CT引导下肝脓肿穿刺治疗

本文报告了在CT引导下，对8例肝脓肿病人实施穿刺，吸脓，冲洗，埋管引流的方法与疗效探讨。8例患者均经过B超或CT诊断，用5F套管针穿刺，吸脓，冲洗，埋管，在临床配合下，病人症状缓解快，脓腔缩小，此法缩短治疗时间，它操作简单，易行，值得推广。     

雄关漫道真如铁——论中国油气二次创业

半个多世纪以来，中国经历了油气资源的第一次创业，在祖国大陆和近海大陆架地区的新生代陆相碎屑岩沉积盆地中，发现了一批油气田，使原油年产量达1．67亿吨，位居世界第五，天然气疸这241亿立方米，居世界第十五位，成绩是巨大的，但是，1993年开始进口原油3000万吨，2000年进口原油7200万吨，严重影响国家经济建设，而且这种趋势还在不断发展，预测2010年将进口原油1亿吨，天然气200亿立方米，那么，中国油气资源的出路何在？作者指出，从中国大地构造演化来看，前新生代海相残留盆地还有巨大的油气潜力，尽管其勘探的难度是世界级的，但是，只要我们切实地依靠科学技术，进行油气资源的二次创业，困难上，在实践中克服困难，就可以发现更多的石油天然气，支持国家经济建设的持续发展。     

动态监测方法的若干问题

动态监测方法在理论上是可行的，方法也是简便的，有着广阔的发展前景，但是，由于结构的复杂性，测量技术的局限性，单纯依赖理论计算分析诊断结构的病害状况并不总是容易实现的，本文介绍一种依据基本振型的振动反应求局刚度的方法，简单，实用，实践中如果辅以调查，考察，类比，分析．．．，可作出更切合实际的可靠诊断，文中还介绍一些实例，有助于启迪，开拓动态监测的应用领域。     

地震科技人员开发能力的灰色关联分析

应用灰色系统理论，根据江苏省地震工程研究院的地震科技开发资料，分别以项目负责人的年龄，学历，职称，职务，学科作为比较数列，对年度内完成的实际合同额进行了多因素灰色关联分析，排出了关联序。研究结果客观地揭示了开发能力与人的各种因素－年龄，学历，职称，职务，学科之间的相互关系，为市场经济条件下，地震科技人才的开发，培养和应用。，提供了科学依据。     

地磁台站和地磁台网的现代化技术专辑

地磁观测资料在地磁学，空间物理学，固体地球物理学及其它相关领域的研究和应用中具有十分重要的作用，资料质量对研究工作有重要影响，台网资料对研究工作有特殊意义，根据作者近年来学习、研究和实践的结果，本文第一部分从系统设计的角度就地磁台站现代化中的系统组成，功能，仪器和主要技术指标，台网建设，资料质量等问题进行了讨论，本文的第二部分介绍了世界地磁台网，包括ＩＮＴＥＲＭＡＧＮＥＴ的目标，历史，现状，原则，     

动态应力触发的余震

通常认为断层永久位移产生的小“静态”应力变化可以改变附近断层上发生地震的可能性或者说可触发地震(Harris，1998)。许多近场的触发地震，特别是触发余震的研究(Dieterich，1994；Toda，et al，1998；King，et al，1994)，将这种静态变化视为触发因素，并认为它与断层上负载的变化是等价的(Toda，et al，1998；King，et al，1994；Jaume and sykes，1992；Harris and Simpson，1992)。这里我们报道矩震级Mw=7.3的兰德斯地震的余震图象与应力变化的比较，不仅与静态应力做对比，而且与地震波传递的瞬态、振荡应力变化(即，“动态”应力)做对比。动态应力不会永久地改变加载情况，仅能通过改变断层区的力学状态或性质来触发地震。这些被动态弱化的断层在地震波通过后可能破裂，甚至能导致如果没有动态应力就不会发生的地震。我们发现余震和动态应力图象都具有类似的不对称性，动态应力来自于破裂的传播，而静态应力变化没有这种不对称性。先前的研究表明，动态应力在远距离处可促使破裂(Anderson，et al，1994；Gomberg and Bodin，1994；Gomberg，1996；Gomberg and Davis，1996；Hill，et al，1993，1995)，然而本文表明在近处也是如此。     

当前地震系统中一些经济实体存在的问题与对策

指出目前地震系统中一些公司，企业和其他经济实体存在的体制不清，性质模糊，资本不足，运营资产不良和效益较差等问题，提出明确产权关系，引入股份制，充实资本金，加速资金周转，加强资产管理，扶强汰劣等建议及措施。     

燕山地区大红峪组火山岩古风化作用新认识

大红峪组火山岩，在成岩后受古风化作用影响引起化学成分的变化，特别是深风化带岩石后期K2O沉积的影响，造成从未风化到深风化 TAS图解，碱度系数，岩系指数及岩石类型等方面相应地发生变化，在TAS图解上，岩石向碱性增加，SiO2减少方向变化，碱度系数变在，岩系指数的变化使火山岩反映为从钙碱性到超碱性，岩石类型也出现不确定性，深化带岩石根据民分计算标准矿物时，出现白榴石，霞石等碱性矿物，而实际矿未见这一现象，也是后期K2O沉积影响的结果。排除古风化的影响，作者认为大红峪组火岩应力钾质的粗而岩和粗面玄武岩，属钙碱系列，粗面玄武岩为铝过饱和型，粗面岩为正常型。不存在明显的岩浆分离晶作用，其原始岩浆应以基性为主。同上述的原因，影响了对岩浆来源，构造环境的判断，推断其构造环境，是在总的海进条件下，出现多次的海退，伴有多次火山喷发活动，水动能比较大，气候干旱，封闭，半封闭闭的海盆中富含钾的环境。     

火山学与环境

针对当代地质科学转型，拓宽服务领域之趋势，提出火山学与环境地质学科交叉形成的生长点－火山环境地学，火山活动以其高温有毒气体，炽热熔岩流，高温火山碎屑流，空落火山灰云，火山泥石流，伴随火山活动的地震与海啸等形式给人类造成灾害，近４００年全球有２６．５万人丧生于火山活动。火山事件还影响全球气候及生态环境，造成气温，降雨量异常，大气污染，臭氧层被破坏，加剧温室效应及厄尔尼诺现象等，危及人类生存空间和环境     

城市活断层探测中的浅层地震勘探方法

对大量地震灾害的研究表明，地震发生时，位于地表活动断层上的房屋或构筑物的破坏最严重，尤其是20世纪90年代后期美国北岭地震，日本阪神地震和中国台湾集集大地震等的发生后，世界许多国家的政府和地震科学家都清楚地认识到城市活断层探测与研究的重要性和急迫性，城市活断层的探测对于城市规划，抗震设防，减轻地震对城市设施的破坏都具有重要的现实意义，浅层高分辨地震勘探是城市活断层探测手段中最有效，最可靠的方法之一，可以在地表探测到地下活断层的位置，埋深，产状和空间展布情况，但由于城市环境的强干扰背景和场地条件的复杂性，必须针对实际情况，在观测系统，震源，数据采集环境的强干扰背景和场地条件的复杂性，必须针对实际 情况，在观测系统，震源，数据采集和处理方法等环节中，采用一系列提高分辨率， 提高信噪比的有效方法，才能取得可靠的探测成果，本文对城市活断层探测中的浅层地震勘探方法的技术难点和相应的解决方法进行了讨论，并结合我们近几年来在城市开展浅层地震勘探的一些经验，介绍一些实用性的浅层地震勘探工作方法。     

基于神经网络的结构地震反应仿真

提出了基于神经网络的结构地震反应仿真方法，探讨了仿真基本步骤中样本集的准备、目标函数的选取、网络拓扑结构的构建、隐层神经元数目的确定、训练方法的选择以及提高泛化精度的措施等若干实际问题，并通过算例分析验证了本方法的可行性。     

Probabilistic Visibility Forecasting Using Neural Networks

Statistical methods are widely applied in visibility forecasting. In this article, further improvements are explored by extending the standard probabilistic neural network approach. The first approach is to use several models to obtain an averaged output, instead of just selecting the overall best one, while the second approach is to use deterministic neural networks to make input variables for the probabilistic neural network. These approaches are extensively tested at two sites and seen to improve upon the standard approach, although the improvements for one of the sites were not found to be of statistical significance.     

径向基函数(RBF)神经网络及其应用

介绍了径向基函数(RBF)神经网络的原理、 学习算法及其在地震预报专家系统ESEP 3.0中的应用。 实际应用结果表明, 该神经网络可以很好地克服BP神经网络学习过程的收敛过分依赖于初值和可能出现局部收敛的缺陷, 具有较快的运算速度、 较强的非线性映射能力和较好的预报效能。     

Modelling evapotranspiration using discrete wavelet transform and neural networks

This study combines wavelet transforms and feed‐forward neural network methods for reference evapotranspiration estimation. The climatic data (air temperature, solar radiation, wind speed, relative humidity) from two stations in the United States was evaluated for estimating models. For wavelet and neural network (WNN) model, the input data was decomposed into wavelet sub‐time series by wavelet transformation. Later, the new series (reconstructed series) are produced by adding the available wavelet components and these reconstructed series are used as the input of the WNN model. This phase is pre‐processing of raw data and the main different of the WNN model. The performance of the WNN model was compared with classical neural networks approach [artificial neural network (ANN)], multi‐linear regression and Hargreaves empirical method. This study shows that the wavelet transforms and neural network methods could be applied successfully for evapotranspiration modelling from climatic data. Copyright © 2009 John Wiley & Sons, Ltd.     

New method of generating spectrum compatible accelerograms using neural networks

A new method is proposed for generating artificial earthquake accelerograms from response spectra. This method uses the learning capabilities of neural networks to developed the knowledge of the inverse mapping from the response spectra to earthquake accelerogram. In the proposed method the neural networks learn the inverse mapping directly from the actual recorded earthquake accelerograms and their response spectra. A two-stage approach is used. In the first stage, a replicator neural network is used as a data compression tool. The replicator neural network compresses the vector of the discrete Fourier spectra of the accelerograms to vectors of much smaller dimension. In the second stage, a multi-layer feed-forward neural network learns to relate the response spectrum to the compressed Fourier spectrum. A simple example is presented, in which only 30 accelerograms are used to train the two-stage neural networks. This example demonstrates how the method works and shows its potential. © 1998 John Wiley & Sons, Ltd.     

Long‐lead seasonal rainfall forecasting using time‐delay recurrent neural networks: a case study

A temporal artificial neural network‐based model is developed and applied for long‐lead rainfall forecasting. Tapped delay lines and recurrent connections are two different components that are used along with a static multilayer perceptron network to design a time‐delay recurrent neural network. The proposed model is, in fact, a combination of time‐delay and recurrent neural networks. The model is applied in three case studies of the Northwest, West, and Southwest basins of Iran. In addition, an autoregressive moving average with exogenous inputs (ARMAX) model is used as a baseline in order to be compared with the time‐delay recurrent neural networks developed in this study. Large‐scale climate signals, such as sea‐level pressure, that affect the rainfall of the study area are used as the predictors in the models, as well as the persistence between rainfall data. The results of winter‐spring rainfall forecasts are discussed thoroughly. It is demonstrated that in all cases the proposed neural network results in better forecasts in comparison with the statistical ARMAX model. Moreover, it is found that in two of three case studies the time‐delay recurrent neural networks perform better than either recurrent or time‐delay neural networks. The results demonstrate that the proposed method can significantly improve the long‐lead forecast by utilizing a non‐linear relationship between climatic predictors and rainfall in a region. Copyright © 2007 John Wiley & Sons, Ltd.     

Supervised neural network recognition of habitat zones of rice invertebrates

This study aimed to evaluate effectiveness and performance of several supervised neural network models and make pattern recognition on invertebrate habitat zones. Probabilistic, general regression, and linear neural networks, and discriminant analysis were used to recognize both known and unknown invertebrate habitat zones. The results showed that neural network models were better than traditional discriminant analysis in the recognition of known habitat zones. There was not distinctive variation in recognition from different neural network models. Sensitivity analysis indicated that the learning rate of the neural network would influence recognized results. An unknown invertebrate species from Lepidoptera was recognized to be soil-dweller (dryland) by both neural network models and discriminant analysis. In sensitivity analysis it was additionally recognized to be the type of plant canopy (terrestrial). Overall the species was estimated to be a soil-dweller (dryland) or live on plant canopy (terrestrial). It was concluded that neural network models can perform better than conventional statistic models in pattern recognition, but a comprehensive comparison among various models is necessary in order to achieve a high reliable recognition and prediction. Furthermore, sensitivity analysis can lead to an in-depth grasp on the mechanism in the recognition and is thus needed.     

Generating multiple spectrum compatible accelerograms using stochastic neural networks

A new neural‐network‐based methodology for generating artificial earthquake spectrum compatible accelerograms from response spectra was proposed in 1997, in which, the learning capabilities of neural networks were used to develop the knowledge of the inverse mapping from the response spectra to earthquake accelerograms. Recently, this methodology has been further extended and enhanced. This paper presents a new stochastic neural network that is capable of generating multiple earthquake accelerograms from a single‐response spectrum. A new stochastic feature to the neural network has been combined with a new scheme for data compression using the replicator neural networks developed in the original method. A benefit of this extended methodology is gaining efficiency in compressing the earthquake accelerograms and extracting their characteristics. The proposed method produces a stochastic ensemble of earthquake accelerograms from any response spectra or design spectra. An example is presented that used 100 recorded accelerograms to train the neural network and several design spectra and response spectra to test this improved methodology. Copyright © 2001 John Wiley & Sons, Ltd.     

神经网络方法在爆炸地震震中定位方面的应用

地震定位过程中,由于地球介质的不均一性以及台站局部地质条件的复杂性,使震中距和地震波走时呈非线性关系。利用通常地震定位方法所确定的爆炸地震震中位置和实际震中存在２０～３０ｋｍ偏差。人工神经网络具有高度非线性映射功能,可应用于地震震中定位。应用ＢＰ（反向传播）神经网络确定远场爆破地震震中的实例表明,所确定的震中位置和实际震中位置偏差在８ｋｍ以内,外延预测确定的震中位置和实际震中位置偏差小于１８ｋｍ     

Modeling River Stage‐Discharge Relationships Using Different Neural Network Computing Techniques

One of the most important problems in hydrology is the establishment of rating curves. The statistical tools that are commonly used for river stage‐discharge relationships are regression and curve fitting. However, these techniques are not adequate in view of the complexity of the problems involved. Three different neural network techniques, i. e., multi‐layer perceptron neural network with Levenberg‐Marquardt and quasi‐Newton algorithms and radial basis neural networks, are used for the development of river stage‐discharge relationships by constructing nonlinear relationships between stage and discharge. Daily stage and flow data from three stations, Yamula, Tuzkoy and Sogutluhan, on the Kizilirmak River in Turkey were used. Regression techniques are also applied to the same data. Different input combinations including the previous stages and discharges are used. The models' results are compared using three criteria, i. e., root mean square errors, mean absolute error and the determination coefficient. The results of the comparison reveal that the neural network techniques are much more suitable for setting up stage‐discharge relationships than the regression techniques. Among the neural network methods, the radial basis neural network is found to be slightly better than the others.