Hybrid Computational Intelligence

As Artificial Intelligence (AI) technologies become increasingly embedded in critical organizational decision-making processes, questions of ethics, accountability, and integrity have risen to the forefront of academic and industry discourse. This study investigates the ethical implications of AI in decisionmaking, with a specific focus on how organizations can balance technological innovation with moral responsibility and regulatory accountability. Guided by an integrated theoretical framework that combines Ethical Decision-Making Theory, Stakeholder Theory, the Technology Acceptance Model (TAM), and the Responsible Innovation Framework, this research provides a multidimensional perspective on AI ethics in practice. A quantitative research methodology was employed, gathering data from 395 stakeholders including AI developers, corporate leaders, ethics compliance officers, public regulators, data scientists, and end-users across sectors such as finance, healthcare, education, and government services. The study examines stakeholder perceptions on key ethical dimensions of AI implementation-algorithmic transparency, data privacy, bias mitigation, informed consent, accountability mechanisms, and the inclusiveness of AI design. A structured survey instrument was used to assess how these variables influence organizational trust, adoption willingness, and public acceptance of AI-driven decisions. The findings are expected to demonstrate that organizations that embed ethical safeguards and transparent governance frameworks within their AI systems can significantly enhance stakeholder trust, user engagement, and regulatory compliance. The study also highlights critical challenges, including the opacity of black-box algorithms, the absence of global ethical standards, the underrepresentation of marginalized groups in algorithmic training data, and the tensions between innovation speed and ethical reflection. Additionally, it explores how external institutional pressures-such as media scrutiny, customer expectations for ethical AI, investor demand for ESG-compliant practices, and evolving legal mandates-act as catalysts for adopting ethical AI governance models. This research makes several key contributions. First, it bridges a significant gap in the empirical literature on AI ethics by quantitatively analyzing perceptions across diverse industries and stakeholder categories. Second, it offers a conceptual model for balancing innovation with ethical accountability that can guide practitioners, policymakers, and technologists in AI strategy formulation. Third, it provides a framework for integrating responsible AI principles into corporate governance and digital transformation strategies. The study ultimately advocates for the co-evolution of ethical standards and AI capabilities to ensure that technological progress does not come at the expense of human values, social justice, or democratic integrity.

The maritime industry stands at a pivotal juncture, poised for a transformative shift driven by artificial intelligence. This academic study provides a comprehensive blueprint for the "AI-Powered Digital Captain," a multi-layered system designed not merely to automate, but to redefine vessel operations. Our analysis moves beyond a purely technical discussion to present a holistic framework that integrates innovative technology with the paramount importance of human expertise. It explores the systemic anatomy of the Digital Captain, from its on-vessel bionic reflexes for real-time crisis response to its shore-based command hubs.

As maritime transport continues to be the lifeblood of global trade, it stands on the cusp of a profound transformation driven by autonomous vessels and AI-powered systems. This research goes beyond a mere technological transition, providing an in-depth exploration of the complex integration of AI-driven Digital Captains, their emergency response capabilities, and the psychological underpinnings of human-machine interaction. Our study outlines a strategic framework for post-2030 autonomous maritime operations, demonstrating how technological innovation must be seamlessly interwoven with regulatory compliance, ethical considerations, and human cognition.

A key contribution of this work is the development of a novel algorithmic training paradigm that translates the human-centric competencies of the International Convention on Standards of Training, Certification and Watchkeeping for Seafarers (STCW) into verifiable, data-driven standards for AI. Furthermore, it introduces the concept of a "Neurotic AI," a perpetually vigilant system designed to anticipate failures and collaborate with human operators, ensuring seamless and safe transitions in high-stakes environments. This work offers a forward-looking roadmap for an ecosystem where technology enhances, rather than sidelines, human judgment, steering the industry towards a safer and more efficient future.

This systematic literature review examines how data privacy can be engineered and governed as an intrinsic property of business intelligence (BI) programs that consume Human Resource Information Systems (HRIS) and wider enterprise platforms. Following a registered PRISMA protocol, we searched multidisciplinary databases, screened records in duplicate, appraised quality with designappropriate tools, and synthesized heterogeneous evidence narratively and thematically. In total, 115 peer-reviewed articles and standards met the inclusion criteria. The synthesis maps regulatory obligations such as purpose limitation, minimization, storage limitation, transparency, rights handling, accountability, and integrity-confidentiality to concrete controls across the analytics lifecycle. We find that privacy outcomes improve when governance is encoded in code via policy-as-code approvals, slim ingestion schemas, retention rules, and purpose tags; least-privilege access is most durable when role-based baselines are refined with attribute-based context and enforced as row-and column-level security at the semantic layer; protection works best as a choreography that assigns encryption, tokenization, pseudonymization, and masking to precise pipeline stages; and verification hinges on engineered lineage, runtime observability, and tamper-evident audit logs that make "what happened to whose data and why" answerable under audit. We also surface operational patterns for DSAR fulfillment, retention and erasure in warehouses and lakehouses, machine unlearning for models, and cross-border and vendor risk mitigations using customer-managed keys, regionalization, and purpose-aware authorization. Contributions include a regulation-to-engineering crosswalk, a reference architecture, a maturity model, DPIA prompt templates tailored to analytics, and a compact assurance metric set for continuous monitoring. Collectively, the review translates legal principles into testable, auditable design choices that enable compliant, trustworthy HRIS-to-BI analytics at scale.

This paper refines the Lagrangian formulation of a consciousnesscoupled Theory of Everything (ToE), providing explicit derivations of the field dynamics and numerical estimates for experimental predictions. We expand on the non-commutative spacetime algebra, derive the stress-energy tensor for ψ C , and quantify expected anomalies in quantum systems (e.g., ∆[x, p] shifts of order 10-34 J•s under EEG modulation). Supported by 21 references from quantum biology, AdS/CFT, and LQG, we demonstrate mathematical consistency with empirical bounds (e.g., LIGO's strain sensitivity ∼ 10-23).

This systematic review investigates the psychological and socioeconomic risk indicators that influence loan default behavior, aiming to bridge the gap between traditional credit assessment models and emerging behavioral insights. As financial institutions increasingly face challenges in accurately predicting borrower defaults, it becomes crucial to explore non-traditional variables such as cognitive biases, personality traits, financial literacy, income volatility, and employment stability. Drawing on a comprehensive synthesis of 67 peer-reviewed studies published between 2010 and 2024, this review analyzes a wide range of empirical evidence from diverse geographical, cultural, and lending contexts. The findings indicate that behavioral factors particularly impulsivity, time-inconsistency, and overconfidence play a critical role in undermining repayment discipline, especially when compounded by limited financial literacy and socioeconomic instability. Moreover, the review highlights the growing use of behavioral interventions, such as personalized nudges, commitment devices, and financial education tools, which have shown measurable effectiveness in reducing default rates. The integration of behavioral analytics into credit risk assessment, as seen in emerging hybrid models, represents a shift toward more holistic, personalized, and accurate prediction frameworks. Additionally, the review underscores the importance of tailoring financial products and risk models to cultural and contextual realities, particularly in underserved markets. By synthesizing interdisciplinary research across economics, psychology, and finance, this study provides a comprehensive framework for understanding the multidimensional drivers of loan default and offers strategic insights for lenders, policymakers, and fintech innovators aiming to enhance creditworthiness assessment and borrower support systems.

Currently, engineers are using numerical correlations to describe the flow of oil and gas through chokes. These numerical correlations are not 100% accurate, as indicated by other studies, so there is a need to find a better approach to describe and calculate the choke size. Artificial intelligence (AI) can be used for better results. In this study, AI was used to estimate the optimum choke size that is required to meet the desired flow rate. Four techniques are used in this study: artificial neural networks, fuzzy logic (FL), support vector machines, and functional networks. Results obtained using these techniques were compared. After researching each technique, FL was found to give the best predictions.

Computational intelligence (CI) techniques have positively impacted the petroleum reservoir characterization and modeling landscape. However, studies have showed that each CI technique has its strengths and weaknesses. Some of the techniques have the ability to handle datasets of high dimensionality and fast in execution, while others are limited in their ability to handle uncertainties, difficult to learn, and could not deal with datasets of high or low dimensionality. The ''no free lunch'' theorem also gives credence to this problem as it postulates that no technique or method can be applicable to all problems in all situations. A technique that worked well on a problem may not perform well in another problem domain just as a technique that was written off on one problem may be promising with another. There was the need for robust techniques that will make the best use of the strengths to overcome the weaknesses while producing the best results. The machine learning concepts of hybrid intelligent system (HIS) have been proposed to partly overcome this problem. In this review paper, the impact of HIS on the petroleum reservoir characterization process is enumerated, analyzed, and extensively discussed. It was concluded that HIS has huge potentials in the improvement of petroleum reservoir property predictions resulting in improved exploration, more efficient exploitation, increased production, and more effective management of energy resources. Lastly, a number of yet-to-be-explored hybrid possibilities were recommended.

This paper presents a comparative study of the performance of three versions of Adaptive Neuro-Fuzzy Inference System (ANFIS) hybrid model and two innovative hybrid models in the prediction of oil and gas reservoir properties. ANFIS is a hybrid learning algorithm that combines the rule-based inferencing of fuzzy logic and the back-propagation learning procedure of Artificial Neural Networks. Functional Networks-Support Vector Machines (FN-SVM) and Functional Networks-Type-2 Fuzzy Logic (FN-T2FL) were proposed to improve the performance of the stand-alone SVM and T2FL models respectively. The FN component of the FN-T2FL hybrid model automatically extracts the most relevant attributes from the input data using the least square fitting algorithm as an improvement over the individual Functional Networks and Type-2 Fuzzy Logic models. The former is more promising as it combines two existing techniques that are very close in performance and well known for their computational stability and fast processing. The FN-SVM hybrid model also benefits from the excellent performance of the least-square-based model-selection algorithm of Functional Networks and the non-linear high-dimensional feature transformation capability that is based on structural risk minimization and Tikhonov regularization properties of SVM. Training and testing the SVM component of the hybrid model with the best and dimensionally-reduced variables from the input data resulted in better performance with higher correlation coefficients, lower root mean square errors and less execution time than the traditional SVM model. A comparison of FN-SVM and FN-T2FL with the three versions of ANFIS showed the superiority of the FN-SVM model over the others. The three ANFIS models still proved to be good in solving real industrial problems due to their speed of execution especially in dense data conditions.

This paper was selected for presentation by an SPE program committee following review of information contained in an abstract submitted by the author(s). Contents of th e paper have not been reviewed by the Society of Petroleum Engineers and are subject to correction by the author(s). The material does not necessarily reflect any position of the Society of Petroleum Engineers, its officers, or members. Electronic reproduction, distribution, or storage of any part of this paper without the written consent of the Society of Petroleum Engineers is prohibited.

Various computational intelligence techniques have been used in the prediction of petroleum reservoir properties. However, each of them has its limitations depending on different conditions such as data size and dimensionality. Hybrid computational intelligence has been introduced as a new paradigm to complement the weaknesses of one technique with the strengths of another or others. This paper presents a computational intelligence hybrid model to overcome some of the limitations of the standalone type-2 fuzzy logic system (T2FLS) model by using a least-square-fitting-based model selection algorithm to reduce the dimensionality of the input data while selecting the best variables. This novel feature selection procedure resulted in the improvement of the performance of T2FLS whose complexity is usually increased and performance degraded with increased dimensionality of input data. The iterative least-square-fitting algorithm part of functional networks (FN) and T2FLS techniques were combined in a hybrid manner to predict the porosity and permeability of North American and Middle Eastern oil and gas reservoirs. Training and testing the T2FLS block of the hybrid model with the best and dimensionally reduced input variables caused the hybrid model to perform better with higher correlation coefficients, lower root mean square errors, and less execution times than the standalone T2FLS model. This work has demonstrated the promising capability of hybrid modelling and has given more insight into the possibility of more robust hybrid models with better functionality and capability indices.

This systematic literature review provides a comprehensive and methodologically rigorous synthesis of scholarly work on Intelligent Support Systems (ISS), focusing on their design architectures, strategic applications, ethical governance, and human-AI interaction (HAII) frameworks within organizational contexts. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines, the review evaluates 124 peer-reviewed journal articles published between 2013 and 2023, ensuring transparency, reproducibility, and academic rigor in article selection and synthesis. The findings reveal a significant shift in ISS development from traditional rule-based systems toward hybrid and neural network-driven architectures, which offer improved predictive capabilities, flexibility, and real-time responsiveness. However, this transition introduces new challenges, particularly in terms of model interpretability, trust calibration, and dynamic system transparency. The review also identifies a growing trend in the adoption of AI-augmented strategic decision-making tools, such as decision-tree learning and reinforcement learning, which support portfolio management, resource optimization, and scenario-based planning. Despite these advancements, there is a notable deficiency in longitudinal performance evaluation, with very few studies tracking system impact or user trust over extended periods. While regulatory and governance frameworks such as GDPR, NIST AI RMF, and ISO/IEC standards are frequently referenced, only a limited number of studies report concrete implementation in live systems. The study concludes that future research must adopt a multidisciplinary lens, incorporating ethical AI principles, culturally aware design, longterm performance tracking, and user-centric evaluation metrics to ensure that ISS technologies evolve in a responsible, equitable, and sustainable manner. This review contributes to bridging the gap between advanced computational capabilities and the ethical, strategic, and social imperatives that define effective decision support in contemporary enterprises.

Quantum algorithms present unique advantages over classical methods but remain constrained by the limited number of qubits in current quantum computers. This limitation hinders their effectiveness in machine learning tasks, such as image classification. Despite its relevance, the impact of these constraints on quantum machine learning remains underexplored. This study addresses this gap by analyzing preprocessing techniques for preparing images on quantum processors. We evaluated 10 dimensionality reduction methods across four standard datasets using three distinct quantum neural network architectures. The results provide valuable insights into optimizing classification efficiency under qubit constraints, paving the way for broader applications of quantum machine learning.

Flow measurement is an essential requirement for monitoring and controlling oil movements through pipelines and facilities. However, delivering reliably accurate measurements through certain meters requires cumbersome calculations that can be simplified by using supervised machine learning techniques exploiting optimizers. In this study, a dataset of 6292 data records with seven input variables relating to oil flow through 40 pipelines plus processing facilities in southwestern Iran is evaluated with hybrid machine-learning-optimizer models to predict a wide range of oil flow rates (Qo) through orifice plate meters. Distance-weighted K-nearest-neighbor (DWKNN) and multi-layer perceptron (MLP) algorithms are coupled with artificial-bee colony (ABC) and firefly (FF) swarmtype optimizers. The two-stage ABC-DWKNN Plus MLP-FF model achieved the highest prediction accuracy (root mean square errors = 8.70 stock-tank barrels of oil per day) for oil flow rate through the orifice plates, thereby removing dependence on unreliable empirical formulas in such flow calculations.

Abstract. A thin film carbon monoxide (CO) gas sensor based on PEDOT:PSS/Fe (salen) has been developed using the spin coating technique on several glass pieces with interdigitated Au electrodes. The change in electrical resistance of the sensors with various content of dopants was measured in different CO gas concentrations and temperatures. It is found that Fe (salen) as a dopant can significantly improve the performance of PEDOT:PSS based gas sensors. Least square support vector regression (LSSVM) method was applied to predict the gas response characteristics of the films for different testing conditions. Modeling results show a satisfactory agreement with experimental findings.

In this study, using Adaptive Neuro-Fuzzy Inference System (ANFIS) an intelligent model was developed to predict bubble point oil formation volume factor (Bob) for Middle East crudes. A total of 429 data sets, included Bob and conventional PVT properties, were used. Among those, 286 and 143 data sets were selected randomly for constructing and testing the model, respectively. The mean squared errors and correlation coefficient (R) between predicted values from the modeling and experimental values in the test data were 0.0023 and 0.9731, respectively. The model, which promptitude and save in time and costs are its advantages, is more accurate than all of the previous empirical correlations.

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Currently, engineers are using numerical correlations to describe the flow of oil and gas through chokes. These numerical correlations are not 100% accurate, as indicated by other studies, so there is a need to find a better approach to describe and calculate the choke size. Artificial intelligence (AI) can be used for better results. In this study, AI was used to estimate the optimum choke size that is required to meet the desired flow rate. Four techniques are used in this study: artificial neural networks, fuzzy logic (FL), support vector machines, and functional networks. Results obtained using these techniques were compared. After researching each technique, FL was found to give the best predictions.

In this study, using Adaptive Neuro-Fuzzy Inference System (ANFIS) an intelligent model was developed to predict bubble point oil formation volume factor (Bob) for Middle East crudes. A total of 429 data sets, included Bob and conventional PVT properties, were used. Among those, 286 and 143 data sets were selected randomly for constructing and testing the model, respectively. The mean squared errors and correlation coefficient (R) between predicted values from the modeling and experimental values in the test data were 0.0023 and 0.9731, respectively. The model, which promptitude and save in time and costs are its advantages, is more accurate than all of the previous empirical correlations.

Thorough knowledge of PVT properties of oil and gas reservoirs plays an important role in forecasting the phase behavior of oil reservoirs and designing appropriate actions for optimized production from them. Among these PVT properties, some have a determinative role in gas and oil equilibrium in the hydrocarbon reservoirs. In this study, a powerful computational intelligent model is designed to develop a reliable model for predicting amount of dissolved gas in oil at reservoir conditions as one of the most important PVT properties of reservoir oils. To achieve this model, different Adaptive Neuro-Fuzzy Inference System (ANFIS) models (by changing the training optimization algorithms) are designed. Moreover, prediction accuracy of the developed models has been compared with the number of wellknown correlations in literature. The results show that the proposed model has a significantly improved performance in comparison with the other existing correlations.

Abstract. A thin film carbon monoxide (CO) gas sensor based on PEDOT:PSS/Fe (salen) has been developed using the spin coating technique on several glass pieces with interdigitated Au electrodes. The change in electrical resistance of the sensors with various content of dopants was measured in different CO gas concentrations and temperatures. It is found that Fe (salen) as a dopant can significantly improve the performance of PEDOT:PSS based gas sensors. Least square support vector regression (LSSVM) method was applied to predict the gas response characteristics of the films for different testing conditions. Modeling results show a satisfactory agreement with experimental findings.

One of the challenges that reservoir engineers, drilling engineers, and geoscientists face in the oil and gas industry is determining the fracture density (FVDC) of reservoir rock. This critical parameter is valuable because its presence in oil and gas reservoirs boosts productivity and is pivotal for reservoir management, operation, and ultimately energy management. This valuable parameter is determined by some expensive operations such as FMI logs and core analysis techniques. As a result, this paper attempts to predict this important parameter using petrophysics logs routinely collected at oil and gas wells and by applying four robust computational algorithms and artificial intelligence hybrids. A total of 6067 data points were collected from three gas wells (#W1, #W2, and #W3) in one gas reservoir in Southwest Asia. Following feature selection, the input variables include spectral gamma ray (SGR); sonic porosity (PHIS); potassium (POTA); photoelectric absorption factor (PEF); ne...

Abstract. A thin film carbon monoxide (CO) gas sensor based on PEDOT:PSS/Fe (salen) has been developed using the spin coating technique on several glass pieces with interdigitated Au electrodes. The change in electrical resistance of the sensors with various content of dopants was measured in different CO gas concentrations and temperatures. It is found that Fe (salen) as a dopant can significantly improve the performance of PEDOT:PSS based gas sensors. Least square support vector regression (LSSVM) method was applied to predict the gas response characteristics of the films for different testing conditions. Modeling results show a satisfactory agreement with experimental findings.

Adequate Knowledge of reservoir fluid characteristics (e.g., bubble point pressure) plays a crucial role while conducting modeling/simulation of production processes in petroleum reservoirs. Although many efforts have been made to obtain proper correlations for prediction of bubble point pressure (BPP) of reservoir fluids, there is still relatively high magnitude of error with the developed predictive tools available in the literature. To fill this lacuna, a robust and effective technique, called gene expression programming (GEP), is employed to determine BPP of crude oil samples as a function of temperature, oil composition, molecular weight of C 7+ , and specific gravity of C 7+. The GEP method is built based on the experimental (or real) data used for training and testing phases in order to develop an appropriate correlation. The previous predictive methods are also reported in this study and employed to calculate BPP as a function of independent parameters when the same data bank is utilized. Comparing the outputs obtained

The accuracy of many petroleum engineering calculations (e.g., material balance calculations, reserve estimation, well test analysis, advanced production data analysis, nodal analysis, surface network modeling, surface separation, and numerical reservoir simulations) largely depends on the accuracy of the data on pressure, volume, and temperature (PVT). An approach to improve the material balance calculation method is presented in this study. To achieve the objective, PVTP and MBAL Software programs were applied. PVT model was built by different methods. Software was implemented to calculate stock-tank oil, initially in place (STOIIP), using different approaches. Sensitive analysis was performed to investigate the effect of different parameters on material balance calculation. Illustration of the proposed approach was done on the data obtained from AL-Nasr oil field. The Average absolute error of PVT properties such as bubble-point pressure, relative volume, oil formation volume factor,Solution gas oil ratio and oil density is used to compare between actual and calculated values. Results showed a good agreement. History production (cumulative oil production, cumulative gas production, cumulative water production) were also calculated to investigate the match between history parameters and calculated parameters. Results indicated that the impact of PVT errors on material balance calculations can be significant.

      The accuracy of many petroleum engineering calculations (e.g., material balance calculations, reserve estimation, well test analysis, advanced production data analysis, nodal analysis, surface network modeling, surface separation, and numerical reservoir simulations) largely depends on the accuracy of the data on pressure, volume, and temperature (PVT). An approach to improve the material balance calculation method is presented in this study.    To achieve the objective, PVTP and MBAL Software programs were applied. PVT model was built by different methods. Software was implemented to calculate stock-tank oil, initially in place (STOIIP), using different approaches. Sensitive analysis was performed to investigate the effect of different parameters on material balance calculation.  Illustration of the proposed approach was done on the data obtained from AL-Nasr oil field.    The Average absolute error of PVT properties such as bubble-point pressure, relative volume, oil formati...

Accurate predictions of fluid properties, such as density, oil formation volume factor and bubble point pressure, are essentials for all reservoir engineering calculations. In this paper, an approach based on nonlinear system identification modeling; Nonlinear ARX (NARX) and Hammerstein-Wiener (HW) predictive model, is proposed for forecasting the pressure/volume/temperature (PVT) properties of crude oil systems. To this end, two datasets; one containing 168 PVT samples from different Iranian oil reservoirs and other a databank containing 755 data from various geographical locations, were employed to construct (i.e. train) and evaluate (i.e. test) the models. Simulation results demonstrate that the proposed NARX and HW models outperform previously employed methods including three types of artificial neural networks models (committee machine, multilayer perceptron and radial basis function), two types of ANFIS models (grid partition and fuzzy c-mean) and several empirical correlations with the smallest prediction error, and that they are reliable models for predicting the oil properties in reservoirs engineering among other soft computing approaches.

Determining BPP is one of the critical parameters for the development of oil and gas reservoirs and have this parameter requires a lot of time and money. As a result, this study aims to develop a new predictive model for BPP that uses some available input variables such as solution oil ratio (Rs), gas specific gravity (γg), API Gravity (API). In this study, two innovatively combined hybrid algorithms, DWKNN-GSA and DWKNN-ICA, are developed to predict BPP. The outcomes of the study show the models developed are capable of predicting BPP with promising performance, where the best result was achieved for DWKNN-ICA (RMSE = 0.90276 psi and R2 = 1.000 for the test dataset). Moreover, the performance comparison of the developed hybrid models with some previously developed models revealed that the DWKNN-ICA outperforms the former empirical models with respect to perdition accuracy. In addition to presenting new techniques in the present study, the effect of each of the input parameters on B...

This paper presents the modelling of wear data resulting from linear dry contact using artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) with the aim of constructing predictor models for the depth and volume of the wear scar, with great impact in the characterization of new industrial processes utilizing existing materials. The dataset is the result of laboratory testing, presenting both numerical and categorical variables whose inclusion into the model allows for a number of possibilities. The width of the wear scar was measured on a microscope, and its depth was calculated. A multitude of experimental tests was performed with normal loads and different speeds, which led to some conclusive results, but in some cases, with relatively high variance. Various options for the automatic generation of fuzzy inference systems were also approached (genfis2). The innovative approach was compared with a baseline model featuring multivariate linear regression optimized using gradient descent, drawing on previous experimentation on the same dataset. The models developed can be implemented in future research and in practical applications under similar conditions, aiming to optimize performance by applying Computer Science. The obtained results lead to highly accurate prediction models which are further integrated into various metallic surface characterizations in the wear process for tribological and robotics research in new industrial processes using short glass fiber reinforced polymers.

One of the challenges that reservoir engineers, drilling engineers, and geoscientists face in the oil and gas industry is determining the fracture density (FVDC) of reservoir rock. This critical parameter is valuable because its presence in oil and gas reservoirs boosts productivity and is pivotal for reservoir management, operation, and ultimately energy management. This valuable parameter is determined by some expensive operations such as FMI logs and core analysis techniques. As a result, this paper attempts to predict this important parameter using petrophysics logs routinely collected at oil and gas wells and by applying four robust computational algorithms and artificial intelligence hybrids. A total of 6067 data points were collected from three gas wells (#W1, #W2, and #W3) in one gas reservoir in Southwest Asia. Following feature selection, the input variables include spectral gamma ray (SGR); sonic porosity (PHIS); potassium (POTA); photoelectric absorption factor (PEF); ne...

It is well known that the kingdom of Saudi Arabia is a vast natural potential for developing solar energy, there so solar power generation is growing rapidly. Solar energy depends on different weather and meteorological factors. Moreover, solar radiation variations throughout the year are considered an obstacle for predicting the solar energy. There so it is needed to develop predictive model that gives a precise estimation of the solar energy. The paper proposes effective model to give a reliable prediction of the global horizontal irradiance for the next day in Hail city. Estimating global horizontal irradiance has its influence on different outcomes for solar energy generation companies. It helps in reducing electricity production costs. The developed model applies subtractive clustering algorithm for generating initial model. Afterwards, it applies adaptive neuro-fuzzy inference system for tuning the parameters of the membership functions of the generated model. The simulation r...

The precise estimation of oilfield PVT properties is of primary importance for improving field evaluation and development strategies. In the present work, adaptive network-based fuzzy inference system (ANFIS) and genetic programming (GP) models were established for the accurate assessment of reservoir oil formation volume factor (OFVF). A large database including nearly 1200 datapoints from all over the globe was collected for modeling. The performance of the new models was compared to correlations in the existing literature via several graphical and

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. Porosity is of vital importance for describing the hydrocarbon reservoirs. It is used for various purposes such as hydrocarbon reserves estimation, describing the reservoir quality, and fluid flow properties within the oil/gas reservoirs. Total porosity is the combination of all types of porosity of the rock formation i.e. effective, isolated porosity and fractures porosity. Generally, it is assumed for the shale free formations (clean formations) and for carbonate formations that effective porosity is equal to total porosity of the formation however it is not true for all cases. Otherwise, correction has to be applied for shale content present in the rock formation as shale presence may lead to the overestimation of formation porosity. There are several techniques of porosity determination in the field and laboratory such like helium porosity in laboratory, mercury injection, nuclear magnetic resonance (NMR), x-ray computed tomography, density logs, sonic logs, neutron porosity. However, among all the techniques, NMR has been found the most reliable and robust technique for the accurate determination of accurate total porosity 1 .

Determining BPP is one of the critical parameters for the development of oil and gas reservoirs and have this parameter requires a lot of time and money. As a result, this study aims to develop a new predictive model for BPP that uses some available input variables such as solution oil ratio (Rs), gas specific gravity (γg), API Gravity (API). In this study, two innovatively combined hybrid algorithms, DWKNN-GSA and DWKNN-ICA, are developed to predict BPP. The outcomes of the study show the models developed are capable of predicting BPP with promising performance, where the best result was achieved for DWKNN-ICA (RMSE = 0.90276 psi and R2 = 1.000 for the test dataset). Moreover, the performance comparison of the developed hybrid models with some previously developed models revealed that the DWKNN-ICA outperforms the former empirical models with respect to perdition accuracy. In addition to presenting new techniques in the present study, the effect of each of the input parameters on B...

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

The reservoir fluid properties, the solution gas-oil ratio (GOR), are of great importance in various aspects of petroleum engineering. Therefore, a rapid means for estimating such parameters is much sort after. In this study, the linear interaction and general optimization method is applied in the development of a precise and reliable model for estimating the solution GOR. In order to develop a model that would be comprehensive, a reliable and extensive databank comprising of more than 1000 datasets collected from various geographical locations, including Asia, Mediterranean Basin, North America, Africa, and Middle East was compiled. Furthermore, the model developed was benchmarked against widely-used empirical methods in order to evaluate the performance of method proposed in predicting solution GOR data. The results show that the model proposed in this study outperforms the empirical methods to which it was compared. This study also investigated the influence of the reservoir fluid properties on the estimated solution GOR for the newly-developed model. Results show that bubble point pressure and gas gravity have the largest and the smallest influences on the predicted solution GOR, respectively. Finally, the Leverage approach was applied to determine the applicability domain for the proposed method via the detection of outlier data points. It was determined that only 26 data points, out of more than 1000 data, are identified as outlier data points.

The effective stress parameter (χ) is applied to obtain the shear strength of unsaturated soils. In this study, two adaptive neuro-fuzzy inference system (ANFIS) models, including SC-FIS model (created by subtractive clustering) and FCM-FIS model (created by Fuzzy c-means (FCM) clustering), are presented for prediction of χ and the results are compared. The soil water characteristic curve fitting parameter (λ), the confining pressure, the suction and the volumetric water content in dimensionless forms are used as input parameters for these two models. Using a trial and error process, a series of analyses were performed to determine the optimum methods. The ANFIS models are constructed, trained and validated to predict the value of χ. The quality of the ANFIS prediction ability was quantified in terms of the determination coefficient (R 2), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). These two ANFIS models are effectively able to predict the value of χ with reasonable values of R 2 , RMSE and MAE. Sensitivity analysis was used to acquire the effect of input parameters on χ prediction, and the results revealed that the confining pressure and the volumetric water content parameters had the most influence on the prediction of χ.

Classical decision and value of information theories have been applied in the oil and gas industry from the 1960s with partial success. In this research, we identify that the classical theory of value of information has weaknesses related with optimal data acquisition selection, data fuzziness and fuzzy decision criteria and we propose a modification in the theory to fill the gaps found. The research presented in this paper integrates theories and techniques from statistical analysis and artificial intelligence to develop a more coherent, robust and complete methodology for assessing the value of acquiring new information in the context of the oil and gas industry. The proposed methodology is applied to a case study describing a value of information assessment in an oil field where two alternatives for data acquisition are discussed. It is shown that: i) the technique of design of experiments provides a full identification of the input parameters affecting the value of the project and allows a proper selection of the data acquisition actions, ii) when the fuzziness of the data is included in the assessment, the value of the data decreases compared with the case where data are assumed to be crisp; this result means that the decision concerning the value of acquiring new data depends on whether the fuzzy nature of the data is included in the assessment and on the difference between the project value with and without data acquisition, iii) the fuzzy inference system developed for this case study successfully follows the logic of the decision-maker and results in a straightforward system to aggregate decision criteria.

Knowledge of permeability, a measure of the ability of rocks to allow fluids to flow through them, is essential for building accurate models of oil and gas reservoirs. Permeability is best measured in the laboratory using special core analysis (SCAL), but this is expensive and time-consuming. This is the first major work on predicting permeability in the in the UK Continental Shelf (UKCS) based only on routine core analysis (RCA) data and a machine-learning approach. We present a comparative analysis of the various machine learning algorithms and validate the results, using permeability measured on 273 core samples from 104 wells. Results suggest that machine learning can predict permeability with relatively high accuracy. This opens new research directions in particular in the oil and gas sector.

This paper presents a method to predict permeability of an offset well using well logs and core data from a multi-layer sandstone reservoir with various depositional environments. Many studies have been conducted to predict permeability but limited to wells drilled in a formation with a single depositional environment. This study implements fuzzy models to predict the FZI (flow zone indicator) and permeability, and applied HU (hydraulic unit) grouping to classify the rock properties of various depositional environments in terms of the correlation between permeability and porosity. Then, an individual fuzzy model is developed for each HU group. A field application confirms that the method can be applied to permeability prediction using well data from various depositional environments. A comparative study shows that HU grouping plays a key role in grouping cores of similar flow characteristics in the case of core data from multiple layers with various depositional environments.

It is vital to optimize the drilling trajectory to reduce the possibility of drilling accidents and boosting the efficiency. Previously, the wellbore trajectory was optimized using the true measured depth and well profile energy as objective functions without considering uncertainty between the actual and planned trajectories. Without an effective management of the uncertainty associated with trajectory planning, the drilling process becomes more complex. Prior techniques have some drawbacks; for example, they could not find isolated minima and have a slow convergence rate when dealing with high-dimensional problems. Consequently, a novel approach termed the “Modified Multi-Objective Cellular Spotted Hyena Optimizer” is proposed to address the aforesaid concerns. Following that, a mechanism for eliminating outliers has been developed and implemented in the sorting process to minimize uncertainty. The proposed algorithm outperformed the standard methods like cellular spotted hyena op...

Determining BPP is one of the critical parameters for the development of oil and gas reservoirs and have this parameter requires a lot of time and money. As a result, this study aims to develop a new predictive model for BPP that uses some available input variables such as solution oil ratio (Rs), gas specific gravity (γg), API Gravity (API). In this study, two innovatively combined hybrid algorithms, DWKNN-GSA and DWKNN-ICA, are developed to predict BPP. The outcomes of the study show the models developed are capable of predicting BPP with promising performance, where the best result was achieved for DWKNN-ICA (RMSE = 0.90276 psi and R2 = 1.000 for the test dataset). Moreover, the performance comparison of the developed hybrid models with some previously developed models revealed that the DWKNN-ICA outperforms the former empirical models with respect to perdition accuracy. In addition to presenting new techniques in the present study, the effect of each of the input parameters on B...

Value of information is a widely accepted methodology for evaluating the need to acquire new data in the oil and gas industry. In the conventional approach to estimating the value of information, the outcomes of a project assessment relate to the decision reached by following Boolean logic. However, human thinking is based on a more complex logic that includes the ability to process uncertainty. In value of information assessment, it is often desirable to make decisions based on multiple economic criteria which, if independently evaluated, may suggest opposite decisions. Artificial intelligence has been used successfully in several areas of knowledge, increasing and enhancing analytical capabilities. This paper aims at enriching the value of information methodology by integrating fuzzy logic into the decision-making process; this integration makes it possible to develop a human thinking assessment and coherently combine several economic criteria. To the authors' knowledge, this is the first use of a fuzzy inference system in the specified knowledge domain. The methodology is successfully applied to a case study of an oil and gas subsurface assessment where the results of the standard and fuzzy methodologies are compared, leading to a more robust and complete evaluation. Sensitivity analysis is undertaken for several membership functions used in the case study to assess the impact that shifting, narrowing and stretching the membership relationship has on the value of information. The results of the sensitivity study show that, depending on the shifting, the membership functions lead to different decisions; additional sensitivities to the type of membership functions are investigated, including the functions' parameters.

Like many other countries, Nigeria relies on biomass (mainly wood, charcoal or kerosine) for most of its cooking needs. Prediction of machine performance is an essential step for price prediction of Liquified Petrolium Gas (5 kg refill cooking gas). In this study, Adaptive Neuro Fuzzy Inference System (ANFIS) was employed, which is among the most efficient prediction modelling technique exploits to learn the decision surface that accurately maps an input feature space to an output space of class labels. Two different algorithms, Fuzzy C-Means (FCM) and Subtractive Clustering were used to model the prediction performance. The data used in this study is a time series data obtained from the National bureau of statistics for a period of 38 months (January, 2016 to February, 2019). In order to evaluate the performance of the proposed method, the Root Mean Square Error (RMSE) was utilized. The conducted simulation results show that, the proposed ANFIS based FCM algorithm outperforms the results produced by ANFIS based subtractive clustering algorithm. The analysis for this study was simulated using MATLAB software, version 8.3 and executed in PC Intel Pentium IV E7400 processor with 2.80 GHz speed and 2.0 GB of RAM.

This paper presents a comparative study of the performance of three versions of Adaptive Neuro-Fuzzy Inference System (ANFIS) hybrid model and two innovative hybrid models in the prediction of oil and gas reservoir properties. ANFIS is a hybrid learning algorithm that combines the rule-based inferencing of fuzzy logic and the back-propagation learning procedure of Artificial Neural Networks. Functional Networks-Support Vector Machines (FN-SVM) and Functional Networks-Type-2 Fuzzy Logic (FN-T2FL) were proposed to improve the performance of the stand-alone SVM and T2FL models respectively. The FN component of the FN-T2FL hybrid model automatically extracts the most relevant attributes from the input data using the least square fitting algorithm as an improvement over the individual Functional Networks and Type-2 Fuzzy Logic models. The former is more promising as it combines two existing techniques that are very close in performance and well known for their computational stability and fast processing. The FN-SVM hybrid model also benefits from the excellent performance of the least-square-based model-selection algorithm of Functional Networks and the non-linear high-dimensional feature transformation capability that is based on structural risk minimization and Tikhonov regularization properties of SVM. Training and testing the SVM component of the hybrid model with the best and dimensionally-reduced variables from the input data resulted in better performance with higher correlation coefficients, lower root mean square errors and less execution time than the traditional SVM model. A comparison of FN-SVM and FN-T2FL with the three versions of ANFIS showed the superiority of the FN-SVM model over the others. The three ANFIS models still proved to be good in solving real industrial problems due to their speed of execution especially in dense data conditions.

This paper presents a data driven system used for cardiac arrhythmia classification. It applies the Neuro-Fuzzy Inference System (ANFIS) to classify MIT-BIH arrhythmia database electrocardiogram (ECG) recordings into five (5) heartbeat types. In fact, in order to obtain the input feature vector from recordings, a time scale method based on a Discrete Wavelet Transform (DWT) was investigated. Then, the time scale features are selected by applying the Principal Component Analysis (PCA). Therefore, the selected input feature vectors are classified by the Neuro-Fuzzy method. However, the ANFIS configuration needs mainly the choice of an initial Fuzzy Inference System (FIS) and the training algorithm. Indeed, two clustering algorithms which are the fuzzy c-means (FCM) and the subtractive ( SUBCLUST) algorithms, are applied to generate the initial FIS. Besides, for tuning the ANFIS membership function and rule base parameters, Gradient descent and evolutionary training algorithms are also...

Artificial neural networks are becoming increasingly popular in the oil and gas industry. In the past, studies have been done on the use of artificial neural networks in reservoir characterization, field development and formation damage prediction, to name a few. The aim of this study is to provide guidelines to successfully train and develop an artificial neural network (ANN) that will predict reservoir properties that can give an improved history match when input into the reservoir simulation model. An ANN was developed to improve the history match with a 'small' number of simulation runs for a reservoir that produced oil, gas and water for ten years. Due to a lack of specific protocols for this type of study, the trial and error process was utilized to establish guidelines and suggestions. The neural network was developed by using an inverse solution method to formulate the training and testing data. Normalization of the data simplified the neural network, improved its effectiveness and enhanced its performance. The feed-forward network with back-propagation and the hyperbolic tangent sigmoid function (tansig) in the hidden layers of the network proved to be most effective in the training/learning process. Results indicated that functional links and eigenvalues of various matrices were effective in the training/learning process. The functional links and eigenvalues provided the network with the necessary connections that linked the inputs to the required outputs. v TABLE OF CONTENTS LIST OF FIGURES .

Value of information is a widely accepted methodology for evaluating the need to acquire new data in the oil and gas industry. In the conventional approach to estimating the value of information, the outcomes of a project assessment relate to the decision reached by following Boolean logic. However, human thinking is based on a more complex logic that includes the ability to process uncertainty. In value of information assessment, it is often desirable to make decisions based on multiple economic criteria which, if independently evaluated, may suggest opposite decisions. Artificial intelligence has been used successfully in several areas of knowledge, increasing and enhancing analytical capabilities. This paper aims at enriching the value of information methodology by integrating fuzzy logic into the decision-making process; this integration makes it possible to develop a human thinking assessment and coherently combine several economic criteria. To the authors' knowledge, this is the first use of a fuzzy inference system in the specified knowledge domain. The methodology is successfully applied to a case study of an oil and gas subsurface assessment where the results of the standard and fuzzy methodologies are compared, leading to a more robust and complete evaluation. Sensitivity analysis is undertaken for several membership functions used in the case study to assess the impact that shifting, narrowing and stretching the membership relationship has on the value of information. The results of the sensitivity study show that, depending on the shifting, the membership functions lead to different decisions; additional sensitivities to the type of membership functions are investigated, including the functions' parameters.

This paper presents a data driven system used for cardiac arrhythmia classification. It applies the Neuro-Fuzzy Inference System (ANFIS) to classify MIT-BIH arrhythmia database electrocardiogram (ECG) recordings into five (5) heartbeat types. In fact, in order to obtain the input feature vector from recordings, a time scale method based on a Discrete Wavelet Transform (DWT) was investigated. Then, the time scale features are selected by applying the Principal Component Analysis (PCA). Therefore, the selected input feature vectors are classified by the Neuro-Fuzzy method. However, the ANFIS configuration needs mainly the choice of an initial Fuzzy Inference System (FIS) and the training algorithm. Indeed, two clustering algorithms which are the fuzzy c-means (FCM) and the subtractive ( SUBCLUST) algorithms, are applied to generate the initial FIS. Besides, for tuning the ANFIS membership function and rule base parameters, Gradient descent and evolutionary training algorithms are also...