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。     

Artificial neural network and liquefaction susceptibility assessment: a case study using the 2001 Bhuj earthquake data,Gujarat, India

This study pertains to prediction of liquefaction susceptibility of unconsolidated sediments using artificial neural network (ANN) as a prediction model. The backpropagation neural network was trained, tested, and validated with 23 datasets comprising parameters such as cyclic resistance ratio (CRR), cyclic stress ratio (CSR), liquefaction severity index (LSI), and liquefaction sensitivity index (LSeI). The network was also trained to predict the CRR values from LSI, LSeI, and CSR values. The predicted results were comparable with the field data on CRR and liquefaction severity. Thus, this study indicates the potentiality of the ANN technique in mapping the liquefaction susceptibility of the area.     

Prediction of copper and chromium concentrations in bean leaves based on an artificial neural network model

The assessment of copper and chromium concentrations in plants requires the quantification of a large number of soil factors that affect their potential availability and subsequent toxicity and a mathematical model that predicts their relative concentrations in plants. While many soil characteristics have been implicated as altering copper and chromium availability to plants in soil, accurate, rapid and simple predictive models of metal concentrations are still lacking for soil and plant analysis. In the current study, an artificial neural network model was developed and applied to predict the exposure of bean leaves (BL) to high concentrations of copper and chromium versus some selected soil properties (pH, soil electrical conductivity and dissolved organic carbon). A series of measurements was performed on soil samples to assess the variation of copper and chromium concentrations in BL versus the soil inputs. The performance of the artificial neural network model was then evaluated using a test data set and applied to predict the exposure of the BL to the metal concentration versus the soil inputs. Correlation coefficients of 0.99981 and 0.9979 for Cu and 0.99979 and 0.9975 for Cr between the measured and artificial neural networks predicted values were found, respectively, during the testing and validation procedures. Results showed that the artificial neural network model can be successfully applied to the rapid and accurate prediction of copper and chromium concentrations in BL.     

Spatial and temporal monthly precipitation forecasting using wavelet transform and neural networks,Qara-Qum catchment,Iran

This paper aims to provide a spatial and temporal analysis to prediction of monthly precipitation data which are measured at irregularly spaced synoptic stations at discrete time points. In the present study, the rainfall data were used which were observed at four stations over the Qara-Qum catchment, located in the northeast of Iran. Several models can be used to spatially and temporally predict the precipitation data. For temporal analysis, the wavelet transform with artificial neural network (WTANN) framework combines with the wavelet transform, and an artificial neural network (ANN) is used to analyze the nonstationary precipitation time-series. The time series of dew point, temperature, and wind speed are also considered as ancillary variables in temporal prediction. Furthermore, an artificial neural network model was used for comparing the results of the WTANN model. Therefore, four models were developed, including WTANN and ANN with and without ancillary data. Several statistical methods were used for comparing the results of the temporal analysis. It was evident that at three of the four stations, the WTANN models were more effective than the ANN models, and only at one station, the ANN model with ancillary data had better performance than the WTANN model without ancillary data. The values of correlation coefficient and RMSE for WTANN model with ancillary data for the validation period at Mashhad station which showed the best results were equal to 0.787 and 13.525 mm, respectively. Finally, an artificial neural network model was used as an alternative interpolating technique for spatial analysis.     

An intelligent neural network model for evaluating performance of immobilized cell biofilter treating hydrogen sulphide vapors

Biofiltration has shown to be a promising technique for handling malodours arising from process industries. The present investigation pertains to the removal of hydrogen sulphide in a lab scale biofilter packed with biomedia, encapsulated by sodium alginate and poly vinyl alcohol. The experimental data obtained under both steady state and shock loaded conditions were modelled using the basic principles of artificial neural networks. Artificial neural networks are powerful data driven modelling tools which has the potential to approximate and interpret complex input/output relationships based on the given sets of data matrix. A predictive computerised approach has been proposed to predict the performance parameters namely, removal efficiency and elimination capacity using inlet concentration, loading rate, flow rate and pressure drop as the input parameters to the artificial neural network model. Earlier, experiments from continuous operation in the biofilter showed removal efficiencies from 50 to 100 % at inlet loading rates varying up to 13 g H₂S/m³h. The internal network parameter of the artificial neural network model during simulation was selected using the 2^k factorial design and the best network topology for the model was thus estimated. The results showed that a multilayer network (4-4-2) with a back propagation algorithm was able to predict biofilter performance effectively with R² values of 0.9157 and 0.9965 for removal efficiency and elimination capacity in the test data. The proposed artificial neural network model for biofilter operation could be used as a potential alternative for knowledge based models through proper training and testing of the state variables.     

Prediction of thermal conductivity of rocks by soft computing

The transfer of energy between two adjacent parts of rock mainly depends on its thermal conductivity. Knowledge of the thermal conductivity of rocks is necessary for the calculation of heat flow or for the longtime modeling of geothermal resources. In recent years, considerable effort has been made to develop artificial intelligence techniques to determine these properties. Present study supports the application of artificial neural network (ANN) in the study of thermal conductivity along with other intrinsic properties of rock due to its increasing importance in many areas of rock engineering, agronomy, and geoenvironmental engineering field. In this paper, an attempt has been made to predict the thermal conductivity (TC) of rocks by incorporating uniaxial compressive strength, density, porosity, and P-wave velocity using artificial neural network (ANN) technique. A three-layer feed forward back propagation neural network with 4-7-1 architecture was trained and tested using 107 experimental data sets of various rocks. Twenty new data sets were used for the validation and comparison of the TC by ANN. Multivariate regression analysis (MVRA) has also been done with same data sets of ANN. ANN and MVRA results were compared based on coefficient of determination (CoD) and mean absolute error (MAE) between experimental and predicted values of TC. It was found that CoD between measured and predicted values of TC by ANN and MVRA were 0.984 and 0.914, respectively, whereas MAE was 0.0894 and 0.2085 for ANN and MVRA, respectively.     

基于人工神经网络的岩爆预测方法

在分析岩爆主要影响因素的基础上，建立了一种新的人工神经网络岩爆预测模型。采用已有岩爆发生数据作为训练样本对网络进行训练，利用收敛的网络进行岩爆烈度预测，预测结果与实际吻合，说明利用人工神经网络预测岩爆发生烈度是一种可行的方法。     

基于BP神经网络的深埋隧洞地应力预测研究

深部地应力的测量一直是工程界难题之一。由于研究手段和测试技术的限制, 深部地应力很难测到, 或者部分数据不理想。本文将BP神经网络方法引入地应力场研究, 选取深度、岩芯密度(天然密度)、岩芯弹模、岩芯的三轴抗压强度(10MPa围压)、岩芯的声发射地应力测值、岩芯裂隙率6个参数作为地应力预测研究的主要指标, 在此模型的基础上对秦岭深埋隧洞地应力测量数据进行了拟合分析, 并对深部的地应力做了预测。结果表明用BP神经网络模型进行深埋隧洞地应力大小的预测是可行的。      

Neural network modeling for regional hazard assessment of debris flow in Lake Qionghai Watershed, China

This paper presents a neural network (NN) based model to assess the regional hazard degree of debris flows in Lake Qionghai Watershed, China. The NN model was used as an alternative for the more conventional linear model MFCAM (multi-factor composite assessment model) in order to effectively handle the nonlinearity and uncertainty inherent in the debris flow hazard analysis. The NN model was configured using a three layer structure with eight input nodes and one output node, and the number of nodes in the hidden layer was determined through an iterative process of varying the number of nodes in the hidden layer until an optimal performance was achieved. The eight variables used to represent the eight input nodes include density of debris flow gully, degree of weathering of rocks, active fault density, area percentage of slope land greater than 25° of the total land (APL25), frequency of flooding hazards, average covariance of monthly precipitation by 10 years (ACMP10), average days with rainfall >25 mm by 10 years (25D10Y), and percentage of cultivated land with slope land greater than 25° of the total cultivated land (PCL25). The output node represents the hazard-degree ranks (HDR). The model was trained with the 35 sets of data obtained from previous researches reported in literatures, and an explicit uncertainty analysis was undertaken to address the uncertainty in model training and prediction. Before the NN model is extrapolated to Lake Qionghai Watershed, a validation case, different from the above data, is conducted. In addition, the performances of the NN model and the MFCAM were compared. The NN model predicted that the HDRs of the five sub-watersheds in the Lake Qionghai Watershed were IV, IV, III, III, and IV–V, indicating that the study area covers normal hazard and severe hazard areas. Based on the NN model results, debris flow management and economic development strategies in the study are proposed for each sub-watershed.     

基于人工神经网络模型的岩石特性预测

近年来,软计算技术被用作替代的统计工具。如人工神经网络（ANN）被用于开发预测模型来估计所需的参数。在本研究中,通过利用冲击钻进过程中的一些钻进参数（气压、推力、钻头直径、穿透率）和所产生的声级,建立了预测岩石性质的神经网络模型。在实验室中所产生的数据,用于开发预测岩石特性（如单轴抗压强度、耐磨性、抗拉强度和施密特回弹数）的神经网络模型,并使用各种预测性能指标对所建模型进行检验,结果表明人工神经网络模型适用于岩石性质的预测。     

Using and Improving Neural Network Models for Ground Settlement Prediction

Earth-fill structures such as embankments, which are constructed for the preservation of land and infrastructure, show significant amount of settlement during and after construction in lowland areas with soft grounds. Settlements are often still predicted with large uncertainty and frequently observational methods are applied using settlement monitoring results in the early stage after construction to predict the long term settlement. Most of these methods require a significant amount of measurements to enable accurate predictions. In this paper, an artificial neural network model for settlement prediction is evaluated and improved using measurement records from a test embankment in The Netherlands. Based on a learning pattern that focuses on convergence of the settlement rate, the basic model predicted settlements which were in good agreement with the measurements, when the amount of measured data used as teach data for the model exceeded a degree of consolidation of 69 %. For lower amounts of teach data the accuracy of settlement prediction was limited. To improve the accuracy of settlement prediction, it is proposed to add short-term predicted values that satisfy predefined statistical criteria of low coefficient of variance or low standard deviation to the teach data, after which the model is allowed to relearn and repredict the settlement. This procedure is repeated until all predicted values satisfy the criterion. Using the improved network model resulted in significantly better predictions. Predicted settlements were in good agreement with the measurements, even when only the measurements up to a consolidation stage of 35 % were used as initial teach data.     

A nonlinear modeling and forecasting system of earth fractures based on coupling of artificial neural network and geographical information system—exemplified by earth fractures in Yuci City,Shanxi, China

Earth fracturing or fissuring is a natural phenomenon and a major geohazard in many countries. The factors that cause the earth to fracture were analyzed in Yuci City, in Shanxi Province of China using the geographical information system (GIS). A nonlinear simulation and assessment model of earth fracturing was established using the artificial neural network (ANN) technology to simulate the structure and function of the neural network (NN) of the human brain with engineering technology. The developed nonlinear modeling and forecasting system was used to assess and forecast the earth fracture hazard in Yuci City. The results of this study provided useful and essential information for scientific policy-making in the areas of city planning, environmental protection, and land development.     

基于灰色关联-遗传神经网络的煤与瓦斯突出预测模型

在综合分析影响煤与瓦斯突出的各种评价指标的基础上,基于人工神经网络极强的非线性逼真能力,建立了煤与瓦斯突出强度预测的遗传神经网络模型。模型采用灰色关联理论完成了评价指标的优化,并利用遗传算法对BP网络初始权值和阈值的确定进行了优化。以重庆南桐矿区砚石台矿为例,对煤与瓦斯突出强度进行了预测,结果表明,采用本模型的预测结果与矿井实际突出状况一致,模型可靠,具有一定的理论与实际意义。     

Risk assessment on storm surges in the coastal area of Guangdong Province

The coastal area of Guangdong Province is one of the most developed regions in China. It is also often under severe risk of storm surges, as one of the few regions in China which are seriously threatened by storm surges. Based on the data of storm surges in the study area in the past 30 years, the return periods of 18 tide stations for storm surge are calculated separately. Using the spatial analysis technology of ArcGIS, combined with the topography data of the study area, the submerged scope for storm surge in the coastal area of Guangdong Province is determined, and the hazard assessment is carried out. According to the view of systematic point, this article quotes the result of vulnerability assessment which was done by the author in the previous research. Based on the hazard evaluation and vulnerability evaluation, risk assessment of storm surges in the study region is done, and the risk zoning map is drawn. According to the assessment, Zhuhai, Panyu and Taishan are classified as the highest risk to storm surges in Guangdong Province; Yangdong, Yangjiang and Haifeng are in higher risk to storm surges; Dongguan, Jiangmen, Baoan and Huidong are in middle risk to storm surges; Zhongshan, Enping, Shanwei, Huiyang, Longgang and Shenzhen are in lower risk of storm surges; Guangzhou, Shunde and Kaiping are in the lowest risk to storm surges. This study builds a complete process for risk assessment of storm surges. It reveals the risk of storm surges in the coastal cities, and it would guide the land use of coastal cities in the future and provide scientific advices to the government for the prevention and mitigation of storm surge disaster. It has important theoretical and practical significance.     

Simulation of Storm Surges Along Myanmar Coast Using a Location Specific Numerical Model

Coastal flooding induced by storm surges associated with tropical cyclones is one of the greatest natural hazards sometimes even surpassing earthquakes. Although the frequency of tropical cyclones in the Indian seas is not high, the coastal region of India, Bangladesh and Myanmar suffer most in terms of life and property caused by the surges. Therefore, a location-specific storm surge prediction model for the coastal regions of Myanmar has been developed to carry out simulations of the 1975 Pathein, 1982 Gwa, 1992 Sandoway and 1994 Sittwe cyclones. The analysis area of the model covers from 8° N to 23° N and 90° E to 100° E. A uniform grid distance of about 9 km is taken along latitudinal and longitudinal directions. The coastal boundaries in the model are represented by orthogonal straight line segments. Using this model, numerical experiments are performed to simulate the storm surge heights associated with past severe cyclonic storms which struck the coastal regions of Myanmar. The model results are in agreement with the limited available surge estimates and observations.     

基于BP神经网络的孔隙充水矿井涌水量预测

文章分析了孔隙充水矿井的充水水源和通道,利用非线性的BP人工神经网络建立了徐州韩桥煤矿涌水量短期预测模型,选取每天的降水量作为影响因子,用已有的涌水量资料训练得到权值和阈值来表示充水通道,并对-200m水平、-270m水平、-330m水平和全矿井涌水量进行了预测。结果显示,涌水量的预测值与实测值吻合得较好,说明该模型具有一定实用性。     

Numerical simulation and prediction of storm surges and water levels in Shanghai harbour and its vicinity

A water level model incorporating the nonlinear interactions between tides and storm surges for numerical simulation and prediction use is developed in this paper. Using a conventional two-dimensional nonlinear storm surge model and tide model and associated semi-momentum finite-difference scheme, both the storm surges caused by the tropical cyclones hitting Shanghai and the tides in related regions during the period 1949–1990, are numerically simulated. In simulating storm surges, 16 tropical cyclones with different kinds of tracks are chosen. Meanwhile, to simulate tides, the governing equations for tides, along with 63 prescribed tidal constituents at open sea boundaries are numerically computed. Sixteen associated cases of total water-level simulations comprising joint effects linking surges and tides and one case of real-time prediction have been carried out in 1990 on the basis of computed surges and tides. The total water levels thus obtained in this way give better results than those obtained by the traditional method, i.e. without taking into account, in the model, nonlinear coupling between storm surges and tides.Comparison of the predictions of storm surges and the total water level with the hindcast ones in 1990 showed that a relatively larger error of prediction mainly results from the incorrect forecasting of tropical cyclones but not from the prediction method itself.     

Forewarning of sustainable utilization of regional water resources: a model based on BP neural network and set pair analysis

Early warning for sustainable utilization of regional water resources is an important control measure for regional water security management. To establish operable and quantitative forewarning model, in this paper, a new forewarning model for sustainable utilization of water resources based on BP neural network and set pair analysis (named BPSPA-FM for short) was established. In the proposed approach, the accelerating genetic algorithm–based fuzzy analytic hierarchy process was suggested to determine the weights of evaluation indexes, back-propagation neural network updating model was used to predict the values of the evaluation indexes, and the set pair analysis was used to determine the function values of relative membership in variable fuzzy set of the samples. BPSPA-FM was applied to early warning for sustainable utilization of regional water resources of Yuanyang Hani terrace in Yunnan Province of China. The results show that the states of sustainable utilization in this system were near the critical value between nonalarm and slight alarm from 1990 to 2000, the states of the system fell into slight alarm and were rapidly close to intermediate alarm from 2001 to 2004, and the states of the system were predicted to be near the critical value between slight alarm and intermediate alarm from 2005 to 2010. The main alarm indexes of the system were utilization ratio of water in agriculture, control ratio of surface water, per capita water supply, per unit area irrigation water and per capita water consumption. BPSPA-FM can take full advantage of the changing information of the evaluation indexes in adjacent periods and the relationship between the samples and the criterion grades. The results of BPSPA-FM are reasonable with high accuracy. BPSPA-FM is general and can be applied to early warning problems of different natural hazards systems such as drought disaster.     

Superiority of neural networks for pillar stress prediction in bord and pillar method

Estimation of pillar stress is a crucial task in underground mining. This is used to determine pillar dimensions, room width, roof conditions, and general mine layout. There are several methods for estimating induced stresses due to underground excavations, i.e., empirical methods, numerical solutions, and currently artificial intelligence (AI). AI based techniques are gradually gaining popularity especially for problems involving uncertainty. In this paper, an attempt has been made to predict stresses developed in the pillars of bord and pillar mining using artificial neural network. A comparison has also been done to compare the obtained results with the boundary element method as well as measured field values. For this purpose, a multilayer perceptron neural network model was developed. A number of architectures with different hidden layers and neurons were tried to get the best solution, and the architecture 5-20-8-1 was found to be an optimum solution. Sensitivity analysis was also carried out to understand the influence of important input parameters on pillar stress concentration.     

Prediction of relative crest settlement of concrete-faced rockfill dams analyzed using an artificial neural network model

A neural network model has been developed for the prediction of relative crest settlement (RCS) of concrete-faced rockfill dams (CFRDs) using 30 databases of field data from seven countries (of which 21 were used for training and 9 for testing). The settlement values predicted using the optimum artificial neural network (ANN) model are in good agreement with these field data. A database prepared from reported crest settlement values of CFRDs after construction was used to train the ANN model to predict the RCS. It is demonstrated here that the model is capable of predicting accurately the relative crest settlement of CFRDs and is potentially applicable for general usage with knowledge of the three basic properties of a dam (void ratio, e; height, H; and vertical deformation modulus, E_V).

The performance of the new ANN model is compared with that of conventional methods based on the Clements theory and also with that of a proposed equation derived from the field data. The comparison indicates that the ANN model has strong potential and offers better performance than conventional methods when used as a quick interpolation and extrapolation tool. The conventional calculation model was proposed based on the fixed connection weights and bias factors of the optimum ANN structure. This method can support the dam engineer in predicting the relative crest settlement of a CFRD after impounding.