点与土壤有机质间的非线性映射关系（RBF2）,模拟土壤有机质的空间分布。与普通克里法（OK）和仅以坐标为网络输入的神经网络方法（RBF1）相比,RBF2的插值精度有显著的提高;相同样点密度下其相对预测误差分别较OK和RBF1减小了9.87%、1.97%（样本A）和13.09%、2.36%（样本B）;即使样点数减半的情况下RBF2的相对预测误差也分别较OK和RBF1减小了10.23%和2.33%,并且插值图差异相对较小,可以更好地反映土壤有机质空间分布的异质性。因此,利用以坐标和邻近样点为输入的神经网络方法可以相对准确、快速地获取区域土壤性质空间分布的异质性信息。     

基于BP人工神经网络的长江河口地区土壤盐分动态模拟及预测

为开展长江河口地区土壤盐分动态的中长期模拟与预测,采用人工神经网络中应用较为成熟和广泛的BP网络建立长江河口地区土壤盐分与降雨量、蒸发量、长江水电导率、内河水电导率、地下水位、地下水电导率6因子间的非线性神经网络响应模型。网络模型结构为6-11-1,隐含层单元数用"试错法"确定。选择合适的参数训练和学习网络模型后,对河口地区2003年各月平均根层土壤电导率进行预测,并与线性回归模型预测结果进行比较。结果表明:BP网络模型较线性回归模型具有更高的预测精度,平均相对预测误差为7.3%,预测值与实测值相关性良好,可以满足实际应用需求。     

基于PCA-RBF神经网络的烟田土壤水分预测

为建立烟田土壤水分预测模型以利于烟区种植的规划和管理,该文提出了基于主元分析（PCA）与径向基函数（RBF）神经网络模型的烟田土壤水分预测方法。首先,利用PCA消除原始输入层数据的相关性,以解决神经网络建模时输入变量过多、网络规模过大导致效率下降的问题;然后,以主元模型结果为输入建立土壤水分RBF神经网络预测模型。实例研究表明,烟田土壤水分PCA-RBF神经网络预测模型具有较好的预测效果,平均预测精度达到96.02%,与全要素误差反向传播（BP）神经网络和RBF神经网络相比,平均预测精度分别提高5.20%和6.06%,完全符合实际烟区种植规划的需求,为研究其他类型的土壤水分预测提供了参考。     

基于人工神经网络的PV/T热电联供系统性能预测

为研究太阳能PV/T热电联供系统的性能和针对太阳能PV/T系统复杂的能量平衡方程,搭建了太阳能PV/T系统试验台,同时建立了基于改进灰狼优化的BP神经网络(back propagation neural network model based on improved grey wolf algorithm, IGWO-BP)预测模型,在晴朗天气下进行试验,并采用该模型对系统电功率以及蓄热水箱内水温进行预测。结果显示,晴朗日系统的电效率8.7%～12.2%、热效率51.7%;预测结果与BP神经网络预测模型、基于粒子群优化的BP神经网络(back propagation neural network based on particle swarm optimization, PSO-BP)预测模型和卷积神经网络（convolutional neural network, CNN）预测模型预测结果进行比较,结果显示IGWO-BP预测模型电效率预测模型的绝对百分比误差(mean absolute percentage error, MAPE)、决定系数(determination coefficient, R ² )、均方根误差(root mean square error, RMSE)、效率因子(efficient factor, EF)和Pearson相关系数(pearson related coefficient, r )分别为4.5E-05、0.99、0.24、0.99和1.00,在储热罐温度预测中,上述指标分别为8.90E-04、0.98、0.07、0.98、0.99,均优于其他预测模型,IGWO-BP神经网络预测模型具有更好的预测性能。研究结果可为太阳能PV/T热电联供系统性能预测与优化控制提供参考。     

基于人工神经网络方法的冬小麦叶面积指数反演

实践中,大尺度上测量叶面积指数（LAI）很难实现,利用遥感技术进行LAI的定量反演成为当前研究的重点。该文应用MODIS地表反射率数据反演冬小麦叶面积指数,假设MODIS像元由作物和土壤混合,建立了SAILH模型与裸土反射率组成的线性光谱混合模型,基于人工神经网络的方法进行LAI反演,获得了北京顺义冬小麦种植区在2001年4月1个时间序列的LAI。研究表明,此方法能够较好的获取大区域尺度上的LAI,对冬小麦长势监测具有重要意义。     

Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity

Modeling water flow and solute transport in vadose zone requires knowledge of soil hydraulic properties, which are water retention and hydraulic conductivity curves. As an alternative to direct measurement, indirect determination of these functions from basic soil properties using pedotransfer functions (PTFs) has attracted the attention of researchers in a variety of fields such as soil scientists, hydrologists, and agricultural and environmental engineers. In this study, PTFs for point and parametric (van Genuchten's parameters) estimation of soil hydraulic parameters from basic soil properties such as particle-size distribution, bulk density, and three different pore sizes were developed and validated using artificial neural network (ANN) and multiple-linear regression methods and the predictive capabilities of the two methods was compared using some evaluation criteria. Total of 195 soil samples was divided into two groups as 130 for the development and 65 for the validation of PTFs. Although the differences between the two methods were not statistically significant (p > 0.05), regression predicted point and parametric variables of soil hydraulic parameters better than ANN. Both methods had lower accuracy in parametric predictions than in point predictions. Accuracy of the predictions was evaluated by the coefficient of determination (R²) and the root mean square error (RMSE) between the measured and predicted parameter values. The R² and RMSE varied from 0.637 to 0.979 and from 0.013 to 0.938 for regression, and varied from 0.444 to 0.952 and from 0.020 to 3.511 for ANN, respectively. Even though regression performs insignificantly better than ANN in this case, ANN produces promising results and its advantages can be utilized by developing or using new algorithms in future studies.     

基于人工神经网络的田间信息插值方法研究

提出了一种基于人工神经网络的田间信息插值新方法，并利用ArcView3.2软件绘制碱解氮的BP神经网络插值空间分布图和球状插值分布图，并对BP神经网络插值方法和克立格球状插值方法的结果进行了误差分析。结果表明，BP神经网络的插值方法优于克立格球状插值法，该方法有利于田间信息空间分布特性准确、直观的表达，有利于农田精确施肥、灌溉、播种等精细农业生产管理。     

缓坡水平梯田土壤水分空间变异性

以江苏省扬州市区北部某梯田为例,分析了小于2°的缓坡水平梯田土壤含水率的空间变异特征,并针对缓坡水平梯田土壤含水率由较高田块到较低田块逐渐增加、同一级梯田内由内侧到外侧含水率逐渐减小的分布特征,提出了适合研究该种地形土壤含水率空间分布的有效方法,即趋势辅助克立格法(简记为KTAI)。该方法同时考虑了不同级梯田高程和同级田块内不同部位对土壤含水率的影响,用它对梯田土壤含水率进行插值,估计方差比传统的普通克立格法(简记为OK)大幅度降低,大大提高了估值精度,减轻了野外采样工作量,对于研究梯田土壤水分空间变异性具有重要意义,同时拓展了地质统计学理论在土壤水分空间变异性研究中的应用范围。     

Comparing multivariate regression and artificial neural network to predict barley production from soil characteristics in northern Iran

In this study artificial neural network (ANN) models were designed to predict the biomass and grain yield of barley from soil properties; and the performance of ANN models was compared with earlier tested statistical models based on multivariate regression. Barley yield data and surface soil samples (0–30 cm depth) were collected from 1 m² plots at 112 selected points in the arid region of northern Iran. ANN yield models gave higher coefficient of determination and lower root mean square error compared to the multivariate regression, indicating that ANN is a more powerful tool than multivariate regression. Sensitivity analysis showed that soil electrical conductivity, sodium absorption ratio, pH, total nitrogen, available phosphorus, and organic matter consistently influenced barley biomass and grain yield. A comparison of the two methods to identify the most important factors indicated that while in the ANN analysis, soil organic matter (SOM) was included among the most important factors; SOM was excluded from the most important factors in the multivariate analysis. This significant discrepancy between the two methods was apparently a consequence ofthe non-linear relationships of SOM with other soil properties. Overall, our results indicated that the ANN models could explain 93 and 89% of the total variability in barley biomass and grain yield, respectively. The performance of the ANN models as compared to multivariate regression has better chance for predicting yield, especially when complex non-linear relationships exist among thefactors. We suggest that for further potential improvement in predicting thebarley yield, factors other than the soil properties considered such as soil micronutrient status and soil and crop management practices followed during the growing season, need to be included in the models.     

应用LM算法的神经网络模型研究灌区退水问题

在一些引黄灌区中,灌溉引水的相当大部分要转化为退水回归黄河,灌区退水研究对这部分水量的重新利用有着重要的意义。该文采用相关分析的方法确定了灌区退水的主要影响因素,应用LM算法的神经网络模型对灌区退水的量化分析方法进行了探讨。实例研究表明,模型能够较准确的对灌区退水量进行模拟和预测,对灌区退水问题研究具有较好的应用价值。     

利用地统计学研究土壤有机质空间分布：评估意大利中部地区土地退化的重要指标

Soil organic matter (SOM) content is one of the main factors to be considered in the evaluation of soil health and fertility. As timing, human and monetary resources often limit the amount of available data, geostatistical techniques provide a valid scientific approach to cope with spatial variability, to interpolate existing data and to predict values at unsampled locations for accurate SOM status survey. Using geostatistical and geographic information system (GIS) approaches, the spatial variability of some physical and chemical soil parameters was investigated under Mediterranean climatic condition in the Abruzzo region of central Italy, where soil erosion processes accelerated by human induced factors are the main causes of soil degradation associated with low SOM content. Experimental semivariograms were established to determine the spatial dependence of the soil variables under investigation. The results of 250 soil sampling point data were interpolated by means of ordinary kriging coupled with a GIS to produce contour maps distribution of soil texture, SOM content related to texture, and C/N ratio. The resulting spatial interpolation of the dataset highlighted a low content of SOM in relation with soil texture in most of the surveyed area (87%) and an optimal C/N ratio for only half of the investigated surface area. Spatial location of degraded area and the assessment of its magnitude can provide decision makers with an accurate support to design appropriate soil conservation strategies and then facilitate a regional planning of agri-environmental measures in the framework of the European Common Agricultural Policy.     

土壤水盐动态的BP神经网络模型及灰色关联分析

以陕西洛惠渠灌区实测数据为例,引用3层前馈型BP网络建模方法,对灌区综合条件下土壤水盐动态进行研究,采用附加动量法和学习速率自适应调整策略对反向传播算法进行改造;在此基础上运用缺省因子检验法分析了土壤含盐量和土壤碱度对输入层各因子的敏感性,并采用灰色关联法加以验证。结果表明,人工神经网络模型具有较高的精度,能够很好地定量描述土壤水盐动态变化与其影响因子之间的响应关系;土壤含水率、地下水含盐量和蒸发量是影响土壤水盐动态的主要敏感因子,各因子之间相互作用,形成了复杂条件下的耦合关系。灰色关联法进一步验证了各因子的敏感程度。将以上方法相结合,可为分析浅地下水埋深条件下作物生育期内土壤水盐动态规律提供有效可行的方法,是对传统土壤水盐动态研究方法的补充与完善。