Simulation of the availability index of soil copper content using general regression neural network

Excessive soil copper (Cu) availability leads to plant growth retardation and leaf chlorosis, and the contamination of Cu in the food chain would be detrimental to human and animal health. The most important path for Cu accumulation in plants is uptake from soils. It is therefore important to understand the availability of soil Cu and its controlling factors to modify Cu availability and prevent excessive Cu from entering the food chain. The present study proposed a general regression neural network (GRNN) to simulate the availability index of soil Cu (available heavy mental concentrations/total heavy metal concentrations), based on the influencing factors of total Cu concentration, pH, organic matter (OM), available phosphorus (AP), and readily available potassium (RAK). Results showed that total Cu concentration, combined with OM and AP, achieved the lowest RMSE value (0.0524) for the modeled value of the availability index of soil Cu. The simulated results by GRNN and the ground truth values had better agreement (R ² = 0.7760) than that by a linear model (R ² = 0.6464) for 23 test samples. Moreover, GRNN obtained lower averaged relative errors than linear model. This demonstrated that GRNN could be used to simulate the availability index of soil heavy metals and gained better results than linear model.     

水稻、小麦与土壤中重金属Cd含量的关系模拟研究

土壤污染防治工作已成为提升耕地质量、保护国土生态安全的重要任务之一.为了科学预测我国大宗农作物(如水稻、小麦)与土壤重金属含量的关系,减少安全利用类农用地的大量农产品与土壤的协同监测,实现重金属污染农用地的安全利用,本研究以重金属Cd为例,选取对水稻、小麦Cd含量影响较大的土壤Cd含量、土壤pH值、土壤阳离子交换量(C...     

人工神经网络在边坡滑移预测中的应用

利用一项实际边坡工程的多年实测滑移资料，基于人工神经网络方法，建立了非线性人工神经网络分析模型，从而能够较精确地对该边坡的滑移进行预测，通过本工程实际的应用实践，发现它可避开复杂的本构模型而成为解决岩土工程问题的新途径。     

Heavy metal distribution in soil and plant in municipal solid waste compost amended plots

A field study was carried out to evaluate long-term heavy metal accumulation in the top 20 cm of a Tunisian clayey loam soil amended for four consecutive years with municipal solid waste compost at three levels (0, 40 and 80 t/ha/y). Heavy metals uptake and translocation within wheat plants grown on these soils were also investigated. Compared to untreated soils, compost-amended soils showed significant increases in the content of all measured metals: cadmium, chromium, copper, nickel, lead and zinc in the last three years, especially for plots amended with municipal solid waste compost at 80 t/ha/y. Wheat plants grown on compost-amended soils showed a general increase in metal uptake and translocation, especially for chromium and nickel. This heavy metal uptake was about three folds greater in plots amended at 80 t/ha/y as compared to plots amended at 40 t/ha/y. At the end of the experimental period, the diluting effect resulting from enhanced growth rates of wheat plants due to successive compost applications resulted in lower concentrations in the plants (grain part) grown on treated plots. On the other hand, chromium and nickel were less mobile in the aerial part of wheat plants and were accumulated essentially in root tissues. Plant/soil transfer coefficients for compost-amended treatments were higher than threshold range reported in the literature, indicating that there was an important load/transfer of metal ions from soils to wheat plants.     

Prediction of swelling pressure of soil using artificial intelligence techniques

The swelling pressure of soil depends upon various soil parameters such as mineralogy, clay content, Atterberg’s limits, dry density, moisture content, initial degree of saturation, etc. along with structural and environmental factors. It is very difficult to model and analyze swelling pressure effectively taking all the above aspects into consideration. Various statistical/empirical methods have been attempted to predict the swelling pressure based on index properties of soil. In this paper, the computational intelligence techniques artificial neural network and support vector machine have been used to develop models based on the set of available experimental results to predict swelling pressure from the inputs; natural moisture content, dry density, liquid limit, plasticity index, and clay fraction. The generalization of the model to new set of data other than the training set of data is discussed which is required for successful application of a model. A detailed study of the relative performance of the computational intelligence techniques has been carried out based on different statistical performance criteria.     

Neural network modeling applications in active slope stability problems

A back propagation artificial neural network approach is applied to three common challenges in engineering geology: (1) characterization of subsurface geometry/position of the slip (or failure surface) of active landslides, (2) assessment of slope displacements based on ground water elevation and climate, and (3) assessment of groundwater elevations based on climate data. Series of neural network models are trained, validated, and applied to a landslide study along Lake Michigan and cases from the literature. The subsurface characterization results are also compared to a limit equilibrium circular failure surface search with specific adopted boundary conditions. It is determined that the neural network models predict slip surfaces better than the limit equilibrium slip surface search using the most conservative criteria. Displacements and groundwater elevations are also predicted fairly well, in real time. The models’ ability to predict displacements and groundwater elevations provides a foundational framework for building future warning systems with additional inputs.     

人工神经网络在天津市区地面沉降预测中的应用

在分析天津市区地面沉降特点的基础上，结合人工神经网络原理，选择1961-1980年的天津市区降水量、地下水开采量、前年沉降量、固结度作为训练样本的输入量，以这20年的地面沉降量作为输出量，用贝叶斯正则化算法训练BP网络，得到沉降的仿真模型。并把1981-1993年的资料用来进行预测检验，结果表明这是一种比较理想的地面沉降预测方法。最后在不同的降水量保证率下，预测了到2010年天津市区地面沉降的情况。     

Developing artificial neural network models to predict allowable bearing capacity and elastic settlement of shallow foundation in Sharjah,United Arab Emirates

This research proposes the use of artificial neural network to predict the allowable bearing capacity and elastic settlement of shallow foundation on granular soils in Sharjah, United Arab Emirates. Data obtained from existing soil reports of 600 boreholes were used to train and validate the model. Three parameters (footing width, effective unit weight, and SPT blow count) are considered to have the most significant impact on the magnitude of allowable bearing capacity and elastic settlement of shallow foundations, and thus were used as the model inputs. Throughout the study, depth of footing was limited to 1.5 m below existing ground level and water table depth taken at the level of the footing. Performance comparison of the developed models (in terms of coefficient of determination, root mean square error, and mean absolute error) revealed that the developed artificial neural network models could be effectively used for predicting the allowable bearing capacity and elastic settlement. As such, the developed models can be used at the preliminary stage of estimating the allowable bearing capacity and settlements of shallow foundations on granular soils, instead of the conventional methods.     

Height prediction of water flowing fractured zones based on BP artificial neural network

Factures caused by deformation and destruction of bedrocks over coal seams can easily lead to water flooding(inrush)in mines,a threat to safety production.Fractures with high hydraulic conductivity are good watercourses as well as passages for inrush in mines and tunnels.An accurate height prediction of water flowing fractured zones is a key issue in today's mine water prevention and control.The theory of leveraging BP artificial neural network in height prediction of water flowing fractured zones is analysed and applied in Qianjiaying Mine as an example in this paper.Per the comparison with traditional calculation results,the BP artificial neural network better reflects the geological conditions of the research mine areas and produces more objective,accurate and reasonable results,which can be applied to predict the height of water flowing fractured zones.     

Modeling of a permeate flux of cross-flow membrane filtration of colloidal suspensions: A wavelet network approach

Although traditional artificial neural networks have been an attractive topic in modeling membrane filtration, lower efficiency by trial-and-error constructing and random initializing methods often accompanies neural networks. To improve traditional neural networks, the present research used the wavelet network, a special feedforward neural network with a single hidden layer supported by the wavelet theory. Prediction performance and efficiency of the proposed network were examined with a published experimental dataset of cross-flow membrane filtration. The dataset was divided into two parts: 62 samples for training data and 329 samples for testing data. Various combinations of transmembrane pressure, filtration time, ionic strength and zeta potential were used as inputs of the wavelet network so as to predict the permeate flux. Through the orthogonal least square alogorithm, an initial network with 12 hidden neurons was obtained which offered a normalized square root of mean square of 0.103 for the training data. The initial network led to a wavelet network model after training procedures with fast convergence within 30 epochs. Futher the wavelet network model accurately depicted the positive effects of either transmembrane pressure or zeta potential on permeate flux. The wavelet network also offered accurate predictions for the testing data, 96.4 % of which deviated the measured data within the ± 10 % relative error range. Moreover, comparisons indicated the wavelet network model produced better predictability than the back-forward backpropagation neural network and the multiple regression models. Thus the wavelet network approach could be employed successfully in modeling dynamic permeate flux in cross-flow membrane filtration.     

Application of artificial neural networks for estimating Cd,Zn, Pb removal efficiency from wastewater using complexation-microfiltration process

Complexation-microfiltration process for removal of heavy metal ions such as lead, cadmium and zinc from water had been investigated. Two soluble derivates of cellulose was selected as complexing agents. The dependence of the removal efficiency from the operating parameters (pH value, pressure, concentration of metal ion, concentration of complexing agent and type of counter ion) was established. Two approaches of preparation of input data and two different artificial neural network architectures, general regression neural network and back-propagation neural network have been used for modeling of experimental data. The extrapolation ability of selected architectures, i.e., the prediction of rejection coefficient with inputs beyond the calibration range of original model, was also determined. The predictions were successful, and after evaluation of performances, the models that were developed gave relatively good results of mean absolute percentage error from 4 to 14% and R-squared from 0.717 to 0.852 for general regression neural network and from 0.897 to 0.955 for back-propagation neural network.     

Accumulation of heavy metals in soil and uptake by plant species with phytoremediation potential

Contamination of heavy metals represents one of the most pressing threats to water and soil resources, as well as human health. Phytoremediation can be potentially used to remediate metal contaminated sites. In this study, concentrations of copper, zinc, iron, and magnesium accumulated by native plant species were determined in field conditions of Hame Kasi iron and copper mine in the central part of Iran in Hamadan province. The results showed that metal accumulation by plants differed among species and tissue bodies. Species grown in substrata with elevated metals contained significantly higher metals in plants. Metals accumulated by plants were mostly distributed in root tissues, suggesting that an exclusion strategy for metal tolerance exists widely amongst them. The mentioned species could accumulate relatively higher metal concentrations far above the toxic concentration in the plant shoots. With high translocation factor, metal concentration ratio of plant shoots to roots indicates internal detoxification metal tolerance mechanism; thus, they have potential for phytoextraction. The factors affecting metal accumulation by plant species including metal concentrations, pH, electrical conductivity, and nutrient status in substrata were measured. Mostly, concentrations of zinc and copper in both aboveground and underground tissues of the plants were significantly, positively related to their total in substrata, while iron, zinc, and copper were negatively correlated to soil phosphorus.     

Height prediction of water flowing fractured zones based on BP artificial neural network

Factures caused by deformation and destruction of bedrocks over coal seams can easily lead to water flooding (inrush) in mines, a threat to safety production. Fractures with high hydraulic conductivity are good watercourses as well as passages for inrush in mines and tunnels. An accurate height prediction of water flowing fractured zones is a key issue in today's mine water prevention and control. The theory of leveraging BP artificial neural network in height prediction of water flowing fractured zones is analysed and app-lied in Qianjiaying Mine as an example in this paper. Per the comparison with traditional calculation results, the BP artificial neural network better reflects the geological condi-tions of the research mine areas and produces more objective, accurate and reasonable results, which can be applied to predict the height of water flowing fractured zones.     

基于RBF神经网络的软基短期沉降预测研究

RBF(radial basis function)神经网络是一类比较优越的前向式多层神经网络,比传统的BP网络有较快的收敛速度.以深圳湾西部通道填海软基沉降的预测分析为例,探讨采用RBF神经网络解决这一问题的方法.采用插值方法构建时间间隔统一的时间序列数据并进行归一化处理,在此基础上建立了沉降变形时间序列的RBF神经网络模型,通过训练网络模型来预测沉降量.计算实例表明,模型具有运算速度快、预测精度高的特点,是一种具有应用前景的软基预测新方法.     

The retention of heavy metals in sewage sludge applied to a freshwater tidal wetland

The hypothesis that freshwater tidal wetlands act as sinks for heavy metals was tested using sewage sludge applied biweekly from March to October 1981 at low treatment (25 g m^?2 wk^?1) and high treatment (100 g m^?1) levels. No differences in aboveground macrophyte standing crop were found except in June when high and low treatment sites had significantly higher (p=0.05) standing crops than control sites. Except for chromium, metal standing stocks in the vegetation on treatment sites did not increase as a result of sludge application. The March litter had significantly higher (p=0.05) concentrations of chromium, copper, lead, and nickel at all sites than the October vegetation, but only high and low treatment litter chromium levels were significantly higher (p=0.05) than control litter. When sludge application terminated in October, the top 5 cm of soil at the high and low treatment sites had retained, respectively, 47 and 43% of the cadmium, 53 and 28% of the chromium, 52 and 0% of the copper, 51 and 0% of the zinc, 31 and 0% of the lead, and 0 and 0% of the nickel applied; only cadmium (15 and 46%, respectively) and chromium (12 and 28%, respectively) were still retained the following March. Thus, freshwater tidal wetlands can retain significant quantities of heavy metals associated with sewage sludge. The vegetation and litter play minor roles while the soil plays a major role in heavy metal retention.     

Application of soft computing in predicting rock fragmentation to reduce environmental blasting side effects

In the blasting operation, risk of facing with undesirable environmental phenomena such as ground vibration, air blast, and flyrock is very high. Blasting pattern should properly be designed to achieve better fragmentation to guarantee the successfulness of the process. A good fragmentation means that the explosive energy has been applied in a right direction. However, many studies indicate that only 20–30 % of the available energy is actually utilized for rock fragmentation. Involvement of various effective parameters has made the problem complicated, advocating application of new approaches such as artificial intelligence-based techniques. In this paper, artificial neural network (ANN) method is used to predict rock fragmentation in the blasting operation of the Sungun copper mine, Iran. The predictive model is developed using eight and three input and output parameters, respectively. Trying various types of the networks, it was found that a trained model with back-propagation algorithm having architecture 8-15-8-3 is the optimum network. Also, performance comparison of the ANN modeling with that of the statistical method was confirmed robustness of the neural networks to predict rock fragmentation in the blasting operation. Finally, sensitivity analysis showed that the most influential parameters on fragmentation are powder factor, burden, and bench height.     

基于神经网络的地质勘测反分析研究

针对地质勘查中,土的力学参数的确定及土的分类这两类复杂问题,根据反问题理论的基本原理,提出了一种基于回归分析与RBF神经网络结合的新型智能方法,建立了从土的力学参数估计到模型分类的完整智能化分析系统。考虑到土的物理参数测定方法比较简单,且实测变异性小,而力学参数实测变异性大的特点,利用RBF神经网络的数值逼近的特性,建立了神经网络模型来逼近两者之间的函数关系,可以有效地反演力学参数。同时,利用RBF神经网络所具有的模式识别功能,为地质勘察中土层划分提供依据。通过对黄石地区岩土勘查资料的分析与预测表明,该方法简捷有效。     

Heavy metal pollution in the soil surrounding a thermal power plant in Playas de Rosarito,Mexico

The generation of electricity has been identified as one of the main pollutant activities, and some studies have established an increment of heavy metals in soil in the areas surrounding these plants. The aim of this study was to evaluate the soil concentrations of heavy metals in the zone surrounding a thermoelectric power in Mexico. Thirty-two top soil samples (0–5 cm) were collected; additionally, four depth profiles (1 m) were investigated. Median concentrations for chromium, vanadium, nickel, mercury, and cadmium were 47, 47, 73, 0.02, and 0.01 mg/kg, respectively. Higher Cr, Ni, and V concentrations were observed in the soil depth profiles located closer to the plant in comparison with the concentrations found in the soil depth profile located further away from the plant; these results may indicate a possible accumulation of these metals. The geoaccumulation index results indicated that most of the sites were in the classifications of unpolluted and unpolluted to moderately polluted (classes 1 and 2). The statistical results showed that downwind of the plant in relation to the prevailing winds, there was a strong correlation between soil concentrations of chromium, copper, nickel, and vanadium. Based on the results of this study, it can be concluded that the use of fuel oil at the thermoelectric plant contributed to the accumulation of vanadium and nickel in the soil of the surrounding areas, as well as chromium and copper.     

Prediction of Rock Fragmentation Due to Blasting in Sarcheshmeh Copper Mine Using Artificial Neural Networks

The main objective in production blasting is to achieve a proper fragmentation. In this paper, rock fragmentation the Sarcheshmeh copper mine has been predicted by developing a model using artificial neural network. To construct the model, parameters such as burden to spacing ratio, hole-diameter, stemming, total charge-per-delay and point load index have been considered as input parameters. A model with architecture 9-8-5-1 trained by back propagation method was found to be optimum. To compare performance of the neural network, statistical method was also applied. Determination coefficient (R ²) and root mean square error were calculated for both the models, which show absolute superiority of neural network over traditional statistical method.     

公路软基沉降预测的支持向量机模型

提出了基于支持向量机（SVM）模型对公路软基沉降进行预测的一种新方法,工程实例预测结果表明,在同样的训练均方误差下,SVM模型预测能力要优于BP神经网络模型,同时该模型能够综合利用分级加载过程中的沉降观测数据作为训练样本集,比仅依靠预压期内部分实测沉降数据的双曲线法更能反映地基土的变形趋势。因此,将建立的SVM模型应用于公路软基沉降预测能够更准确地反映实际沉降过程