Raoof Gholami

Evaluation of flyrock phenomenon due to blasting operation by support vector machine

Flyrock is an undesirable phenomenon in the blasting operation of open pit mines. Flyrock danger zone should be taken into consideration because it is the major cause of considerable damage on the nearby structures. Even with the best care and competent personnel, flyrock may not be totally avoided. There are several empirical methods for prediction of flyrock phenomenon. Low performance of these models is due to complexity of flyrock analysis. Support vector machine (SVM) is a novel machine learning technique usually considered as a robust artificial intelligence method in classification and regression tasks. The aim of this paper is to test the capability of SVM for the prediction of flyrock in the Soungun copper mine, Iran. Comparing the obtained results of SVM with that of artificial neural network (ANN), it was concluded that SVM approach is faster and more precise than ANN method in predicting the flyrock of Soungun copper mine.

Mechanical and Elastic Properties of Transversely Isotropic Slate

Planes of weakness like schistosity and foliation affect the strength and deformational behaviors of rocks. In this paper, an attempt has been made to study the elastic and strength behavior of slate rocks obtained from foundation of Sardasht dam site in Iran. Wet and dry specimens with different orientation of foliation were evaluated under uniaxial, triaxial, and Brazilian tests. According to the results obtained, slate mechanically pronounced U-shaped anisotropy in uniaxial and triaxial compression tests. In addition, the degree of anisotropy for the slates tested in current study was relatively high, showing the effect of foliation plane on strength and elastic parameters. It was concluded that stiffness of the samples decrease as the angle of anisotropy reaches 30–40°. This change was more pronounced for wet comparing to dry samples. However, the tensile strength obtained during Brazilian tests indicated that there is no apparent relationship between angle of anisotropy and tensile strength. However, increasing the water saturation decreased the tensile strength of the samples. The calculated elastic moduli referring to different anisotropy angles could be valuable for the design of various engineering structures in planar textured rock masses.

Prediction of Hydrocarbon Reservoirs Permeability Using Support Vector Machine

Permeability is a key parameter associated with the characterization of any hydrocarbon reservoir. In fact, it is not possible to have accurate solutions to many petroleum engineering problems without having accurate permeability value. The conventional methods for permeability determination are core analysis and well test techniques. These methods are very expensive and time consuming. Therefore, attempts have usually been carried out to use artificial neural network for identification of the relationship between the well log data and core permeability. In this way, recent works on artificial intelligence techniques have led to introduce a robust machine learning methodology called support vector machine. This paper aims to utilize the SVM for predicting the permeability of three gas wells in the Southern Pars field. Obtained results of SVM showed that the correlation coefficient between core and predicted permeability is 0.97 for testing dataset. Comparing the result of SVM with that of a general regression neural network (GRNN) revealed that the SVM approach is faster and more accurate than the GRNN in prediction of hydrocarbon reservoirs permeability.

Assessing the Performance of Independent Component Analysis in Remote Sensing Data Processing

Independent component analysis (ICA) is a novel method to be considered as a powerful type of analysis in the process of source signal separation. Based on the capabilities of this particular analysis, there will be a hypothesis of applying ICA in the image processing of remote sensing data. This paper aims to introduce the ability of ICA in contrasting and highlighting some area with potential of mineralization. Considering and applying ICA transformation on the ETM+ image of southern Masule, Iran has resulted in finding some favorable points for further investigation. Moreover, sampling program on the indicated area has led to identify some huge, unexpected lithology and dikes. ICA analysis is a robust method even in remote sensing data processing with the high speed and capabilities in separating source signals from noise.

Heavy metal pollution assessment using support vector machine in the Shur River, Sarcheshmeh copper mine, Iran

Mining and related industries are widely considered as having unfavorable effects on environment in terms of magnitude and diversity. As a matter of fact, groundwater and soil pollution are noted to be the worst environmental problems related to the mining industry because of the pyrite oxidation, acid mine drainage generation, release and transport of the heavy metals. Acid mine drainage (AMD) containing heavy metals including Manganese (Mn), Copper (Cu), Lead (Pb), and Iron (Fe), is harmful for the human and aquatic environment. Metal pollution assessment using cost-effective methods, will be a crucial task in designing a remediation strategy. The aim of this paper is to predict the heavy metals included in the AMD using support vector machine (SVM). In addition, the obtained results are compared with those of the general regression neural network (GRNN). Results indicated that the SVM approach is faster and is more precise than the GRNN method in prediction of heavy metals. The results obtained from this paper can be considered as an easy and cost-effective method to monitor groundwater and surface water affected by AMD.

Prediction of shear wave velocity using empirical correlations and artificial intelligence methods

Abstract Good understanding of mechanical properties of rock formations is essential during the development and production phases of a hydrocarbon reservoir. Conventionally, these properties are estimated from the petrophysical logs with compression and shear sonic data being the main input to the correlations. This is while in many cases the shear sonic data are not acquired during well logging, which may be for cost saving purposes. In this case, shear wave velocity is estimated using available empirical correlations or artificial intelligent methods proposed during the last few decades. In this paper, petrophysical logs corresponding to a well drilled in southern part of Iran were used to estimate the shear wave velocity using empirical correlations as well as two robust artificial intelligence methods knows as Support Vector Regression (SVR) and Back-Propagation Neural Network (BPNN). Although the results obtained by SVR seem to be reliable, the estimated values are not very precise and considering the importance of shear sonic data as the input into different models, this study suggests acquiring shear sonic data during well logging. It is important to note that the benefits of having reliable shear sonic data for estimation of rock formation mechanical properties will compensate the possible additional costs for acquiring a shear log.

A modified empirical criterion for strength of transversely anisotropic rocks with metamorphic origin

A modified empirical criterion is proposed to determine the strength of transversely anisotropic rocks. In this regard, mechanical properties of intact anisotropic slate obtained from three different districts of Iran were taken into consideration. Afterward, triaxial rock strength criterion introduced by Rafiai was modified for transversely anisotropic rocks. The criterion was modified by adding a new parameter

Geomechanical and Numerical Studies of Casing Damages in a Reservoir with Solid Production

\alpha