Improving Water-Based Drilling Mud Performance Using Biopolymer Gum: Integrating Experimental and Machine Learning Techniques.

Drilling through shale formations can be expensive and time-consuming due to the instability of the wellbore. Further, there is a need to develop inhibitors that are environmentally friendly. Our study discovered a cost-effective solution to this problem using Gum Arabic (ArG). We evaluated the inhibition potential of an ArG clay swelling inhibitor and fluid loss controller in water-based mud (WBM) by conducting a linear swelling test, capillary suction timer test, and zeta potential, fluid loss, and rheology tests. Our results displayed a significant reduction in linear swelling of bentonite clay (Na-Ben) by up to 36.1% at a concentration of 1.0 wt. % ArG. The capillary suction timer (CST) showed that capillary suction time also increased with the increase in the concentration of ArG, which indicates the fluid-loss-controlling potential of ArG. Adding ArG to the drilling mud prominently decreased fluid loss by up to 50%. Further, ArG reduced the shear stresses of the base mud, showing its inhibition and friction-reducing effect. These findings suggest that ArG is a strong candidate for an alternate green swelling inhibitor and fluid loss controller in WBM. Introducing this new green additive could significantly reduce non-productive time and costs associated with wellbore instability while drilling. Further, a dynamic linear swelling model, based on machine learning (ML), was created to forecast the linear swelling capacity of clay samples treated with ArG. The ML model proposed demonstrates exceptional accuracy (R2 score = 0.998 on testing) in predicting the swelling properties of ArG in drilling mud.

The use of FreeStyle libre improves glycaemic control along with reducing diabetes burden and hospital admissions in a socially deprived Northwest English population.

Aim: This retrospective study aimed to use mixed (qualitative and quantitative) methods to evaluate the role of FSL in reducing hospital admissions due to all causes, HbA1c, and reported hypoglycaemic episodes in people with diabetes living in a socially deprived region of Northwest England. Methods: Data were collected retrospectively from previous consultations, which coincided with the 6th -week, 6th -month and annual review including blood tests, hospital admissions due to any cause and reported hypoglycaemia. Also, FSL assessment and satisfaction semi-structured questionnaire was done to assess the impact of FSL on diabetes management and quality of life. Mixed-effects models were used to assess glycaemic control and reductions in hospital admissions and reported hypoglycaemic episodes. Results: Just 127 patients met the inclusion criteria. A multivariate linear mixed model method that analyses HbA1c data longitudinally revealed mean differences (mmol/mol) between baseline and post-FSL measurements, estimated by restricted maximum likelihood method (REML) of 9.64 (six weeks), 7.68 (six months) and 7.58 (annual review); all with a corresponding p-value of < 0.0001. For DKA patients, the bootstrap method revealed a significant reduction in mean HbA1c of 25.5, 95% confidence interval (CI) [8.8, 42.6] mmol/mol. It is demonstrated that FSL use for one year resulted in 59% reduction in hospital admissions and 46% reduction in reported hypoglycaemic episodes. Conclusion: The use of FSL resulted in statistically significant reductions in hospital admissions, HbA1c and reported hypoglycaemic episodes among diabetics in a socially deprived Northwest region of England. These outcomes show a direct association with a higher questionnaire score. Supplementary Information: The online version contains supplementary material available at 10.1007/s40200-024-01424-4.

Prediction of Foam Rheology Models Parameters Utilizing Machine Learning Tools.

Rheological models are usually used to predict foamed fluid viscosity; however, obtaining the model constants under various conditions is challenging. Hence, this paper investigated the effect of different variables on foam rheology, such as shear rate, temperature, pressure, surfactant types, gas phase, and salinity, using a high-pressure high-temperature foam rheometer. Power-law, Bingham plastic, and Casson fluid models fit the experimental data well. Therefore, the data were fed to different machine learning techniques to evaluate the rheological model constants with different features. In this study, seven different machine learning techniques have been applied to predict the rheological models' constants, including decision tree, random forest, XGBoost (XGB), adaptive gradient boosting, gradient boosting, support vector regression, and voting regression. We evaluated the performance of our machine learning models using the coefficient of determination (R2), cross-plots, root-mean-square error, and average absolute percentage error. Based on the prediction outcomes, the XGB model outperformed the other ML models. The XGB model exhibited remarkably low error rates, achieving a prediction accuracy of 95% under ideal conditions. Furthermore, our prediction results demonstrated that the Casson model accurately captured the rheological behavior of the foam. Additionally, we used Pearson's correlation coefficients to assess the significance of various properties in relation to the constants within the rheological models. It is evident that the XGB model makes predictions with nearly all features contributing significantly, while other machine learning techniques rely more heavily on specific features over others. The proposed methodology can minimize the experimental cost of measuring rheological parameters and serves as a quick assessment tool.

Fractured Geothermal Reservoir Using CO2 as Geofluid: Numerical Analysis and Machine Learning Modeling.

The effect of natural fractures, their orientation, and their interaction with hydraulic fractures on the extraction of heat and the extension of injection fluid are fully examined. A fully coupled and dynamic thermo-hydro-mechanical (THM) model is utilized to examine the behavior of a fractured geothermal reservoir with supercritical CO2 as a geofluid. The interaction between natural fracture and hydraulic fracture, as well as the type and location of geofluids, influences the production temperature, thermal strain, mechanical strains, and effective stress in rock/fractures in the reservoir. A mathematical model is developed by using the fully connected neural network (FCN) model to establish a mathematical relationship between the reservoir parameters and the temperature. The response surface methodology is applied for qualitative numerical experimentation. It is found that the developed FCN model can be utilized to forecast the temporal variation of temperature in the production well to a desired level using FCN. Therefore, the numerical simulations developed with the FCN method can be useful tools to investigate the temperature evolution with higher accuracy.

Predicting wettability of mineral/CO2/brine systems via data-driven machine learning modeling: Implications for carbon geo-sequestration.

Effectively storing carbon dioxide (CO2) in geological formations synergizes with algal-based removal technology, enhancing carbon capture efficiency, leveraging biological processes for sustainable, long-term sequestration while aiding ecosystem restoration. On the other hand, geological carbon storage effectiveness depends on the interactions and wettability of rock, CO2, and brine. Rock wettability during storage determines the CO2/brine distribution, maximum storage capacity, and trapping potential. Due to the high CO2 reactivity and damage risk, an experimental assessment of the CO2 wettability on storage/caprocks is challenging. Data-driven machine learning (ML) models provide an efficient and less strenuous alternative, enabling research at geological storage conditions that are impossible or hazardous to achieve in the laboratory. This study used robust ML models, including fully connected feedforward neural networks (FCFNNs), extreme gradient boosting, k-nearest neighbors, decision trees, adaptive boosting, and random forest, to model the wettability of the CO2/brine and rock minerals (quartz and mica) in a ternary system under varying conditions. Exploratory data analysis methods were used to examine the experimental data. The GridSearchCV and Kfold cross-validation approaches were implemented to augment the performance abilities of the ML models. In addition, sensitivity plots were generated to study the influence of individual parameters on the model performance. The results indicated that the applied ML models accurately predicted the wettability behavior of the mineral/CO2/brine system under various operating conditions, where FCFNN performed better than other ML techniques with an R2 above 0.98 and an error of less than 3%.

Machine learning accelerated approach to infer nuclear magnetic resonance porosity for a middle eastern carbonate reservoir.

Carbonate rocks present a complicated pore system owing to the existence of intra-particle and interparticle porosities. Therefore, characterization of carbonate rocks using petrophysical data is a challenging task. Conventional neutron, sonic, and neutron-density porosities are proven to be less accurate as compared to the NMR porosity. This study aims to predict the NMR porosity by implementing three different machine learning (ML) algorithms using conventional well logs including neutron-porosity, sonic, resistivity, gamma ray, and photoelectric factor. Data, comprising 3500 data points, was acquired from a vast carbonate petroleum reservoir in the Middle East. The input parameters were selected based on their relative importance with respect to output parameter. Three ML techniques such as adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and functional network (FN) were implemented for the development of prediction models. The model's accuracy was evaluated by correlation coefficient (R), root mean square error (RMSE), and average absolute percentage error (AAPE). The results demonstrated that all three prediction models are reliable and consistent exhibiting low errors and high 'R' values for both training and testing prediction when related to actual dataset. However, the performance of ANN model was better as compared to other two studied ML techniques based on minimum AAPE and RMSE errors (5.12 and 0.39) and highest R (0.95) for testing and validation outcome. The AAPE and RMSE for the testing and validation results were found to be 5.38 and 0.41 for ANFIS and 6.06 and 0.48 for FN model, respectively. The ANFIS and FN models exhibited 'R' 0.937 and 0.942, for testing and validation dataset, respectively. Based on testing and validation results, ANFIS and FN models have been ranked second and third after ANN. Further, optimized ANN and FN models were used to extract explicit correlations to compute the NMR porosity. Hence, this study reveals the successful applications of ML techniques for the accurate prediction of NMR porosity.

Machine Learning-Based Accelerated Approaches to Infer Breakdown Pressure of Several Unconventional Rock Types.

Unconventional oil and gas reservoirs are usually classified by extremely low porosity and permeability values. The most economical way to produce hydrocarbons from such reservoirs is by creating artificially induced channels. To effectively design hydraulic fracturing jobs, accurate values of rock breakdown pressure are needed. Conducting hydraulic fracturing experiments in the laboratory is a very expensive and time-consuming process. Therefore, in this study, different machine learning (ML) models were efficiently utilized to predict the breakdown pressure of tight rocks. In the first part of the study, to measure the breakdown pressures, a comprehensive hydraulic fracturing experimental study was conducted on various rock specimens. A total of 130 experiments were conducted on different rock types such as shales, sandstone, tight carbonates, and synthetic samples. Rock mechanical properties such as Young's modulus (E), Poisson's ratio (ν), unconfined compressive strength, and indirect tensile strength (σt) were measured before conducting hydraulic fracturing tests. ML models were used to correlate the breakdown pressure of the rock as a function of fracturing experimental conditions and rock properties. In the ML model, we considered experimental conditions, including the injection rate, overburden pressures, and fracturing fluid viscosity, and rock properties including Young's modulus (E), Poisson's ratio (ν), UCS, and indirect tensile strength (σt), porosity, permeability, and bulk density. ML models include artificial neural networks (ANNs), random forests, decision trees, and the K-nearest neighbor. During training of ML models, the model hyperparameters were optimized by the grid-search optimization approach. With the optimal setting of the ML models, the breakdown pressure of the unconventional formation was predicted with an accuracy of 95%. The accuracy of all ML techniques was quite similar; however, an explicit empirical correlation from the ANN technique is proposed. The empirical correlation is the function of all input features and can be used as a standalone package in any software. The proposed methodology to predict the breakdown pressure of unconventional rocks can minimize the laboratory experimental cost of measuring fracture parameters and can be used as a quick assessment tool to evaluate the development prospect of unconventional tight rocks.

A Review of Enzyme-Induced Calcium Carbonate Precipitation Applicability in the Oil and Gas Industry.

Enzyme-induced calcium carbonate precipitation (EICP) techniques are used in several disciplines and for a wide range of applications. In the oil and gas industry, EICP is a relatively new technique and is actively used for enhanced oil recovery applications, removal of undesired chemicals and generating desired chemicals in situ, and plugging of fractures, lost circulation, and sand consolidation. Many oil- and gas-bearing formations encounter the problem of the flow of sand grains into the wellbore along with the reservoir fluids. This study offers a detailed review of sand consolidation using EICP to solve and prevent sand production issues in oil and gas wells. Interest in bio-cementation techniques has gained a sharp increase recently due to their sustainable and environmentally friendly nature. An overview of the factors affecting the EICP technique is discussed with an emphasis on the in situ reactions, leading to sand consolidation. Furthermore, this study provides a guideline to assess sand consolidation performance and the applicability of EICP to mitigate sand production issues in oil and gas wells.

A Review of Advanced Molecular Engineering Approaches to Enhance the Thermostability of Enzyme Breakers: From Prospective of Upstream Oil and Gas Industry.

During the fracture stimulation of oil and gas wells, fracturing fluids are used to create fractures and transport the proppant into the fractured reservoirs. The fracturing fluid viscosity is responsible for proppant suspension, the viscosity can be increased through the incorporation of guar polymer and cross-linkers. After the fracturing operation, the fluid viscosity is decreased by breakers for efficient oil and gas recovery. Different types of enzyme breakers have been engineered and employed to reduce the fracturing fluid's viscosity, but thermal stability remains the major constraint for the use of enzymes. The latest enzyme engineering approaches such as direct evolution and rational design, have great potential to increase the enzyme breakers' thermostability against high temperatures of reservoirs. In this review article, we have reviewed recently advanced enzyme molecular engineering technologies and how these strategies could be used to enhance the thermostability of enzyme breakers in the upstream oil and gas industry.

Application of Anhydrous Calcium Sulfate as a Weighting Agent in Oil-Based Drilling Fluids.

The hydrostatic pressure exerted during the drilling operation is controlled by adding a weighting agent into drilling fluids. Various weighting materials such as barite, calcium carbonate, hematite, and ilmenite are used to increase the density of drilling fluids. Some weighting additives can cause serious drilling problems, including particle settling, formation damage, erosion, and insoluble filters. In this study, anhydrite (calcium sulfate) is used as a weighting additive in the oil-based drilling fluid (OBDF). Anhydrite is an abundantly available resource used in the preparation of desiccant, plaster of Paris, and Stucco. Anhydrite application in drilling fluids is discouraged because of its filter cake removal issue. This study investigated anhydrite (anhydrous CaSO4) as a weighting agent and its filter cake removal procedure for OBDFs. The anhydrite performance as a weighting agent in OBDFs was evaluated by conducting several laboratory experiments such as density, rheology, fluid loss, and electrical stability and compared with that of commonly used weighting materials (barite, calcium carbonate, and hematite). The anhydrite was mixed in three different concentrations (62, 124, and 175 ppb) in a base-drilling fluid. The results showed that calcium sulfate enhanced rheological parameters such as plastic viscosity, yield point, apparent viscosity, and gel strength. CaSO4 reduced the fluid loss and provided better control over the fluid loss than other tested weighting materials tested at the same concentration of 124 ppb. Similarly, the emulsion stability was decreased with the increase in the amount of calcium sulfate in the OBDF. The calcium sulfate filter cake can be removed easily from the wellbore with an efficiency of 83 to 91% in single-stage and multistage removal processes, respectively using the newly developed formulation consisting of 20 wt % potassium salt of glutamic acid-N,N-diacetic acid (K4GLDA) as a chelating agent, 6 wt % potassium carbonate, and 10% ethylene glycol monobutyl ether. The introduction of anhydrite as a weighting agent can be more beneficial for both academia and industry.

Machine Learning-Based Propped Fracture Conductivity Correlations of Several Shale Formations.

In hydraulic fracturing operations, small rounded particles called proppants are mixed and injected with fracture fluids into the targeted formation. The proppant particles hold the fracture open against formation closure stresses, providing a conduit for the reservoir fluid flow. The fracture's capacity to transport fluids is called fracture conductivity and is the product of proppant permeability and fracture width. Prediction of the propped fracture conductivity is essential for fracture design optimization. Several theoretical and few empirical models have been developed in the literature to estimate fracture conductivity, but these models either suffer from complexity, making them impractical, or accuracy due to data limitations. In this research, and for the first time, a machine learning approach was used to generate simple and accurate propped fracture conductivity correlations in unconventional gas shale formations. Around 350 consistent data points were collected from experiments on several important shale formations, namely, Marcellus, Barnett, Fayetteville, and Eagle Ford. Several machine learning models were utilized in this research, such as artificial neural network (ANN), fuzzy logic, and functional network. The ANN model provided the highest accuracy in fracture conductivity estimation with R 2 of 0.89 and 0.93 for training and testing data sets, respectively. We observed that a higher accuracy could be achieved by creating a correlation specific for each shale formation individually. Easily obtained input parameters were used to predict the fracture conductivity, namely, fracture orientation, closure stress, proppant mesh size, proppant load, static Young's modulus, static Poisson's ratio, and brittleness index. Exploratory data analysis showed that the features above are important where the closure stress is the most significant.

Reduction of Breakdown Pressure by Filter Cake Removal Using Thermochemical Fluids and Solvents: Experimental and Numerical Studies.

The process of well cleanup involves the removal of an impermeable layer of filter cake from the face of the formation. The inefficient removal of the filter cake imposes difficulty on fracturing operations. Filter cake's impermeable features increase the required pressure to fracture the formation. In this study, a novel method is introduced to reduce the required breakdown pressure to fracture the formation containing the water-based drilling fluid filter cake. The breakdown pressure was tested for five samples of similar properties using different solutions. A simulated borehole was drilled in the core samples. An impermeable filter cake using barite-weighted drilling fluid was built on the face of the drilled hole of each sample. The breakdown pressure for the virgin sample without damage (filter cake) was 6.9 MPa. The breakdown pressure increased to 26.7 MPa after the formation of an impermeable filter cake. Partial removal of filter cake by chelating agent reduced the breakdown pressure to 17.9 MPa. Complete dissolution of the filter cake with chelating agents resulted in the breakdown pressure approximately equivalent to the virgin rock breakdown pressure, i.e., 6.8 MPa. The combined thermochemical and chelating agent solution removed the filter cake and reduced the breakdown pressure to 3.8 MPa. Post-treatment analysis was carried out using nuclear magnetic resonance (NMR) and scratch test. NMR showed the pore size redistributions with good communication between different pores after the thermochemical removal of filter cake. At the same time, there was no communication between the different pores due to permeability impairment after filter cake formation. The diffusion coupling through NMR scans confirmed the higher interconnectivity between different pores systems after the combined thermochemical and chelating agent treatment. Compressive strength was measured from the scratch test, confirming that filter cake formation caused added strength to the rock that impacts the rock breakdown pressure. The average compressive strength of the original specimen was 44.5 MPa that increased to 73.5 MPa after the formation of filter cake. When the filter cake was partially removed, the strength was reduced to 61.7 MPa. Complete removal with chelating agents removed the extra strength that was added due to the filter cake presence. Thermochemical and chelating agents resulted in a significantly lower compressive strength of 25.3 MPa. A numerical model was created to observe the reduction in breakdown pressure due to the thermochemical treatment of the filter cake. The result presented in this study showed the engineering applications of thermochemical treatment for filter cake removal.

Dicationic Surfactants as an Additive in Fracturing Fluids to Mitigate Clay Swelling: A Petrophysical and Rock Mechanical Assessment.

The interactions of clays with freshwater in unconventional tight sandstones can affect the mechanical properties of the rock. The hydraulic fracturing technique is the most successful technique to produce hydrocarbons from unconventional tight sandstone formations. Knowledge of clay minerals and their chemical interactions with fracturing fluids is extremely vital in the optimal design of fracturing fluids. In this study, quaternary ammonium-based dicationic surfactants are proposed as clay swelling inhibitors in fracturing fluids to reduce the fractured face skin. For this purpose, several coreflooding and breakdown pressure experiments were conducted on the Scioto sandstone samples, and the rock mechanical properties of the flooded samples after drying were assessed. Coreflooding experiments proceeded in a way that the samples were flooded with the investigated fluid and then postflooded with deionized water (DW). Rock mechanical parameters, such as compressive strength, tensile strength, and linear elastic properties, were evaluated using unconfined compressive strength test, scratch test, indirect Brazilian disc test, and breakdown pressure test. The performance of novel synthesized surfactants was compared with commercially used clay stabilizing additives such as sodium chloride (NaCl) and potassium chloride (KCl). For comparison, base case experiments were performed with untreated samples and samples treated with DW. Scioto sandstone samples with high illite contents were used in this study. Results showed that the samples treated with conventional electrolyte solutions lost permeability up to 65% when postflooded with DW. In contrast, fracturing fluid containing surfactant solutions retained the original permeability even after being postflooded with DW. Conventional clay stabilizing additives led to the swelling of clays caused by high compression and tensile strength of the rock when tested at dry conditions. Consequently, the rock fractures at a higher breakdown pressure. However, novel dicationic surfactants do not cause any swelling, and therefore, the rock fractures at the original breakdown pressure.

Novel Expandable Cement System for Prevention of Sustained Casing Pressure and Minimization of Lost Circulation.

Sustained casing pressure (SCP) is a common issue in the oil and gas industry. There were several solutions applied to contain it either by mechanical means or by injecting high-performing cement slurries. There are some limitations associated with these solutions such as volume loss, mechanical failures, limited expansion, exact spotting, and material deterioration with time. In this study, a novel expandable cement system contains a novel silicate aqueous alkali alumino silicate (AAAS) and zinc (Zn) metal slurry, and class G cement is introduced as an expandable solution to prevent annulus flow between the casing and formation. The silicate-based admixture reacts with the Zn metal slurry to generate hydrogen gas that results in the expansion of the cement slurry. The reaction and expansion can be controlled by optimizing the quantities of silicate systems and metal slurry. The expansive properties of the silicate system can be utilized to formulate a cement mix for plugging off the annulus flow. Cement slurries with different percentages such as 3, 5, and 8% by weight of water (BWOW) of AAAS silicate and Zn metal slurry were prepared and tested for their expansion. Several laboratory tests such as expansion, consistency, viscosity, and unconfined compressive strength were performed to assess the percentage expansion. The expansion was tested in the plastic tube as well as in expansion molds. The cement slurries were cured at 50 °C temperature in a water bath. It was observed that metal slurry upon reaction with AAAS silicate resulted in cement expansion by several percentages. The cement expansion was reduced by 16% at 8% BWOW concentration of AAAS silicate as compared to the expansion gained at 3% BWOW concentration. Further, the temperature triggers the expansion of cement slurry. The consistency and viscosity were impacted by the addition of AAAS and metal slurry. The application of expandable slurry can help in preventing the annulus flow and eliminating the safety issues associated with SCP. The expansion solution can be applied in loss circulation zones.

H2S Scavenging Capacity and Rheological Properties of Water-Based Drilling Muds.

Drilling hydrocarbon formations where hydrogen sulfide (H2S) is present could lead to the carryover of H2S with the drilling mud (i.e., drilling fluid) to the surface, exposing working personnel to this lethal gas. Additionally, H2S is very corrosive, causing severe corrosion of metal parts of the drilling equipment, which in turn results in serious operational problems. The addition of an effective H2S scavenger(s) in the drilling mud formulations will overcome these health, safety, and operational issues. In this work, zinc oxide (ZnO), which is a common H2S scavenger, has been incorporated into water-based drilling mud. The H2S scavenging performance of this ZnO-containing drilling mud has been assessed. Additionally, drilling mud formulations containing either copper nitrate (Cu(NO3)2·3H2O) or potassium permanganate (KMnO4) have been prepared, and their H2S scavenging performances have been studied and compared to that of the ZnO-containing drilling mud. It has been observed that the scavenging performance (in terms of the H2S amounts scavenged up to the breakthrough time and at the saturation condition) of the ZnO-containing drilling mud is very poor compared to those of the copper nitrate-containing and KMnO4-containing drilling muds. For instance, the amounts of H2S scavenged up to the breakthrough time by ZnO-containing, copper nitrate-containing, and KMnO4-containing drilling muds were 5.5, 15.8, and 125.3 mg/g, respectively. Furthermore, the amounts of H2S scavenged at the saturation condition by these drilling muds were, respectively, 35.1, 146.8, and 307.5 mg/g, demonstrating the superiority of the KMnO4-containing drilling mud. Besides its attractive H2S scavenging performance, the KMnO4-containing drilling mud possessed more favorable rheological properties [i.e., plastic viscosity (PV), yield point (YP), carrying capacity of the drill cuttings, and gelling characteristics] relative to the base and the ZnO-containing and copper nitrate-containing drilling muds. The addition of KMnO4 to the base drilling mud increased its apparent viscosity, PV, and YP by 20, 33, and 10%, respectively. Additionally, all tested drilling muds possessed acceptable fluid loss characteristics. To the best of our knowledge, there are so far no published studies concurrently tackling the H2S scavenging (i.e., breakthrough time, breakthrough capacity, saturation time, saturation capacity, and scavenger utilization) and the rheological properties of water-based drilling muds, as demonstrated in the current study, highlighting the novelty of this work.

Data-Driven Acid Fracture Conductivity Correlations Honoring Different Mineralogy and Etching Patterns.

Acid-fracturing operations are mainly applied in tight carbonate formations to create a highly conductive path. Estimating the conductivity of a hydraulic fracture is essential for predicting the fractured well productivity. Several models were developed previously to estimate the conductivity of acid-fractured rocks. In this research, machine learning methods were applied to 560 acid fracture experimental datapoints to develop several conductivity correlations that honor the rock types and etching patterns. Developing one universal correlation often results in significant error. To develop conductivity correlations, various data preprocessing methods were applied to remove the outliers and failed experiments. Features that did not contribute to precise predictions were removed through regularization. A machine learning classifier was built to predict the etching pattern based on the input data. We generated a multivariate linear regression model and compared it with other models generated through ridge regression. In addition to that, artificial neural network-based model was proposed to predict the fracture conductivity of several carbonate rocks such as dolomite, chalk, and limestone. The performance of the developed models was assessed using well-known metrics such as precision, accuracy, mean squared error, recall, and correlation coefficients. Cross-validation was also employed to assure accuracy and avoid overfitting. The classifier accuracy was 93%, while the regression model resulted in a relatively high correlation coefficient.

Development of New Rheological Models for Class G Cement with Nanoclay as an Additive Using Machine Learning Techniques.

The rheology of the oil well cement plays a pivotal role in the cement placement. Accurate prediction of cement rheological parameters helps to monitor the durability and pumpability of the cement slurry. In this study, an artificial neural network is used to develop different models for the prediction of various rheological parameters such as shear stress, apparent viscosity, plastic viscosity, and yield point of a class G cement slurry with nanoclay as an additive. An extensive experimental study was conducted to generate enough data set for the training of artificial intelligence models. The class G oil well cement slurries were prepared by fixing the water-cement ratio to 0.44 and adding organically modified nanoclays as a strength enhancer. The rheological properties of the oil well cement slurries were investigated at a wide range of temperatures (37 ≤ T ≤ 90 °C) and shear rates (5 ≤ γ ≤ 500 s-1). Experimental data generated were used for the training of feed-forward neural networks. The predicted values of the rheological properties from the trained model showed a good agreement when compared with the experimental values. The average absolute percentage error was less than 5% in both training and validation phases of modeling. A trend analysis was carried out to ensure that the proposed models can define the underlying physics. From the validation and the trend analysis, it was found that the new models can be used to predict cement rheological properties within the range of data set on which the models were trained. The proposed models are independent of laboratory-dependent variables and can give quick and real-time values of the rheological parameters.

Effects of Nanoclay and Silica Flour on the Mechanical Properties of Class G Cement.

The mechanical properties of oil well cement slurry are usually measured to evaluate the durability, sustainability, and long-lasting behavior of a cement sheath under wellbore conditions. High-pressure and high-temperature (HPHT) conditions affect the mechanical properties of cement slurry such as its strength, elasticity, and curing time. In this study, an organically modified montmorillonite nanoclay (NC) and silica flour (SF) materials are used to enhance the strength of the class G cement. Four different cement slurries with the addition of different concentrations of NC (1% and 2%) and SF (20%) in a class G cement were tested under temperatures ranging between 70 and 100 °C and pressure ranging between 1000 and 3000 psia. The slurries were prepared by maintaining a water to cement ratio of 0.44. All the slurries were cured for 24 h before any test was conducted. Extensive laboratory experiments were carried out to measure the compressive and tensile strength of cement slurries cured at HPHT conditions. Compressive strength was measured using unconfined compressive strength (UCS) tests, scratch tests, and ultrasonic cement analyzer (UCA). Tensile strength was measured using breakdown pressure tests and Brazilian disc test analysis. Scanning electron microscopy (SEM), X-ray diffraction (XRD), and petrophysical analysis were also carried out to evaluate the performance of new cement additives at HPHT conditions. Results showed that the addition of organically modified NC and SF significantly increased the compressive and tensile strength of the class G cement slurry cured at HPHT conditions.