Prediction of Density Flow Plunging Depth in Dam Reservoirs: An Artificial Neural Network Approach

Experimental findings and observations indicate that plunging flow is related to the formation of bed load deposition in dam reservoirs. The sediment delta begins to form in the plunging region where the inflow river water meets the ambient reservoir water. Correct estimation of dam reservoir flow, plunging point, and plunging depth is crucial for dam reservoir sedimentation and water quality issues. In this study, artificial neural network (ANN), multi‐linear regression (MLR), and two‐dimensional hydrodynamic model approaches are used for modeling the plunging point and depth. A multi layer perceptron (MLP) is used as the ANN structure. A two‐dimensional model is adapted to simulate density plunging flow through a reservoir with a sloping bottom. In the model, nonlinear and unsteady continuity, momentum, energy, and k–ε turbulence equations are formulated in the Cartesian coordinates. Density flow parameters such as velocity, plunging points, and plunging depths are determined from the simulation and model results, and these are compared with previous experimental and model works. The results show that the ANN model forecasts are much closer to the experimental data than the MLR and mathematical model forecasts.     

An elliptical basis function network for classification of remote sensing images

An elliptical basis function (EBF) network is employed in this study for the classification of remotely sensed images. Though similar in structure, the EBF network differs from the well-known radial basis function (RBF) network by incorporating full covariance matrices and employing the expectation-maximization (EM) algorithm to estimate the basis functions. Since remotely sensed data often take on mixture-density distributions in the feature space, the network not only possesses the advantage of the RBF mechanism, but also utilizes the EM algorithm to compute the maximum likelihood estimates of the mean vectors and covariance matrices of a Gaussian mixture distribution in the training phase. Experimental results show that the EM-based EBF network is more effective in training and simpler in structure than an RBF network constructed for the same task.The research was supported by grant 40101021 from the Natural Science Foundation of China, and grant 2002AA135230 from Hi-Tech research and development program of China. The authors would like to thank the reviewers for their valuable comments.     

基于神经网络的高速公路软基沉降分析

简述了高速公路软基沉降观测的目的和意义。介绍了工后沉降的预测方法。其后，简述了BP神经网络的基本概念。论文提出了基于神经网络的高速公路工后沉降预报方法。结合江苏省某高速公路现场监测资料，进行了实例分析，说明此方法是可行的和有效的。它对提高高速公路建设质量具有十分重要的现实意义。     

Mineral Potential Mapping Using Bayesian Learning for Multilayer Perceptrons

Multilayer perceptrons (MLPs) can be used to discover a function which can be used to map from a set of input variables onto a value representing the conditional probability of mineralization. The standard approach to training MLPs is gradient descent, in which the error between the network output and the target output is reduced in each iteration of the training algorithm. In order to prevent overfitting, a split-sample validation procedure is used, in which the data is partitioned into two sets: a training set, which is used for weight optimization, and a validation set, which is used to optimize various parameters that can be used to prevent overfitting. One of the problems with this approach is that the resulting maps can display significant variability which stems from (i) the (randomly initialized) starting weights and (ii) the particular training/validation set partition (also determined randomly). This problem is especially pertinent on mineral potential mapping tasks, in which the number of deposit cells is a very small proportion of the total number of cells in the study area. In contrast to gradient descent methods, Bayesian learning techniques do not find a single weight vector; rather, they infer the posterior distribution of the weights given the data. Predictions are then made by integrating over this distribution. An important advantage of the Bayesian approach is that the optimization of parameters such as the weight decay regularization coefficient can be performed using training data alone, thus avoiding the noise introduced through split-sample validation. This paper reports results of applying Bayesian learning techniques to the production of maps representing gold mineralization potential over the Castlemaine region of Victoria, Australia. Maps produced using the Bayesian approach display significantly less variability than those produced using gradient descent training. They are also more reliable at predicting the presence of unknown deposits.     

Geochemical patterns of schists from the Bushmanland Group: An artificial neural networks approach

The Mesoproterozoic Bushmanland Group is situated in the central region of the 1000 to 1200 Ma Namaqualand Metamorphic Complex (NMC). The NMC comprises a belt of highly deformed medium- to high-grade metamorphic rocks to the west of the Archean Kaapvaal Craton of southern Africa. The Bushmanland Group, one of the many supracrustal sequences that make up the NMC, is a metavolcano-sedimentary succession that hosts economically significant concentrations of sillimanite and base-metal sulfide deposits. The present investigation was carried out to study the geochemistry of a large set of representative samples of psammo-pelitic schists from the Bushmanland Group, which includes data from three different schist units: Namies Schist Formation, Shaft Schist Formation and Ore Equivalent Schist. The objective was three-fold: to test the lateral correlatability of these schist units as determined by field relationships, to identify the geochemical signature of the schists and to test the validity of an Artificial Neural Network approach as an exploration tool. Two multidimensional datasets, respectively comprising 10 major and 18 trace elements, were constructed using selected published schist analyses. Both schist datasets were analyzed using self-organizing neural maps for visualizing and clustering high-dimensional geochemical data. Geochemical differences between the various schists were visualized using colored two-dimensional maps that can be visually and quantitatively interpreted. The results of this study confirm the lateral correlatability of the schist units evaluated in this communication. It was also found that each schist unit or portions of them represent a distinct geochemical signature that is related to true lithological variations. The results show that the Artificial Neural Network approach can be used as a powerful tool for regional mineral exploration in poly-deformed and metamorphosed terrains where identification of stratigraphic units through lateral correlation by means of fieldwork and petrography remains highly speculative.     

Geoacoustic inversion using adaptive neuro-fuzzy inference system

The geoacoustic parameters form significant input for underwater acoustic propagation studies and geoacoustic modeling. Conventional inversion techniques commonly used as indirect approach for extraction of geoacoustic parameters from acoustic or seismic data are computationally intensive and time-consuming. In the present study, we have tried to exploit the advantage of soft computing techniques like, reasoning ability of fuzzy logic and learning abilities of neural networks, in inversion studies. The network model based on the combined approach called adaptive neuro-fuzzy inference system (ANFIS), is found to be very promising in inversion of the acoustic data. The network model once built is capable of invert a few thousand data sets instantaneously, to a reasonably good accuracy. In the case of conventional approaches, repetition of the entire inversion process with each new data set is required. A limited number of sensor’s data are sufficient for simulation of the network model and provides an advantage to use short hydrophone array data. Inversion results of a few hundred test data sets, representing different geoacoustic environments, show the prediction error is much less than 0.01 g/cc, 10 m/s, 10 m and 0.1 against first layer’s density, compressional sound speed, thickness and attenuation respectively for a three-layer geoacoustic model. However, the error is relatively large for the second- and third-layer parameters, which need to be improved. The model is efficient, robust and inexpensive.     

果蝇优化算法优化灰色神经网络的卫星钟差预报

针对导航卫星短期钟差预报精度不高的问题,文章提出了一种基于果蝇优化算法(FOA)优化灰色神经网络的卫星钟差预报方法.利用FOA较强的全局寻优能力对灰色参数进行迭代动态微调,改善随机初始化所导致网络进化易陷入局部最优的问题,以提高灰色神经网络的预报精度;选取IGS产品中典型的卫星钟差数据,分别采用FOA优化灰色神经网络模型、神经网络模型、灰色系统模型和灰色神经网络模型进行短期钟差预报.仿真结果表明:FOA优化灰色神经网络模型的预报精度优于其他三种模型,性能满足卫星短期高精度钟差预报的要求.     

重庆市臭氧污染及其气象因子预报方法对比研究

利用2014年1月1日至2018年12月31日的重庆市空气质量日均值资料,分析了重庆近5 a臭氧污染的特征。发现重庆市臭氧是除PM_2.5以外的第二大大气污染物,具有较强的季节变化特征,主要污染时段位于夏半年,在7—8月臭氧污染程度明显超过了PM_2.5。臭氧年平均浓度呈现逐年增加的趋势,首要污染物为臭氧的日数在2018年首次超过PM_2.5,臭氧成为2018年重庆市的第一大污染物,表明重庆正在由一个以颗粒物污染为主的城市转变为臭氧污染为主的城市。通过对同期逐日气象资料与臭氧8 h滑动平均日最大值相关性分析发现,大气温度、湿度及气压均为影响臭氧污染的重要气象因子。利用气象影响因子,采用逐步回归、支持向量机、神经网络方法对臭氧8 h滑动平均日最大值进行预报实验表明,三种预报模型均具有较强的预报能力,但总体来看预报均比实况略偏小。支持向量机方法的预报效果要稍好于逐步回归和神经网络方法,可为重庆市臭氧浓度预报提供参考。     

用神经网络方法对NOAA-AVHRR资料进行云客观分类

利用NOAA AVHRR 5个通道资料建立了 6种云类以及陆地和水体的样本数据库 ,其中包括 8× 8象素样本和单象素样本。AVHRR的 5个探测通道都位于大气窗区 ,吸收物质少 ,比较透明 ,可以比较准确地反映探测表面的性质。理论分析和试验结果表明 :除了不同性质的云在 5个通道中有不同的表现外 ,通道之间的差别也可用于云分类。在理论分析和试验的基础上 ,对 8× 8象素样本库提取了包括光谱特征、灰度特征、通道差特征、灰度统计量和灰度直方图统计量特征在内的 80个特征 ,并利用逐步判别分析方法进行特征筛选 ,共选出 2 0个特征 ,用神经网络方法对 8种类型云和地表样本数据库分类 ,选择网络结构为 2 0 - 4 0 - 15 - 4的B P网络 ,利用 30 0 0多个样本进行神经网络训练 ,并用其余的 3万多个独立样本数据进行检验 ,测试正确率达 79%。类似地 ,对单象素样本数据 ,提取了包括光谱特征、灰度特征、通道差特征在内的 2 0个特征 ,用神经网络方法对 8种类型云和地表分类 ,选择网络结构为 2 0 - 4 0 - 15 - 4的 4层B P网络 ,利用 2 0 0 0多个样本进行神经网络训练 ,并用其余的 2万多个独立样本数据进行检验 ,测试正确率达 78%。设计并编写了实际云图客观云分类系统和软件 ,该系统输入为 5个通道的AVHRR数据 ,可自动获取已     

星载微波散射计资料反演海面风场进展研究

对星载微波散射计资料反演海面风场的国内外研究进展作一评述。首先介绍星载微波散射计反演海面风场的基本原理;然后对利用地球物理模型函数的反演方法中地球物理模型函数的建立与求解算法及模糊去除过程做了全面评述;最后对神经网络和遗传算法等不利用地球物理模型函数风场反演方法的应用作了相应说明。目前利用模型函数反演方法日趋成熟,但仍然有进一步改进的可能,尤其对于降水、台风等恶劣天气情况;而神经网络和遗传算法为以后进行风场反演改进亦提供了一种可行途径。