An attenuation relationship based on Turkish strong motion data and iso-acceleration map of Turkey

This paper presents an attenuation relationship of peak ground acceleration (PGA) derived from Turkish strong motion data for rock, soil and soft soil sites and an iso-acceleration map of Turkey based on this relationship. For the purpose, among all the three-component accessible records, 221 records from 122 earthquakes that occurred in Turkey between 1976 and November 2003 were selected. The database was compiled for earthquakes with moment magnitudes (M_w) and PGA values ranging between 4.1 and 7.5, and 20 and 806 gal, and distances to epicenter considered in the database were between 5 and 100 km. From the regression analysis of the data, an attenuation equation of PGA considering rock, soil and soft soil conditions was developed. The PGA values predicted from the equation suggested in this study and those both from a few domestic equations and some imported equations were compared. In addition, an iso-acceleration map of Turkey was constructed using the suggested attenuation equation and considering both known active faults and epicenter locations of the earthquakes that have occurred in Turkey.     

The first peak ground motion attenuation relationships for North of Vietnam

The first attenuation relationships of peak ground acceleration (PGA) and peak ground velocity (PGV) for northern Vietnam are obtained in this study. Ground motion data are collected by a portable broadband seismic network in northern Vietnam as a part of cooperation between the Institute of Geophysics, Vietnamese Academy of Science and Technology, Vietnam and Institute of Earth Sciences, Academia Sinica, Taiwan. The database comprises a total of 330 amplitude records by 14 broadband stations from 53 shallow earthquakes, which were occurred in and around northern Vietnam in the period between 01/2006 and 12/2009. These earthquakes are of local magnitudes between 1.6 and 4.6, focal depths less than 30 km, and epicentral distances less than 500 km. The new attenuation relationships for PGA and PGV are:

log₁₀(PGA)=-0.987+0.7521M_L-log₁₀(R)-0.00475R,     

Strong ground motion during the largest aftershock (Mw=5.8) of the 1999 Izmit earthquake, Turkey

We present a preliminary study of strong ground motion during the largest aftershock (M_w 5.8) of the 1999 Izmit earthquake (M_w 7.4), Turkey, at 11:55 on 13 September 1999. The peak ground acceleration observed near the epicentre of this aftershock was in agreement with that predicted by standard empirical prediction equations. Its spectral source parameters of the largest aftershock are also typical for a M_w 5.8 earthquake. At greater epicentral distances, there is an order-of-magnitude in scatter in peak ground acceleration values for this aftershock, which is attributed to site effects. The presence of thick layers of low-velocity sediments caused significant amplification of S-waves in the Avcılar district of Istanbul, at frequencies of 1 Hz, explaining the observed concentration of damage there as a result of the Izmit mainshock.     

人工神经网络在徐州岩溶地面塌陷评价中的应用

岩溶地面塌陷的影响因素很多,发展过程也复杂。在众多的对岩溶地面塌陷的评价方法中,神经网络具有自学习、自适应与高度非线性映射的特点,是一种非常有效的评价手段。在徐州岩溶石地面塌陷的评价中,成功地运用了人工神经网络技术,它具有的强大非线性映射能力,能够建立评价因子和评价对象之间的关系,正确选取评价因子,避免主观判断取值,从而得出可靠的预测模型和岩溶塌陷危险性分区图。     

Determination and application of the weights for landslide susceptibility mapping using an artificial neural network

The purpose of this study is the development, application, and assessment of probability and artificial neural network methods for assessing landslide susceptibility in a chosen study area. As the basic analysis tool, a Geographic Information System (GIS) was used for spatial data management and manipulation. Landslide locations and landslide-related factors such as slope, curvature, soil texture, soil drainage, effective thickness, wood type, and wood diameter were used for analyzing landslide susceptibility. A probability method was used for calculating the rating of the relative importance of each factor class to landslide occurrence. For calculating the weight of the relative importance of each factor to landslide occurrence, an artificial neural network method was developed. Using these methods, the landslide susceptibility index (LSI) was calculated using the rating and weight, and a landslide susceptibility map was produced using the index. The results of the landslide susceptibility analysis, with and without weights, were confirmed from comparison with the landslide location data. The comparison result with weighting was better than the results without weighting. The calculated weight and rating can be used to landslide susceptibility mapping.     

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.     

An intelligent approach to prediction and control ground vibration in mines

Drilling and Blasting are still considered to be the most economical method for rock excavation either on surface or underground. The explosive energy, which breaks the rockmass, is not fully utilized for this purpose. Only 20–30% of explosive energy is utilized for fragmenting the rockmass and the rest wasted away in the form of ground vibration, air blast, noise, fly rock, back breaks, etc. Among them, ground vibration is considered to have the most damaging effect. A number of predictor equations have been proposed by various researchers to predict ground vibration prior to blasting. Still, it is difficult to recommend any one predictor for a particular ground condition because ground vibration is influenced by a number of parameters. These parameters are either controllable or non-controllable like blast geometry, explosive types, rock strength properties, joints patterns, etc. In the present paper, an attempt has been made to predict the ground vibration using an Artificial Neural Network incorporating large number of parameters, which affect the ground vibration. Results are also compared with the values obtained from regression analysis and observed field data sets. Finally, it is found that the neural network approach is more accurate and able to predict the value of blast vibration without increasing error with increasing number of inputs and non-linearity among these.     

An estimate of probabilistic seismic hazard for five cities in Greece by using the parametric-historic procedure

A probabilistic procedure was applied to assess seismic hazard for the sites of five Greek cities (Athens, Heraklion, Patras, Thessaloniki and Volos) using peak ground acceleration as the hazard parameter. The methodology allows the use of either historical or instrumental data, or a combination of both. It has been developed specifically for the estimation of seismic hazard at a given site and does not require any specification of seismic sources or/and seismic zones. A new relation for the attenuation of peak ground acceleration was employed for the shallow seismicity in Greece. The computations involved the area- and site-specific parts. When assessing magnitude recurrence for the areas surrounding the five cities, the maximum magnitude, m_max, was estimated using a recently derived equation. The site-specific results were expressed as probabilities that a given peak ground acceleration value will be exceeded at least once during a time interval of 1, 50 and 100 years at the sites of the cities. They were based on the maximum peak ground acceleration values computed by assuming the occurrence of the strongest possible earthquake (of magnitude m_max) at a very short distance from the site and using the mean value obtained with the help of the attenuation law. This gave 0.24 g for Athens, 0.53 g for Heraklion (shallow) and 0.39 g Heraklion (intermediate-depth seismicity), 0.30 g for Patras, 0.35 g for Thessaloniki and 0.30 g for Volos. In addition, the probabilities of exceedance of the estimated maximum peak ground acceleration values were calculated for the sites. The standard deviation of the new Greek attenuation law demonstrates the uncertainty and large variation of predicted peak ground acceleration values.     

Undrained lateral load capacity of piles in clay using artificial neural network

This paper describes the application of the artificial neural network model to predict the lateral load capacity of piles in clay. Three criteria were selected to compare the ANN model with the available empirical models: the best fit line for predicted lateral load capacity (Q_p) and measured lateral load capacity (Q_m), the mean and standard deviation of the ratio Q_p/Q_m and the cumulative probability for Q_p/Q_m. Different sensitivity analysis to identify the most important input parameters is discussed. A neural interpretation diagram is presented showing the effects of input parameters. A model equation is presented based on neural network parameters.     

Kohonen neural network and factor analysis based approach to geochemical data pattern recognition

Kohonen neural network (KNN) and factor analysis are applied to regional geochemical pattern recognition for a Pb–Zn–Mo–Ag mining area around Sheduolong in Qinghai Province, China. Prior to factor analysis, the geochemical data are classified by KNN. The results demonstrate that the 4-factor model accounted for 67% of the variation in the data. Factor F1, a Pb–Zn–Mo factor and Factor F4, an Au–Ag factor, correlates with monzonitic granite intrusions and particularly with Pb–Zn–Mo–Ag mineralization within those rocks. Factor F2, an As–Co factor, correlates with metamorphic rocks of paleoproterozoic Baishahe formation. Factor F3, a Bi–Cu factor, correlates with granodiorite intrusions. The factor score maps suggest a revised location of faults and their mineralization significance in coarse geological map. The approach not only effectively interprets the geological significance of the factors, but also reduces the area of exploration targets.     

Predicting standard penetration test N-value from cone penetration test data using artificial neural networks

Standard Penetration Test(SPT) and Cone Penetration Test(CPT) are the most frequently used field tests to estimate soil parameters for geotechnical analysis and design.Numerous soil parameters are related to the SPT N-value.In contrast,CPT is becoming more popular for site investigation and geotechnical design.Correlation of CPT data with SPT N-value is very beneficial since most of the field parameters are related to SPT N-values.A back-propagation artificial neural network(ANN) model was developed to predict the N6o-value from CPT data.Data used in this study consisted of 109 CPT-SPT pairs for sand,sandy silt,and silty sand soils.The ANN model input variables are:CPT tip resistance(q_c),effective vertical stress(σ'_v),and CPT sleeve friction(f_s).A different set of SPT-CPT data was used to check the reliability of the developed ANN model.It was shown that ANN model either under-predicted the N_(60)-value by 7-16%or over-predicted it by 7-20%.It is concluded that back-propagation neural networks is a good tool to predict N_(60)-value from CPT data with acceptable accuracy.     

A direct inversion scheme for deep resistivity sounding data using artificial neural networks

Initialization of model parameters is crucial in the conventional 1D inversion of DC electrical data, since a poor guess may result in undesired parameter estimations. In the present work, we investigate the performance of neural networks in the direct inversion of DC sounding data, without the need ofa priori information. We introduce a two-step network approach where the first network identifies the curve type, followed by the model parameter estimation using the second network. This approach provides the flexibility to accommodate all the characteristic sounding curve types with a wide range of resistivity and thickness. Here we realize a three layer feed-forward neural network with fast back propagation learning algorithms performing well. The basic data sets for training and testing were simulated on the basis of available deep resistivity sounding (DRS) data from the crystalline terrains of south India. The optimum network parameters and performance were decided as a function of the testing error convergence with respect to the network training error. On adequate training, the final weights simulate faithfully to recover resistivity and thickness on new data. The small discrepancies noticed, however, are well within the resolvability of resistivity sounding curve interpretations.     

Applicability of artificial neural networks for obtaining velocity models from synthetic seismic data

Seismic velocity analysis is a crucial part of seismic data processing and interpretation which has been practiced using different methods. In contrast to time consuming and complicated numerical methods, artificial neural networks (ANNs) are found to be of potential applicability. ANN ability to establish a relationship between an input and output space is considered to be appropriate for mapping seismic velocity corresponding to travel times picked from seismograms. Accordingly a preliminary attempt is made to evaluate the applicability of ANNs to determine velocity and dips of dipping layered earth models corresponding to travel time data. The study is based on synthetic data generated using inverse modeling approach for three earth models. The models include a three-layer structure with same dips and same directions, a three-layer model with different dips and same directions, as well as a two-layer model with different dips and directions. An ANN structure is designed in three layers, namely, input, output, and hidden ones. The training and testing process of the ANN is successfully accomplished using the synthetic data. The evaluation of the applicability of the trained ANN to unknown data sets indicates that the ANN can satisfactorily compute velocity and dips corresponding to travel times. The error intervals between the desired and calculated velocity and dips are shown to be acceptably small in all cases. The applicability of the trained ANN in extrapolating is also evaluated using a number of data outside of the range already known to ANN. The results indicate that the trained ANN acceptably approximates the velocity and dips. Furthermore, the trained ANN is also evaluated in terms of capability of handling deficiency in input data where acceptable results were also achieved in velocity and dip calculations. Generally, this study shows that velocity analysis using ANNs can promisingly tackle the challenge of retrieving an initial velocity model from the travel time hyperbolas of seismic data.     

Landslide susceptibility analysis and its verification using likelihood ratio, logistic regression, and artificial neural network models: case study of Youngin, Korea

The likelihood ratio, logistic regression, and artificial neural networks models are applied and verified for analysis of landslide susceptibility in Youngin, Korea, using the geographic information system. From a spatial database containing such data as landslide location, topography, soil, forest, geology, and land use, the 14 landslide-related factors were calculated or extracted. Using these factors, landslide susceptibility indexes were calculated by likelihood ratio, logistic regression, and artificial neural network models. Before the calculation, the study area was divided into two sides (west and east) of equal area, for verification of the models. Thus, the west side was used to assess the landslide susceptibility, and the east side was used to verify the derived susceptibility. The results of the landslide susceptibility analysis were verified using success and prediction rates. The verification results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations.     

基于贝叶斯正则化改进BP神经网络的页岩气有机碳含量预测模型

页岩气总有机碳(TOC)含量是评价岩性气藏的关键指标,受复杂地质及岩芯采集等多种因素的影响,常规室内测试分析获得的TOC含量的数据有限且结果有失准确。为合理准确预测页岩气TOC含量,本文首先通过对页岩气储层TOC含量测井资料综合分析选取8条测井曲线,并结合主成分分析法(Principal Component Analysis,PCA)提取四个主成分;其次基于贝叶斯正则化(Bayesian Regularization)改进的BP神经网络方法建立页岩气TOC含量预测的BR-BP模型;最后利用该模型对研究区A区页岩气TOC含量进行预测,并与常规的LM-BP神经网络模型的预测结果进行对比。结果表明：BR-BP模型有较强的非线性拟合能力,能够真实地反映出页岩气TOC含量与各测井参数之间的非线性关系,其模型预测结果与实际值基本吻合,与常规的LM-BP神经网络模型相比,其数据敏感性增强,预测精度有所提高,该研究方法具有一定的理论意义和参考价值,为我国TOC含量预测提供了一种新的技术方法和手段。     

围岩力学参数反演的GSA-BP神经网络模型及应用

针对遗传算法（GA）存在早熟现象和局部寻优能力较差等缺陷,引入具有很强局部搜索能力的模拟退火算法（SA）,组成改进的遗传模拟退火算法（GSA）提高优化问题的能力和求解质量。针对BP神经网络容易陷入局部最小和收敛速度慢等方面的不足,应用改进的遗传模拟退火算法搜索BP神经网络的最优权值和阀值,提高BP神经网络的预测精度,建立了围岩力学参数反分析的GSA-BP神经网络模型。将该模型应用于乌东德水电站右岸地下厂房围岩力学参数的反演分析中,根据监测围岩变形数据反演围岩力学参数,反演所得参数应用到正计算分析中,得出的计算位移与实测值吻合较好,说明该方法的有效性和应用于该工程的可行性。