Automatic classification of volcanic earthquakes by using Multi-Layered neural networks

The application of neural networks as classifiers of seismic events is described with the aim of developing an automatic system for the classification of explosion quakes at the Stromboli volcano. The architecture of the network that we trained to identify four different classes of shocks was a Multi-Layer Perceptron, using the Back Error Propagation algorithm. Five different approaches for representing the information embedded in the seismograms, both in the time and in the frequency domain, were considered, and the results compared. The direct use of the time series of the shocks was not satisfactory. The auto-correlation function worked well, but in some cases it was misleading. A better performance was obtained with a frequency domain representation. Finally, the use of the envelope function did not work well. Combining parameters such as the auto-correlation and envelope functions can improve one source of error, but it may introduce new ones. The performance obtained highlights the importance of the data attributes used for the training of the network. Topologies with eight neurons in a single hidden layer gave, on average, the best results among the considered neural network structures. The overall results provide a large number of events (89% with the best performance) correctly classified, indicating that this automatic technique is reliable, and encouraging further applications in the field of volcanic seismology.     

Modeling of the classification behavior of the diaphragms used in multi-chamber cement mills

A new approach has been developed for describing the classification that arises at the diaphragm in multi-chamber ball mills. Fourteen industrial scale cement mills have been sampled in this study and after mass balancing, model fits of the equipment were done. Successive mill product predictions for the sampled conditions were achieved, and requirements to build up an optimization capable model are discussed.     

A Solution to the Problem of Predicting the Suitability of Silty–clayey Materials for Cement-stabilization

Major geotechnical problems in construction involving silty–clayey soils are due to their low strength, durability and high compressibility of soft soils, and the swell–shrink nature of the overconsolidated swelling soils. Confronted with these problems, a suitable ground improvement technique is needed, for deep excavations in soft clays, for stability, durability and deformation control. Cement-stabilization is one of the alternatives. An increase in strength and durability, reduction in deformability are the main aims of this method. Conventional cement-stabilization methods are used mainly for surface treatment. However, the use of cement has recently been extended to a greater depth in which cement columns were installed to act as a type of soil reinforcement (deep cement–soil mixing and cement jet grouting). In situ engineering properties of these silty–clayey soils are often variable and difficult to predict. For this reason cement-stabilization methods have a basic target to control the aforementioned engineering properties of these clays so that the properties of a silty–clayey soil become more like the properties of a soft rock such as clayey shale or lightly cemented sandstone. So cement-stabilization of these soils is essential to control their engineering properties and to predict their engineering behaviour for construction. In an effort to predict, classify and study the suitability of silty–clayey soils for cement-stabilization both slaking and unconfined compressive strength tests were carried out on clayey–sand mixtures consisted of two types of clays, kaolin and bentonite. Finally diagrams were prepared to study the variation of slaking and strength due to compaction, curing time and cement percentage and also to predict areas of efficient cement-stabilization.     

航磁异常的几种计算机分类方法

目前,应用计算机对航磁异常进行分类存在很大局限性。为克服这些局限性,将航磁异常分类的结果从定性水平提升到定量水平,这里应用三种分类方法在计算机上对航磁异常进行分类。经实例检验,分类结果令人满意,有效地改进和实现了用于航磁异常分类的定量方法。     

Spectral Filtering and Classification of Terrestrial Laser Scanner Point Clouds

A method is presented for filtering and classification of terrestrial laser scanner point clouds. The algorithm exploits the four-channel (blue, green, red and near infrared) multispectral imaging capability of some terrestrial scanners using supervised, parametric classification to assign thematic class labels to all scan cloud points. Its principal advantage is that it is a completely data-driven algorithm and is independent of spatial sampling resolution since the processing is performed in four-dimensional spectral feature space. Its application to two data-sets of different spatial extent and spatial and spectral complexity is reported, for which respective overall classification accuracies of 87·0% and 82·0% were achieved. Analysis of the input data with emphasis on the characteristics pertinent to the anticipated outcomes precedes detailed analysis of the classification results and error sources and their causes. Erroneously classified points are attributed to radiometric errors stemming from both detector hardware and physical effects.     

新疆雷暴天气过程分型

对新疆39a雷暴天气资料的普查，得到367次雷暴天气过程，归结出4种天气形势，雷暴天气由冷锋和中尺度高压造成。     

造山作用概念和分类

本文从造山作用的特征标志出发讨论了Sengor造山带定义的缺陷， 总结了造山作用的六条特征标志，并给出了造山作用新的定义。该定义包括了造山作用的起因、特征标志和大地构造背景。评述了造山带陆内、陆缘、陆间三分法方案的不足之处和剪压造山带的单独设类问题，提出了造山带板内、俯冲、碰撞三分方案。针对碰撞造山带，笔者在总结探讨现有分类方案的优点的基础上， 提出碰撞造山带陆陆碰撞、碰撞增生、弧陆碰撞和无大陆型碰撞造山带四分法方案，其中无大陆型碰撞造山带是描述陆壳物质形成初期计体拼合聚合过程的新类型。     

A study on the early-warning technique concerning debris flow disasters

According to the principle of the eruption of debris flows, the new torrent classification techniques are brought forward. The torrent there can be divided into 4 types such as the debris flow torrent with high destructive strength, the debris flow torrent, high sand-carrying capacity flush flood torrent and common flush flood by the techniques. In this paper, the classification indices system and the quantitative rating methods are presented. Based on torrent classification, debris flow torrent hazard zone mapping techniques by which the debris flow disaster early-warning object can be ascertained accurately are identified. The key techniques of building the debris flow disaster neural network (NN)real time forecasting model are given detailed explanations in this paper, including the determination of neural node at the input layer, the output layer and the implicit layer, the construction of knowledge source and the initial weight value and so on. With this technique, the debris flow disaster real-time forecasting neural network model is built according to the rainfall features of the historical debris flow disasters, which includes multiple rain factors such as rainfall of the disaster day, the rainfall of 15 days before the disaster day, the maximal rate of rainfall in one hour and ten minutes. It can forecast the probability, critical rainfall of eruption of the debris flows, through the real-time rainfall monitoring or weather forecasting. Based on the torrent classification and hazard zone mapping, combined with rainfall monitoring in the rainy season and real-time forecasting models, the debris flow disaster early-warning system is built. In this system, the GIS technique, the advanced international software and hardware are applied, which makes the system′s performance steady with good expansibility. The system is a visual information system that serves management and decision-making, which can facilitate timely inspect of the variation of the torrent type and hazardous zone, the torrent management, the early-warning of disasters and the disaster reduction and prevention.     

三种地统计学图像纹理用于遥感图像分类的比较

该文运用LANDSAT TM数据对三种地统计学纹理量测方法用于图像分类的性能进行了比较和分析。研究发现，基于绝对值变差函数的纹理具有更好的性能。经典的变差函数和基于方根的变差函数的性能依赖于提取纹理时所用的窗口大小。