Search

This study aimed to identify the degree of school principals acquiring of educational technology competencies and its relation to teacher implementation of education technology from teachers point of view, the study used the descriptive analysis correlative approach, two questionnaires were development first one consisted from (20) paragraph, to determine the school principals acquiring of educational technology competences, the second also consisted from (20) paragraph to determine the teacher implementation of education technology , the sample of study consisted from (340) female and male teacher. However, the finding of study showed that the school principals acquiring of educational technology competencies from teacher point of view was average and the teacher implementation of education technology from teacher point of view was also average, the finding also showed there was a statistically significant relationship between the school principals acquiring of educational technology and teacher implementation of them at the level of (α ≤ 0.05). In addition, the finding showed there weren’t any significant relation in the degree of school principals acquiring of educational technology competencies from teacher point of view refers to variable of teacher's sex. Furthermore, there were significant differences at (α ≤ 0.05) according to teacher qualification for higher education.

Reservoir or nonreservoir geomechanics is pivotal to drilling safe and fit-for-purpose boreholes that lead to sustainable operations in the well lifecycle. Accordingly, a 1D mechanical earth model (MEM) plays a crucial role in guiding the exploration to production lifecycle with applications ranging from mud-weight optimization to hydraulic fracture designing. While numerous other petrophysical logs are critical inputs to the MEM, sonic compressional (P) and shear (S) slowness play a direct role in model building, as several geomechanics parameters are derived using them. In cased holes, however, obtaining sonic waves data can be a challenge attributed to contaminated and poor cement behind the casing that creates a hindrance in processing capabilities. This work is a culmination of integrative data analysis based on ultrasonic flexural attenuation and sonic P&S logs that resulted in successful creation of 1D-MEM for an exploratory block in Pakistan. Extensive data gathering through logging was planned in multiple sections at Well X-1, which was the exploratory well in the block, to characterize formations. Likewise, MEM was critical to the success of future wells pertaining to wellbore stability study and optimum mud-weight window selection. Nevertheless, the hole condition in a 12.25-in. section did not encourage the acquisition of an openhole log and, therefore, an alternate strategy for logging in a cased hole was planned. Accordingly, comprehensive cement evaluation was performed using the flexural attenuation-based ultrasonic technology that azimuthally deciphers the material behind casing through solid-liquid-gas mapping. This log is acquired in combination with omnidirectional sonic-based measurements (CBL-VDL). Next, acquisition of acoustic attenuation-based sonic measurements was conducted to obtain P&S slowness for 1D-MEM creation. Finally, using a methodical workflow, integration of the multiple cement evaluation measurements was done to delineate zones of processing for validity of P&S waves. Point-forward, MEM creation, and porosity estimation was performed with meaningful insights. Analyzing sonic cement logs in silo caused doubts on the cement quality because of high CBL amplitude representative of low-quality cementing. Therefore, the traditional approach of using CBL amplitude led to the apparent low-quality flagging of P&S slowness across most of the interval. Integration of flexural-attenuation and sonic CBL allowed for systematic insights into the presence of wet microannulus, which otherwise would have been missed in the absence of ultrasonic measurements. This would have direct repercussions on the validity of P&S waves and ultimately on the 1D-MEM model. However, this integration enabled us to delineate the key intervals for P&S processing where cement placement was least affected. As a result, with minimum and maximum stress vectors, a 1D-MEM model was created that helped the operator to devise a drilling strategy for the next wells in the field. In addition, the P-waves computation also provided us with a reasonable estimate of porosity throughout the casing interval, which was initially not available because of poor hole condition. The importance of data-driven integrative analysis is vital to avoid loss of valuable insights from the acquired data. Ultimately, this paved the way for designing efficient drilling and wellbore stability strategies in future appraisal/development wells in the area.

Rampant move towards the energy transition landscape has propelled the need to reduce and manage greenhouse gas (GHG) emissions. To this end, it is pivotal to explore cost-effective avenues to utilize GHG and flue gases that can lead to achieving a reduction in emissions target and provide EOR opportunities. Accordingly, the injection of these gases in oil reservoirs allows for hitting two targets with one arrow. Nevertheless, the success of these projects is dependent on accurate IFT estimates between injected gas and resident hydrocarbons. Therefore, this paper evaluates the utility of machine learning algorithms for the estimation of IFT between a mixture of CO2:N2 and straight-chain alkanes for variable temperature/pressure conditions.A systematic approach is adopted to implement predictive models for IFT prediction by utilizing over 250 experimental data points from the available literature. A comprehensive statistical analysis is performed to achieve model generalization capabilities and improve control over the most relevant input parameters. Consequently, IFT is demarcated as a function of four readily available inputs with pressure and temperature being the most obvious, while carbon number and flue gas mole fraction is also incorporated as critical parameters. Various smart approaches in this work are proposed through the development of an IFT predictor using Artificial Neural Network (ANN), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost) algorithms. Machine learning model training is enhanced using a K-fold cross-validation technique combined with the exhaustive grid search algorithm. Post-training, the developed models are tested for reliability using blind datasets reserved for this purpose.A fair comparison between model efficiency is ensured by using an in-depth error analysis schema that includes various metrics like the correlation of determination, average error analysis, graphical error analysis, and scatter plots. This allows a relative ranking system to be generated that weighs various factors to classify one model as the most efficient. For the IFT prediction problem, it was found that the neural network was aptly able to yield high efficiency and low errors. This stems from the way ANNs function to map the non-linearity relationship between carbon number and the IFT. It was also observed that enhancement of the intelligent model training through multiple techniques resulted in optimized hyperparameters/parameters.

Minimum miscibility pressure (MMP) is defined as the minimum pressure at which the CO2 is dissolved in the oil phase inside the reservoir. Minimum miscibility pressure (MMP) plays a critical role in the CO2 injection process during miscible CO2 flooding. Experimentally, MMP is determined by slim-tube experiments, rising bubble method etc. However, experimental analysis is time consuming and can have high associated cost.Therefore, application of Artificial Intelligence (AI) techniques can assist in predicting the MMP based on the available input data. This will save significant time and efforts and predicted the MMP results faster and convenient way. Some authors have worked with AI tools to predict MMP, but the model proposed in this paper has a relatively lower error. Thus, the proposed model in this study is an improved model for the prediction of MMP for miscible CO2 flooding applications.A detailed optimization was carried out in this study for both ANN and ANFIS predictive tools. Single hidden layer with 12 neurons and ‘trainlm’ as training algorithm was found out after ANN optimization, whereas subtractive clustering with cluster radius of 0.3 was the optimum scenario for ANFIS technique. ANN prediction was overall better than ANFIS technique for the prediction of CO2 MMP.

Unconventional reservoirs like shale oil/gas are expected to play a major role in many unexplored regions, globally. Shale resource evaluation involves the estimation of Total Organic Carbon (TOC) which correlates to the prospective capability of generating and containing hydrocarbons. Direct measurement of TOC through geochemical analysis is often not feasible, and hence researchers have focused on indirect methods to estimate TOC using analytical and statistical techniques. Accordingly, this work proposes the application of artificial intelligence (AI) techniques to leverage routinely available well logs for the prediction of TOC. Multiple algorithms are developed and compared to rank the most optimum solution based on efficiency analysis.Support Vector Regression (SVR), Random Forest (RF), and XGBoost algorithms are utilized to analyze the well-log data and develop intelligent models for shale TOC. A process-based approach is followed starting with systematic data analysis, which includes the selection of the most relevant input parameters, data cleaning, filtering, and data-dressing, to ensure optimized inputs into the AI models. The data utilized in this work is from major shale basins in Asia and North America. The AI models are then used to develop TOC predictor as a function of fundamental open-hole logs including sonic, gamma-ray, resistivity, and density. Furthermore, to strengthen AI input-output correlation mapping, a k-fold cross-validation methodology integrating with the exhaustive-grid search approach is adopted. This ensures the optimized hyperparameters of the intelligent algorithms developed in this work are selected. Finally, developed models are compared to geochemically derived TOC using a comprehensive error analysis schema.The proposed models are teted for veracity by applying them on blind dataset. An error metrics schema composed of root-mean-squared-error, and coefficient of determination, is developed. This analysis ranks the respective AI models based on the highest performance efficiency and lowest prediction error. Consequently, it is concluded that the XGBoost and SVR-based TOC predictions are inaccurate yielding high deviations from the actual measured values in predictive mode. On the other hand, Random Forest TOC predictor optimized using k-fold validation produces high R2 values of more than 0.85 and reasonably low errors when compared to true values. The RF method overpowers other models by mapping complex non-linear interactions between TOC and various well logs.

Until February 2017, about two hundred and twelve bioactive compounds were confirmed to be present in Annona muricata. Annonaceous acetogenins (AGEs) are the predominant compounds that present in A.muricata followed by phenols, alkaloids and other compounds. Leaves and seeds were the main parts examined in medical field. This study was conducted to evaluate the most probable active chemical components of Annona muricata seeds extracts. Cytotoxic activity of Annona muricata seed extracts against MEF (mice embryo fibroblast) cell line was evaluated by 3-(4, 5 dimethythiazol-2-yl)-2, 5-diphenyl tetrazolium bromide (MTT) assay. Ethanol and chloroform extracts were added at a final concentration (1.56, 3.12, 6.25, 12.5, 25, 50 and 100 μg/ml) for 72h exposure to MEF cells. The applications of common identification and characterization techniques which were Fourier-Transform Infrared (FT-IR) and gas chromatography-mass spectroscopy (GC-MS) for analysis of bioactive compounds in the crude plant extracts involved. As conclusion, Annona muricata seed extract have a marked anti-proliferative activity against MEF cell line after 72h exposure period in concentration-dependent manner. The major active constituents of A.muricata seeds extract involve acetogenins, flavonoids, and alkaloids.

During the design phase of oil and gas well drilling plans, predicting geomechanical parameters is an indispensable job. Accurate estimation of the Poisson's ratio and the maximum horizontal stress is essential where inaccurate estimation may result in wellbore instability and casing collapse increasing the drilling cost. Obtaining mechanical rock properties using mechanical tests on cores is expensive and time-consuming. Machine learning algorithms may be utilized to get a reliable estimate for Poisson's ratio and the maximum horizontal stress. This research aims to estimate the static Poisson's ratio and the maximum horizontal stress based on influencing factors from well-log input data through an Extreme gradient boosting algorithm (XGBoost). In addition, the XGBoost model was also compared with Random Forest.A real data set comprised of 22,325 data points was collected from the literature representing influencing variables which are compressional wave velocity, share wave velocity, bulk density, and pore pressure. The data set was split into 70% for training, and 30% for testing the model. XGBoost and random forest were used for training and testing the model. Mean absolute percentage error (MAPE), root mean squared error (RMSE), and coefficient of determination (R2) were assessed in the error metrics to obtain the optimum model. XGBoost and random forest were implemented using the k-fold cross-validation method integrated with grid search.The proposed XGBoost model shows an effective correlation between the geomechanical parameters (static Poisson's ratio and the maximum horizontal stress) with the input variables. The performance of the XGBoost model was found better than that of the random forest. The evaluation estimates more than 90% of R2 and approximately 4% of MAPE for the training and testing data.The key contribution of this work is the proposal of an intelligent model that estimates the geomechanical parameters without the need for destructive mechanical core testing. A reliable XGBoost model to predict the static Poisson's ratio and the maximum horizontal stress will allow improved wellbore stability analysis which significantly introduces efficiency gains.

In a move towards development of sustainable and efficient hydrocarbon production, the industry looks forward to the deployment of carbon neutral and even carbon negative solutions. Accordingly, CO2 EOR is a viable option to improve recovery and has been applied in mature fields for over four decades. The downsides of poor sweep efficiency linked to viscous fingering and gravity segregation can be sorted through generation of CO2 foams in the reservoir. This work proposes the utilization of machine learning techniques, to predict foam flood performance which will thereby aid in optimization of laboratory core-flood experiments. This work is based upon consumption of large set of existing laboratory data collected from literature, amounting to more than 200 data points. The dataset reports core oil recovery factor as a function of three reservoir parameters including porosity, permeability, initial oil saturation. While injected foam volume and total pore volume are also considered. Furthermore, the data records contain experiments for various foaming agent types which are catered for during the machine learning model development through the implementation of numerical tags. The input data is then divided in training subset for development of XGBoost model, complemented by integration of exhaustive grid search and k-fold cross validation techniques. Subsequently, the testing subset is reserved to measure efficacy of the developed model. The model development process involves tuning of machine learning algorithm hyperparameters which control the resultant accuracy, while at the same time it is ensured that the issue of model overfitting is avoided. Testing of the established model is carried out through an array of statistical measures including the R2 and RMSE values. The proposed model is compared with actual experimental data. The machine learning model can achieve high accuracy in predictive mode for the output parameters. Through statistical error analysis performance measurement, it is observed that the machine learning model can predict CO2 foam flood performance with high R2 of around 0.99 and low errors. The excellent accuracy of the XGBoost model is credited to the complex processing involved with intelligent algorithms that can discover underlying relationships among the input variables.

Minimum miscibility pressure (MMP) is defined as the minimum pressure at which the CO2 is dissolved in the oil phase inside the reservoir. Minimum miscibility pressure (MMP) plays a critical role in the CO2 injection process during miscible CO2 flooding. Experimentally, MMP is determined by slim-tube experiments, rising bubble method etc. However, experimental analysis is time consuming and can have high associated cost. Therefore, application of Artificial Intelligence (AI) techniques can assist in predicting the MMP based on the available input data. This will save significant time and efforts and predicted the MMP results faster and convenient way. Some authors have worked with AI tools to predict MMP, but the model proposed in this paper has a relatively lower error. Thus, the proposed model in this study is an improved model for the prediction of MMP for miscible CO2 flooding applications. A detailed optimization was carried out in this study for both ANN and ANFIS predictive tools. Single hidden layer with 12 neurons and ‘trainlm’ as training algorithm was found out after ANN optimization, whereas subtractive clustering with cluster radius of 0.3 was the optimum scenario for ANFIS technique. ANN prediction was overall better than ANFIS technique for the prediction of CO2 MMP.

Drilling performance is greatly driven by the rate of penetration (ROP) and its optimization. Therefore, accurate prediction of ROP before drilling can help take measures to achieve drilling objectives smoothly. Numerous inter-twined formation and drilling parameters affect the ROP. Consequently, optimizing and predicting ROP is a complex challenge faced by the industry. This study proposes a novel computational intelligence-based (CI) model to predict ROP as a function of multiple readily available mud- and petrophysical- logs. Furthermore, multiple algorithms are utilized, and a comparative analysis is presented. Adaptive Neuro Fuzzy Inference System (ANFIS), along with Artificial Neural Network (ANN) based algorithms are utilized to analyze the data and develop models. A process-based approach is followed starting with systematic data analysis, which includes a selection of the most relevant input parameters, data cleaning, filtering, and data-dressing to ensure optimized inputs into the computational models. This step allows for developing ROP predictor as a function of pivotal formation-related logs such as neutron, density, wave velocity, and gamma ray. Moreover, historical drilling-related parameters such as weight on bit, mud pump parameters, and bit flow rate are also used as model inputs. Next, CI model parameters are tuned for both ANN and ANFIS through a sensitivity analysis on the number of neurons and the cluster radius, respectively. Finally, a comparison of ANN and ANFIS models is performed using graphical and statistical analysis. The developed models are tested on an unseen dataset to verify their efficiency. An error metrics analysis, comprising of average percentage error, root mean squared error, and the correlation coefficientis performed. This analysis ranks the respective CI models based on the highest performance efficiency and lowest prediction error. Resultantly, it is observed that the ANN-based model can perform better than the ANFIS model by accurately predicting ROP. The superior performance of ANN is due to its ability to map the complex non-linear interactions of formation and drilling parameters to the resultant ROP.

Reservoir geomechanics is essential for cost-effective drilling in complex areas, reducing risks related to wellbore stability problems, and other issues related to abnormal pore pressure, efficient reservoir modeling and enhanced oil recovery (EOR) plans. The information of major sources of overpressure generation like tectonics, under compaction, hydrocarbon accumulation and presence of an effective seal is necessary to apply reservoir geomechanics. The present study comprises of structural interpretation and comparative petrophysical evaluation of the Chorgali Formation with special emphasis on reservoir geomechanics for this Eocene reservoir in an oil field. This field is in the Potwar Plateau, included in the list of areas of the world containing over-pressured sedimentary rock. The main objective of this research work is to determine the pore pressure using well log data for two wells. In this model sonic transit (DT) time is correlated to recognize the compaction history for more accurate pore pressure prediction and to analyze the dependence of compressional wave velocity on vertical effective stress, stiffness of material and pore pressure. Pore pressure prediction by using well log data is much more affordable and gives continuous and extensive range of data than direct measurement by modular dynamic tester, drill stem test and repeat formation tester, etc. One dimensional (1D) well concentric mechanical earth model (MEM) is developed for reservoir geomechanics of Eocene carbonates. Seismic interpretation results reveal thrusting and popup structures in the area due to compressional tectonic regime. Petrophysical analysis discloses that the Chorgali Formation has better reservoir characteristics as compared to the Sakesar Formation. Compaction disequilibrium in argillaceous layers and hydrocarbon accumulation in reservoir zones are primary sources of overpressure. The well log-based pore pressure estimation shows good agreement with the in-situ measured formation pressure obtained from modular dynamic tester (MDT). The variation in rock physics properties such as bulk modulus, Young's modulus, shear modulus and Poisson's ratio are also modeled to delineate the high pore pressure zones. Reservoir geomechanics results illustrate that the predicted abnormal pore pressure is mainly due to significant hydrocarbon potential in the Chorgali Formation. On the other hand, shales deposited in the Sakesar Formation during Early Eocene are over-pressured due to compaction disequilibrium.

In response to the highly volatile industry situation post-Covid19, E&P companies are abandoning or delaying exploration projects. It is anticipated that to meet growing energy demand in the future, it would require robust reservoir surveillance to improve individual well productivity. Production logging plays a key role in developing reservoir flow characterization and its integration with multiple data sources can allow for a holistic well dynamic description, leading to production enhancement on a well-by-well basis. Multiple case studies are presented in this work that propose a data-driven, integrated workflow which combines production logging data with plethora of under-utilized data sources to constitute an investigative analysis to solve water production conundrum. The workflow developed as part of this work incorporates three distinct stages. Firstly, an in-depth data analysis is conducted utilizing all historical production data/trends and well events to link it with water production as each will have its distinct impact on the type of production logging tools/techniques that would be deployed on the subject well to achieve job objectives. Secondly, real-time production logging is conducted to ensure job objectives as defined in stage one is being met which is crucial to the resultant wellbore zonal profiling. Finally, once the production log visual representation is created, various other open-hole petrophysical and cased-hole well integrity logs are analyzed to make sense of the derived results and suggest reasoning to the state of the reservoir production pertaining to producing water. The case studies discussed in this paper include the use of petrophysical logs, MDT formation testing data, ultrasonic cement evaluation logs, and production log time-lapse analysis. Integrating various data sources with production log analysis allowed for establishment of water production sources in the various case studies discussed. In one case, production related ambiguity was resolved by integrating formation testing and production logging data together. Another analysis revealed channeling behind the casing through a micro-channel in the cement which caused water to encroach shallow perforations. This highlighted the importance of azimuthal cement logging to detect small channels even when omni-directional sonic measurements are depicting good cement placement. Finally, through integrated time-lapse production log analysis, it was discovered how wellbore dynamics were changing chronologically.

Innovation is pivotal for sustainability in today's dynamically changing E&P industry. Global industry downturn and the pandemic has pushed operators towards squeezing expenditures and look for cheaper, but efficient alternatives to maximize production from producing/discovered resources. Carbonate reservoirs provide a unique set of formation and productivity evaluation related challenges due to the highly variable characteristics of the natural fractures. This work elucidates how production logging data, combined with multiple wireline logs, resulted in resolving water production ambiguity in a well drilled into a Naturally Fractured Reservoir (NFR). Value of integrative data analysis to extend production logging diagnostic capability will be the focus of this paper. The well under consideration in this paper is a wildcat well located in a region which involves complex geology and intricate fracture systems. Accordingly, a two-tier methodical approach to characterize formation evaluation and assess well producibility was proposed and implemented through an integrated lens. Firstly, a combination of petrophysical and fracture image logs helped in comprehensive open-hole characterization. Next, to evaluate reservoir deliverability from the fractures, formation testing with 3D Radial probe and then extended well testing operation was performed, which confirmed hydrocarbon presence however, variable Water Gas Ratio (WGR) posed as a challenge, and it became critical to confirm the source of water for deciding future completion strategy. Finally, to solve the produced water conundrum, real-time production logging with integration of all open-hole data and mud log was performed to provide a definitive answer product. Integration of borehole image logs allowed to delineate complex producing zones based on fracture clusters with classification of variable fracture types and linkage with production log zonal contribution profile. Moreover, analyzing mud logs in the same canvas as the production log, led to establishment of linkage between surface water production and drilling fluid losses at specific depths. Ultimately, produced water anomaly at different choke sizes was resolved through real-time production logging optimization which indicated water sump build up downhole due to lack of lifting capacity from nearby perforations at higher choke sizes. Integrating all relevant well data in a single layout including production logging results helped in achieving objectives and understanding well dynamics in context of fracture flow characterization, water production, and diagnostic capabilities.

Optimization and monitoring schemes for oil well and reservoir system require accurate estimation of production rate. Real-time monitoring is conducted typically using flow transmitters that contain their own inherent uncertainties due to flow of multiple fluids. Because of these limitations, industrial practices involve the usage of wellhead conditions and intermittent well test data to estimate well flow rates through certain established correlations such as Gilbert’s empirical model. These correlations, however, have become ineffective due to inadequate well test data and associated operational and cost-intensive commitments. The main objective of this work was to utilize artificial intelligence (AI) techniques to develop robust correlation to predict oil rates in gas-lift wells. The AI techniques implemented in this study are artificial neural network (ANN), artificial neuro-fuzzy inference systems, support vector machines, and functional networks. In addition, ANN was used to develop physical equation to predict oil flow rate. Separator test dataset from multiple wells of an oil field operating on continuous gas lift was collected. Extensive data analytics were performed before feeding it in the algorithms. The inputs consisted of only the easily available surface parameters. All the developed AI models were compared among themselves as well as with conventionally used empirical models. The comparison was conducted based on average absolute error percentage and coefficient of determination. The newly developed AI model can predict oil rates with accuracy exceeding 98% that is extremely efficient, and examples of such results have not been reported previously.

The rocks may be classified as Archie rocks or Non-Archie rocks, depending on the link between pore structure and resistivity of the rock. For carbonate rocks, keeping this factor in view, the applicability of Archie's law tends to be unreasonable and employing Archie's equation will ultimately lead to inaccurate estimates of the water saturation. Numerous investigators have reported models that forms a link between laboratory results and field well logs to determine water saturation in intricate pore systems. In case of complex systems, Archie's law fails to correctly define the resistivity-index curves. In addition, it is imperative to carry out investigations at lower saturation values in order to elaborate the non-Archie characteristics. This brings the dual and triple porosity conductivity models into the equation. As these models are essential in defining the considerable changes of the resistivity-index curves, both qualitatively and quantitatively. The linkage between the two models is depicted electrically in series or in parallel. Moreover, it is possible to have a combination of the two configurations. As a result, the experimental results can be modeled accurately using least parameters.This work presents two models to determine water saturation in carbonate rocks, containing dual and triple porosity systems. This study also investigates the impact of different influential parameters such as saturation exponents, conductivity ratios, and pore volume fraction of each network systems, on the new models. Finally, the effect of each parameter is individually studied and the sensitivity analysis on the RI curves is produced. A new approach to apply these models is also explained which requires the use of NMR log, mercury injection capillary pressure (MICP) measurement, and simple plotting techniques to determine the water saturation. The proposed new models help petrophysicists to estimate water saturation in Non-Archie rocks, containing double and triple porosity network systems. Keywords: Dual porosity, Triple porosity, Carbonate rocks, Water saturation models

Artificial intelligence is a smart tool widely used in Petroleum engineering. Adaptive Neuro-Fuzzy Inference System (ANFIS) is an artificial intelligence technique that is a hybrid between Artificial Neural Networks (ANN) and fuzzy logic. In this paper, both ANN and ANFIS were applied to propose a new methodology based on intelligent algorithms to predict adsorption of methane gas in shale. Feed-Forward Neural Network and subtractive clustering were applied to correlate adsorption with several parameters. These include temperature, pressure, moisture content, and total organic content (TOC). A real data set collected from the literature, which includes about 350 data points, was used in the development of a new empirical correlation. The set was divided into a 70:30 ratio for training and testing, respectively. The average absolute percentage error, correlation coefficient, and mean squared error were considered in the error metrics to obtain the best possible model. The results show that methane adsorption can be efficiently correlated with the inputs using both machine learning tools. Using ANN, the correlation coefficient for both testing and training data was more than 99%. A detailed sensitivity analysis for the ANN model is also provided in this paper.

During the past decades, several research studies have been made to unfold the immense and diversified benefits of the innovative applications of machine learning (ML) techniques in the petroleum industry. For instance, machine learning algorithms were applied to estimate the various physical properties of natural gas. Natural gas density is considered an indispensable metric that influences the determination of several variables necessary for analyzing natural gas systems. In this work, the Artificial neural network (ANN), a machine learning technique, was applied to estimate natural gas density incorporating the influencing factors. The ANN model was also compared with another ML technique, namely the Adaptive Neuro-Fuzzy Inference System (ANFIS). A mathematical form has been also presented using ANN. A real data set was taken from the literature, comprised of about 4500 data points assimilating three influencing input variables, including pseudo-reduced pressure (PPr), pseudo-reduced temperature (TPr), and molecular weight (Mw). The PPr and TPr are obtained by calculating the averages of the sample gas critical pressures and critical temperatures. A complicated nonlinear relationship exists between the three influencing variables and the gas density. The data set was divided into a 70:30 ratio for training and testing the model, respectively. Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANN) were applied to train and test the model. Absolute average percentage error (AAPE), coefficient of determination (R2), and root mean squared error (RMSE) were considered in the error metrics to acquire the best possible model. Levenberg–Marquardt backpropagation algorithm was employed for ANN, while subtractive clustering was used for ANFIS. Results showed that natural gas density can be well correlated with numerous inputs using machine learning tools (ANN and ANFIS). The input parameters include Ppr, Tpr, and Mw, as mentioned above. ANN performed better than ANFIS. The network was adjusted against the training sub-set to set-up weights and biases covering each node. R2 for both testing and training data was more than 99%, while AAPE was around 4% for both cases. Moreover, a detailed mathematical scheme for the ANN model is also provided in this paper.

In today's dynamically challenging E&P industry, exploration activities demand for out-of-the-box measures to make the most out of the data available at hand. Instead of relying on time consuming and cost-intensive deliverability testing, there is a strong push to extract maximum possible information from time- and cost-efficient wireline formation testers in combination with other openhole logs to get critical reservoir insight. Consequently, driving efficiency in the appraisal process by reducing redundant expenditures linked with reservoir evaluation. Employing a data-driven approach, this paper addresses the need to build single-well analytical models that combines knowledge of core data, petrophysical evaluation and reservoir fluid properties. Resultantly, predictive analysis using cognitive processes to determine multilayer productivity for an exploratory well is achieved. Single Well Predictive Modeling (SWPM) workflow is developed for this case which utilizes plethora of formation evaluation information which traditionally resides across siloed disciplines. A tailor-made workflow has been implemented which goes beyond the conventional formation tester deliverables while incorporating PVT and numerical simulation methodologies. Stage one involved reservoir characterization utilizing Interval Pressure Transient Testing (IPTT) done through the mini-DST operation on wireline formation tester. Stage two concerns the use of analytical modeling to yield exact solution to an approximate problem whose end-product is an estimate of the Absolute Open Flow Potential (AOFP). Stage three involves utilizing fluid properties from downhole fluid samples and integrating with core, OH logs, and IPTT answer products to yield a calibrated SWPM model, which includes development of a 1D petrophysical model. Additionally, this stage produces a 3D simulation model to yield a reservoir production performance deliverable which considers variable rock typing through neural network analysis. Ultimately, stage four combines the preceding analysis to develop a wellbore production model which aids in optimizing completion strategies. The application of this data-driven and cognitive technique has helped the operator in evaluating the potential of the reservoir early-on to aid in the decision-making process for further investments. An exhaustive workflow is in place that can be adopted for informed reservoir deliverability modeling in case of early well-life evaluations.

This investigation presents a powerful predictive model to determine crude oil formation volume factor (FVF) using state-of-the-art artificial intelligence (AI) techniques. FVF is a vital pressure-volume-temperature (PVT) parameter used to characterize hydrocarbon systems and is pivotal to reserves calculation and reservoir engineering studies. Ideally, FVF is measured at the laboratory scale; however, prognostic tools to evaluate this parameter can optimize time and cost estimates. The database utilized in this study is obtained from open literature and covers statistics of crude oils of the Middle East region. Multiple AI algorithms are considered, including Artificial Neural Networks (ANN) and Artificial Neural Fuzzy Inference Systems (ANFIS). Models are developed utilizing an optimization strategy for various parameters/hyper-parameters of the respective algorithms. Unique permutations and combinations for the number of perceptron and their resident layers is investigated to reach a solution that provides the most optimum output. These intelligent models are produced as a function of the parameters intrinsically affecting FVF; reservoir temperature, solution GOR, gas specific gravity, bubble point pressure, and crude oil API gravity. Comparative analysis of developed AI models is performed using visualization/statistical analysis, and the best model is pointed out. Finally, the mathematical equation extraction to determine FVF is accomplished with the respective weights and bias for the model presented. Graphical analysis is used to evaluate the performance of developed AI models. The results of scatter plots showed most of the points are lying on the 45 degree line. Moreover, during this study, an error metric is developed comprising of multiple analysis parameters; Average absolute percentage error (AAPE), Root Mean Squared Error (RMSE), coefficient of determination (R2). All models investigated are tested on an unseen dataset to prevent a biased model's development. Performance of the established AI models is gauged based on this error metric, demonstrating that ANN outperforms ANFIS with error within 1% of the measured PVT values. A computationally derived intelligent model provides the strongest predictive capabilities as it maps complex non-linear interactions between various input parameters leading to FVF.