... composition expansion method at low temperatures (228.15 – 273.15 K). For all the data points, the measurements' uncertainties were 0.14 K and 0.03 MPa, and a maximum composition uncertainty of 0.03%. The experimental data were used to validate the predictive accuracies of two thermodynamic models - Multi...

... Abstract In this dynamic and ever-evolving world, the need for sustainable transportation solutions has become increasingly important. This research employs a data-driven approach aimed at the accurate prediction of two pivotal factors in vehicle sustainability: CO 2 emissions and fuel economy...

... aims to evaluate the application of ensemble boosting supervised machine learning methods to predict lost circulation using drilling parameters. The machine learning techniques namely Adaboost (Adaptive Boosting), LightGBM (Light Gradient Boosting) and XGBoost (Extreme Gradient Boosting...

... conditions, including downhole pressure, wellhead pressure, choke size, and on-stream hours. This holistic approach enhances the accuracy and reliability of predictions compared to conventional univariate forecasting methods that focus solely on a single input variable. Moreover, alongside LSTM, a web...

...INTRODUCTION Abstract This study demonstrates a reliable approach, integrating comprehensive statistical analysis, correlation evaluation, and the use of Machine Learning (ML) models to predict drilling fluids’ Equivalent Circulation Density (ECD). By utilizing a dataset from drilling...

... to accurately predict the asphaltene stability honoring 129 (79 stable and 50 unstable) crude oil density and SARA fractions data points extracted from the literature. Specifically, the predictive prowess of three stability parameters (colloidal stability index (CSI), colloidal instability index (CII...

... revenue loss. Although, ESP sensors, data collection and communication systems have improved in recent years, the industry still lacks a system that can monitor ESP health condition with the capability to accurately predict impending ESP failures. This paper presents a methodology using advanced machine...

... or no interpretability, thereby offering no clues to the underlying physical interactions behind their predictions. To address this issue, an empirical correlation was developed to predict gas lifted oil production rates using interpretable non-linear regression ML models. Production data from four wells were obtained...

..., thereby returning missing sonic log values for some important depth intervals Joshi et al., 2023 . Hence, in this study, an ensemble machine-learning approach was adopted for the real-time prediction of Sonic compressional (ΔTc) and Shear (ΔTs) logs. The ensemble method involved specifically, the Random...

...-effectiveness and accuracy in precision. Several intelligent systems have been utilized to develop models that effectively predict PVT properties. An example of such a system is the ensemble intelligent system. This method functions by using multiple learning algorithms to ensure better performance over...

... deterministic prediction will not allow for the modelling of these uncertainties is essential. To overcome this problem, Stochastic fault and trap analysis can be used to model the parameter uncertainties and thus derive the probability of trapping hydrocarbons and the distributions of hydrocarbon column...

... in, rate of penetration (ROP), surface torque, pump pressure and rotary speed as input parameters, RFC performed better with the resampling techniques than BBC did. Moreover, RFC combined with RU greatly outperformed other combination techniques in the prediction of the geothermal lithology with an F1...

... Recurrent Neural Networks (RNNs) are a class of machine learning algorithms well-suited for time series prediction. They possess internal memory mechanisms that allow them to capture these dependencies. Two prominent RNN architectures for time series forecasting are LSTMs and GRUs. Gated...

... digital twin models poses challenges. This is where AI techniques like optimization (model creation and updating), generative modelling, data analytics, predictive analytics, and decision-making come to play. For instance, according to Abn resource, Shell Lubricants introduced the AI-powered Chatbot tool...

... for estimating hydrocarbon reserves. To accurately estimate the hydrocarbons that can be economically recovered from a field, area, or region, the predicted quantities should closely match the actual observed quantities within the same period. In this study, two models were compared based on their Root Mean...

... ML offers a robust alternative to traditional methods for optimizing reservoir characterization. These models take some initial training data (variables) as input, classify, and predict the behavior of some response variables. ML is necessary for predicting reservoir properties based on seismic...

... Recent advancements in computing technology and data analytics have enabled the development of more advanced and accurate prediction models for crude oil production forecasting. Artificial intelligence (AI) and machine learning (ML) techniques have gained attention in this field, as they can...

... at the wellhead is influenced by changes in reservoir pressure in a multiphase flow. We know the flow rate, pressure, and choke from the wellhead data. These data allow us to forecast downhole conditions. So, we can anticipate PI by anticipating drawdown at the top and conveying it to the bottom. Predicting...

... province penetration reservoir modeling connectivity reservoir engineer nigeria well logging data quality reservoir characterization geological subdiscipline initialization seismic inversion availability prediction obm algorithm Introduction Reservoir models are established tools...

... drawbacks of these methods are the data and samples availability, high costs and time This paper presents an alternative technique of utilizing real-time drilling parameters and machine learning (ML) algorithm in the prediction of UCS thereby enabling timely drilling decisions. ML algorithm enables a system...