Model Development to Predict CEC Using the Intelligence Data Mining Approaches

ABSTRACT

Using easily measurable soil properties and pedotransfer functions (PTFs) is a time-saving, non-destructive and cost-saving way in the prediction of the cation exchange capacity (CEC). The purpose of this study was to compare and evaluate the regression tree (RT), multiple linear regression (MLR) and Mamdani fuzzy inference system (MFIS) in estimating CEC. For this work, 100 soil samples from unsaturated soil hydraulic database (UNSODA) data-set were used. %Organic matter (OM), bulk density (BD), the geometric mean particle diameter (dg) and fractal dimension of particle size (D) were applied as the input predictive variables. First, the type of relationship between easily measurable soil properties and CEC was investigated and, then used for the development of PTFs and fuzzy membership functions. The results showed that MLR method was developed only based on %OM (r = 0.68, p < .01) and D (r = 0.68, p < .01). While in the RT method, all of the predictive variables were appeared in the tree-like based on their correlation coefficient with CEC. The D and %OM also were considered as input variables in developing fuzzy membership functions. Results also revealed that RT method had a higher performance than MLR and MFIS in the estimation of CEC with the highest coefficient of determination (R² = 0.77), smallest root-mean-square error (RMSE = 5.14 meq/100_gsoil), normalized root-mean-square error (NRMSE = 0.25 meq/100_gsoil) and mean error (ME = ?1.80 meq/100_gsoil). In addition, the MFIS had a higher efficiency than the MLR in the CEC estimation.     

丘陵地区田间尺度农地景观坡位划分

运用基于相似度的模糊推理方法对丘陵地区田间尺度农地景观下的地形复杂区域进行了坡位分类,并分别利用土壤物理（土层厚度）、化学（有机质、碱解氮、有效铜和有效铁）和土壤发生属性（土种分布）对分类结果进行了验证,结果表明坡位分类整体上符合研究区的实际地形地貌特征,并能很好地解释土壤物理、化学和发生属性的变化,验证了基于相似度的模糊推理方法在地形复杂区域进行坡位分类的可行性。     

Estimation of Soil Infiltration and Cation Exchange Capacity Based on Multiple Regression,ANN (RBF,MLP), and ANFIS Models

Investigation of soil properties such as cation exchange capacity (CEC) and soil infiltration is an important role in environmental research. The measurement of these parameters is time-consuming and costly. In this study, intelligence-based models [artificial neural networks (MLP and RBF), adaptive neuro-fuzzy inference system (ANFIS), and multiple regression (MR) techniques] are employed as alternatives to estimate the CEC and soil infiltration parameters from more readily available soil data. Two hundred soil samples were collected from soil 0–30 cm deep from two sites of the Ghoshe Region in Semnan Province, Iran. The first site was a flood plain and second site was agriculture land. The input data for models were electrical conductivity (EC), soil texture, lime percentage, sodium adsorption ratio (SAR), and bulk density. To evaluate the performance of these models, the statistical parameters such as root mean square error (RMSE), mean absolute error (MAE), mean error (ME), and coefficient of determination (R²) were used. Then the results of the intelligence-based models and MR were compared to each other’s. The results show that the MLP model was better than ANFIS, MR, and RBF models. Finally, sensitivity analysis was conducted to determine the most and the least influential variables affecting the soil infiltration and CEC parameters. It was found that EC and bulk density have respectively the most and the least effect on soil infiltration, and for CEC they were clay percentage and bulk density, respectively.     

Estimation of Soil Cation Exchange Capacity using Multiple Regression,Artificial Neural Networks,and Adaptive Neuro-fuzzy Inference System Models in Golestan Province,Iran

Artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) provide an alternative by estimating soil parameters from more readily available data. In this article, multilayer perceptron (MLP) and radial basis function (RBF) of ANN and ANFIS models were described to estimate soil cation exchange capacity and compared to traditional multiple regression (MR). Moreover, to test the accuracy of previous functions that estimate cation exchange capacity (CEC), five pedotransfer functions (PTFs) were surveyed. The results showed that the accuracies of ANN and ANFIS models were similar in relation to their statistical parameters. It was also found that ANFIS model exhibited greater performance than RBF, MLP, MR, and PTFs to estimate soil CEC, respectively. Finally, sensitivity analysis was conducted to determine the most and the least influential variables affecting soil CEC. The performance comparisons of used models showed that the soft computing system is a good tool to predict soil characteristics.     

棉花虫害诊断系统的设计与Web实现

为了推广棉花虫害诊断知识,满足更多棉农对领域专家诊断的需求,该文利用Java和Web技术,并以SQL Server2000为数据库开发工具,设计了一套网络化的棉花虫害诊断系统,实现了借助互联网对棉花虫害进行远程诊断的目标。该系统引入了模糊推理与案例相结合的方法,对棉花虫害的诊断及原有知识获取方法进行改进,提高了棉花虫害诊断的准确度和效率,弥补了单纯运用案例检索方法诊断的不足;系统不仅提供了知识浏览、案例查询、专家咨询等功能,可为棉农提供快速、方便、准确的智能查询服务,而且可通过专家咨询功能,向棉农提供在线远程会诊服务。     

太阳自动跟踪系统中光电传感器的设计

针对现有光电传感器存在形式单一、跟踪精度不高、运行稳定性较差等不足,该文通过对光电传感器进行结构设计,设计了一种金字塔式和箱体式嵌套的粗-精跟踪光电传感器,其中箱体式可拆卸、单独使用,其内部的凹面镜利用反射作用有效减小了箱体高度,保证了跟踪过程中的跟踪精度和运行稳定性。在对该传感器的电路进行设计时,选取四运放集成电路LM324为核心,利用其比较作用来控制电机驱动执行机构,从而使聚光系统对准太阳。利用MATLAB/Simulink对模糊PID（proportional integration differentiation,比例-积分-微分）控制器建模和仿真,与PID控制相比,模糊PID控制曲线的响应时间较短,在0.1 s时给系统一个宽度为0.1的矩形脉冲干扰,在0.1～0.2 s之间系统的响应曲线、控制误差的响应曲线以及控制器的输出变化曲线呈现不同的变化;在0.2 s时,均达到稳定状态。通过分析可知,无论是否存在干扰,该控制方法均能使控制器迅速达到稳定状态,减少系统响应时间,从而减少系统的运行成本。该研究为太阳自动跟踪系统的稳定运行和跟踪精度的提高提供了参考。     

区域土壤CEC与相关控制因子的空间非平稳关系评估

土壤阳离子交换量(CEC)对土壤的保肥能力具有重要影响。了解土壤CEC的空间分布及相关控制因子的影响有助于区域土壤肥力的精准调控。以往多采用传统的最小二乘(OLS)回归模型探索相关因子对土壤CEC的影响。然而,该类模型是一种总体回归方法,不能反映局部空间区域内相关因子对土壤CEC的影响。采用一种局部空间回归技术——地理加权回归(GWR)探索表层和亚表层土壤中CEC与相关控制因子(土壤黏粒、土壤有机质和土壤pH)之间的空间非平稳关系。结果表明,各控制因子在不同的子区域和深度对土壤CEC的影响均有明显差异;同时,GWR模型有效地揭示了土壤CEC与相关土壤控制因子的空间非平稳关系。所得的空间非平稳关系图可以为更精确地调控区域土壤肥力提供依据。     

农业专家系统生成工具的设计与实现

应用面向对象思想和方法,设计并实现了农业专家系统生成工具,使农业专家无需知识工程师的帮助就能直接开发自己的专家系统。使用本工具已生成了黄瓜病害、苹果病害、苹果虫害、苹果树施肥、棉花病害等专家系统。     

基于多层次模糊综合评价模型的沙漠绿洲水资源承载力评价与预测

[目的]对腰坝绿洲未来水资源承载力进行评价和预测研究,为该地区水资源的可持续利用及合理管理政策的制定提供决策依据。[方法]取2016年为现状水平年,2020,2025,2030年为规划水平年,根据绿洲发展历史和现状及相关规划,对社会经济发展进行预测,进而对各水平年的需水进行预测。选取9个评价指标构建水资源承载力评价指标体系,建立水资源承载力模糊综合评价模型,对各水平年水资源承载力进行评价分析。[结果]水资源承载力综合评判值2016年仅为0.251 2,表明水资源承载力已达到饱和;至2030年,上升至0.434 4,水资源承载力处于较高的可承载水平,但区内地下水资源开发潜力仍然有限。[结论]现状年水资源承载力处于超载状态,水资源供需矛盾突出,社会经济子系统是水资源承载力提高的主要压力源,通过采取一系列的措施,未来水资源承载力状况将逐渐好转,需采取全面有效的措施使水资源承载力提升至较高水平,将研究区打造成为和谐高效的绿洲。     

烟台市牟平区生态承载力研究

以生态区建设为政策前提,以烟台市牟平区作为研究对象,从资源承载力、环境承载力以及人类支持能力3个方面,构建了研究区域生态承载力评价指标体系。利用SPSS和Matlab统计软件,将主成分分析法(PCA)和模糊综合评价模型(FSEM)相结合,对研究区域综合生态承载力做出定量评估,探讨了影响生态承载力变化的主要因素。研究结果表明,该区域生态承载力在2006—2010年间处于持续下降阶段,从较高的承载度转变为不可承载状态,其中资源承载力指数下降尤为明显。分析结果与牟平区的实际情况基本相一致,反映了构建的指标体系对生态环境比较敏感,经济迅速发展区域的生态承载力评价具有有效性及适用性,验证了主成分分析法与模糊综合评价模型相结合应用于生态承载力评价的准确性及易操作性。     

生物质炭添加对华南双季稻田碳排放强度的影响

中国农田有机物料资源化利用是一项巨大挑战。为研究生物质炭农田施用的生态效应,探讨华南双季稻田碳排放强度(greenhouse gas intensity,GHGI)对生物质炭添加的响应,开展了基于静态箱-气相色谱法的连续两年野外观测。田间试验共设6个处理,即当地农民习惯(CK,化肥,无稻草还田),3个不同用量生物质炭添加处理,即BC1(5 t/hm2)、BC2(10 t/hm2)和BC3(20 t/hm2),和2个稻草还田处理(直接还田和稻草+腐熟剂还田)。结果表明,相比当地农民习惯和稻草还田处理生物质炭添加有效抑制了双季稻田温室气体排放(平均降低温室气体排放当量49.87%),显著降低了土壤容重,增强作物的碳氮养分吸收能力,稳定了水稻产量(平均增产3.54%),降低了稻田碳排放强度(平均降低52.13%)。4个生长季平均而言,相比CK、RS和RI,生物质炭3个处理分别降低稻田100a尺度上温室气体排放当量27.53%,58.65%和63.43%(P0.05),分别增产3.21%,5.11%和2.29%(P0.05),进而分别降低100a尺度上GHGI 30.57%,61.00%和64.82%(P0.05),综合而言,BC3具有较好的减排增产潜力。相关矩阵和主成分分析可视化表达了在生物炭添加影响下,稻田碳排放强度与水稻生长参数及土壤理化特性的关系。生物质炭添加影响着水稻产量、收获指数、土壤有机质、总碳和植株吸氮量等环境变量的分布。通过多元决策回归树分析,发现可通过水稻收获指数(0.5)定量判别其碳排放强度。该研究结果表明,通过优化田间管理,适量生物质炭回田(20 t/hm2)利用是增强土壤固碳、稳定水稻产量、降低稻田碳排放强度和应对气候变化不利影响的可行途径。该研究可为中国秸秆资源科学利用提供基础研究案例。     

Study on Vegetation Root Strength of Pioneer Plants for Forest Areas in Taiwan

Forest plant roots may restrain the occurrence of shallow landslides for forest land and pioneer tree species can also reduce runoff and soil erosion;thus they are useful practical ecological materials for landslide control and erosion control. In this study, two important pioneer plant species ; Formosan Alder （Alnus formosana Makino） and Roxburgh Sumac （Rhus chinensis Mill. Var, roxburghi i（DC. ） Rehd. ） were selected at landslide areas under vegetation treatments for soil and water conservation. In order to obtain the root strength model for the factors affecting pulling resistance and root tensile strength, experimental materials were tested and the data were analyzed using regression techniques. These models could be used to provide the index of slope stability and to quantify the root-strength using non-destructive methods.     

根据天气预报估算参照腾发量的模糊神经网络方法

尝试利用日常天气预报中天气情况和日最高气温的预报信息,采用自适应模糊神经推理系统(ANFIS)方法,构建参照腾发量估算方法,预报参照腾发量。用北京市大兴区1995～2003年间的逐日实测气象资料进行模型训练,用2004年逐日气象资料进行预报和模型检验。由天气预报估算的结果(ANFIS-ET₀)与Penman-Monteith方法计算的ET₀值(PM-ET₀)进行了对比分析。结果表明：后者与训练数据的线性相关系数为0.90,检验结果为0.84;t检验结果表明,训练数据和预报数据均具有很高的显著性(α＝0.01)。结果同时说明,在提高日常天气预报准确率、选择最合适的隶属度函数和模糊规则的基础上,运用智能算法解决农田灌溉复杂问题是可行的和方便快捷的。     

十万大山北坡土壤条件对马尾松高生长影响的初步分析

回归分析结果表明,广西十万大山北坡土壤条件与马尾松高生长间的关系属非线性关系。母岩(母质)、海拔、土壤有机质、土壤质地与马尾松高生长间正相关显著;土壤紧实度与马尾松高生长间负相关显著;而土壤全氮、碱解氮、速效磷、速效钾与马尾松高生长间相关未达到显著水平。各土壤条件对马尾松高生长相关程度的大小顺序为:母岩(母质)>海拔>土壤质地>土壤紧实度>土壤有机质>土壤全氮>土壤速效磷>土壤速效钾>土壤碱解氮。以母岩(母质)、海拔、紧实度、有机质、质地与马尾松平均高所建立的相应一元非线性回归方程,X~2检验无显著差异,对该地区马尾松高生长有较高的预测精度。     

应用灰色聚类法作烤烟生长的气候评价

利用灰色聚灰法对云南省大理州烤烟生长条件进行了气候适宜性分析,给出了定量,可比和综合客观的评价,结果与我州烤烟种植经验基本一致。     

多元模糊回归预测早稻稻蓟马发生程度

根据化州市1985-1997年资料，应用多元模糊回归分析方法，组建了早稻稻蓟马发生程度预测模型。经回测检验，历史符合率达100%，对1998年和1999年发生程度进行预测，结果与大田实际发生情况完全一致。