Unconfined compressive strength (UCS) is the key parameter to; estimate the insitu stresses of the rock, design optimal hydraulic fracture geometry and avoid drilling problems like wellbore instability. UCS can be estimated by rock mechanical tests on core plugs retrieved from the depth of interest but retrieving reservoir rock samples throughout the depth of the reservoir section and performing laboratory tests on them are extremely expensive as well as time consuming. In absence of core plugs, UCS can be estimated from empirical correlations. Most of the empirical correlations for UCS prediction reported in the literature are based on elastic parameters or on compressional wave velocity. These correlations were developed using linear or non-linear regression techniques. Artificial intelligence tools once optimized for training can successfully model UCS since these tools can capture highly complex and non-linear relationship between input parameters and the output parameter. The objective of this research study is to accurately predict UCS of rock using basic geophysical well logs namely; bulk density, compressional, and shear wave velocities, by applying different artificial intelligence techniques namely; Support Vector Machine (SVM), Adaptive neuro fuzzy inference system (ANFIS) and Artificial neural network (ANN). The data set used in this study, comprised of 200 laboratory measured UCS values on core plugs and their corresponding well logs. The data were collected from 10 wells which were located in a giant carbonate reservoir. Based on minimum average absolute percentage error (AAPE) and highest coefficient of determination (R2) between actual and predicted data, ANN model proposed as the best model to predict UCS. A rigorous empirical correlation was developed using the weights and biases of ANN model to predict without the need of any software incorporating AI. A comparison of proposed model with other correlations to predict UCS on new data set also suggested that the proposed model gives less AAPE. Therefore, the proposed model seems very promising and can serve as a handy tool to help geo-mechanical engineers to determine the UCS of the carbonate rock.

Heavy oil reserves accounts for more than 8 trillion barrels of the total reserve. Thermal methods such as steam flooding (SF) and its variants have been applied extensively to develop the reserves. Complex heavy oil reservoirs possess certain properties that make the steam flooding ineffective. The properties include low thickness, deeper depth and formation nature (naturally fractured carbonates). Heat losses, gravity override and channeling are the common problems associated with it. Polymer flooding (PF) is one of the major non-thermal methods employed to recover heavy oil. Higher Salinity and divalency in carbonate reservoirs restricts polymer flooding applications. Higher oil viscosity also limits its application. In this work, we investigated the potential of viscoelastic surfactant (VES) in recovering heavy oil in complex reservoirs where steam-flooding and polymer flooding fail. VES exhibits certain unique properties which are ascertained individually. The properties include IFT reduction, viscosity, elasticity, emulsification, salinity resistance, compatibility, and thermal stability. The properties of VES extend its applicability in complex reservoirs and hybrid technique that combined the synergism of VES, P, and hot water has been investigated. Reservoir simulation studies with 5-spot pattern have been conducted to compare the performance of Steam flood, polymer flood, and hybrid VES flooding in thin heavy oil reservoirs. Results indicated that VES could be an ideal hybrid option along with hot water to recover high viscous heavy oil in thin reservoirs.

Iron Sulfides scale has been a critical problem for oil and gas wells for several decades. One of the best candidates to remove these scales is tetrakis(hydroxymethyl)phosphonium sulfate (THPS). Most studies on the dissolution of iron sulfide scale using THPS have been done at neutral or acidic medium. Such conditions lead to a high corrosion rate when THPS is used in tubular wells. However, this work aims to give a holistic view on the pH effect, especially in alkaline medium, on the ability of THPS to dissolving iron sulfides. A combined approach of experimental and computational methods is used to get a better understanding of the pH effect on THPS ability to dissolve pyrite. Both experimental and theoretical techniques suggest that the pyrite dissolution ability of THPS decreases as pH increases. Conversely, combing THPS with EDTA (Ethylenediaminetetraacetic acid) proved effective in dissolving a mixture of different iron sulfide field scales. EDTA is a basic chelating agent which gave a pH of 8 when combined with THPS giving a slightly alkaline solution. For the field scale the combined formulation of THPS and EDTA yielded more than 70 % scale solubility however, for pure pyrite it was less than 10%. This implies that THPS and EDTA combination is effective in dissolving other iron sulfide scales, such as pyrrhotite (Fe7S8) and troilite (FeS) which are more soluble in comparison with pyrite. Also, THPS with Di-ethyline Tri-amine Penta Acitic acid (DTPA) formulation was tested and resulted in slightly lower solubility compared to THPS/EDTA formulation. Moreover, oilfield scales are usually a mix of a variety of minerals and not only pyrite. Hence, using THPS in combination with EDTA to attain a basic pH would reduce the corrosion rate and subsequently reduce or eliminate the need for corrosion inhibitors.

This paper centers on a novel method for traffic sign recognition (TSR). The method comprises of two major steps: 1) make strong representations for TSR images, by extraction deep features with the deep convolutional generative adversarial networks (DCGANs) and 2) classifier defined by multilayer perceptron (MLP) neural networks trained with a pseudoinverse learning autoencoder (PILAE) algorithm. The PILAE training process is considered efficient in which it does not require the number of hidden layers specified nor does it need the setting of the learning control parameters. This results in the PILAE classifier attaining a better performance in terms of both accuracy and efficiency. Empirical results from the German TSR (GTSRB) and Belgium traffic sign classification (BTSC) have proved that TSR achieves excellent results with other algorithms and reasonably low complexity. INDEX TERMSDeep convolutional generative adversarial networks (DCGAN), feature extraction, pseudoinverse learning autoencoder (PILAE), traffic sign recognition (TSR).

Hydraulic fracturing is performed to enhance production in reservoirs with low permeability. It's an effective technique but there are still several uncertainties associated in its implementation. One of the uncertainties is the dependence of breakdown pressure on the type of fracturing fluid used. The objective of this paper is to perform an experimental study to determine the role of fracturing fluid on the breakdown pressure of tight sandstone rocks. The dimensions of the samples are 2 in. (diameter) by 2 in. (length). A hole of 0.25-in. in diameter and 0.75-in. length is drilled on one face of each core through which the fracturing fluid is pumped. A strong power relation between the viscosity of the fracturing fluid and breakdown pressure was seen. As the viscosity increased, the breakdown pressure increased significantly. Computed Tomography (CT) scan showed that the direction of fracture is along the bedding plane. As the viscosity increased, the fracture width and height increased. For most tests, the fractures created were bi-wing fractures. Some single wing fractures were created due to deformities in the borehole.