... Abstract This paper discusses a methodology to enhance machine learning (ML) models developed to predict lithology from real-time mud logging data. Inaccuracies of geological data obtained in the field can lead to inconsistencies in model predictions. To address this, drilling cuttings...

...-based and evolutionary techniques, combined with varied initial guesses to derive alternative regressed EoS models. Our results reveal that while the alternative regressed EoS models demonstrate similar levels of fit to the experimental data, their predictions for phase equilibria are markedly different...

... is a critical issue, causing pressure drops in subsea lines and adding complexity to petroleum processing, resulting in a loss of productivity and quality of the produced oil. The factors mentioned can determine the technical and economic viability of offshore oil production, so predicting this property...

... development solubility rock type co 2 reservoir characterization sedimentary rock clastic rock united states government subsurface storage north america government chemical flooding methods brine prediction sun 2003 sciencedirect mechanism salinity university saline aquifer journal...

... maritime contrator association configuration proximity prediction subsea system fpso gangway ocean engineering fernande upgrading aged fpso operability wave study oceaneng Introduction In recent years, there has been a significant increase in the demand for updating and maintenance...

... Artificial Neural Network in order to predict the emulsion dynamic viscosity of thirty (30) oils from Brazilian basins. The Artificial Neural Network used as inputs rheological data considering different values of temperature, shear rate, oil °API and water fraction in order to predict the dynamic viscosity...

.... The models were developed in a Jupyter environment using Python libraries. The best classifier has a simple accuracy of 61.4% and approximate accuracy (where the prediction is up to one class away from target) of 91.3%. upstream oil & gas artificial intelligence cement and bond evaluation...

... sometimes it is not as easily perceived as operational losses, one can easily see that such wrong predictions invariably lead to incorrect resource allocation leading to financial misuse of the company's funds. Such concern is notably true for the Brazilian petroleum industry, especially within...

... predictions to the historical data. The predictive model accuracy is evaluated during the process of backtesting. Backtesting Most reservoir engineers are not familiar with the term backtesting. It is, however, widely used by those involved in Quantitative Finance, as detailed in Chan (2009...

... Drilling Reports (DDRs). Technologies capable of assisting the fulfillment of such reports represent valuable contributions. An approach using Machine Learning and Sequence Mining algorithms is proposed for predicting the next operation and classifying it based on textual descriptions. Nowadays, artificial...

... Vibration (VIV) model is here proposed and applied to modelling of drilling riser and wellhead fatigue. The model challenges the industry best practices for VIV predictions which are known to be conservative. The paper is divided in two main parts. The first part is devoted to a validation process...

... smart well production dataset prediction reservoir proxy machine learning architecture upstream oil & gas offshore technology conference case study optimization information deep learning technology conference simulation society of petroleum engineers simulator artificial...

... proportional to their contaminant content. Additionally, a predictive kinetic model previously designed for clay cuttings was tested for reservoir cuttings, showing that the model is also aplicable in the analysis of the drying behavior of reservoir cuttings for low values of applied power. It was concluded...

... Abstract Artificial Neural Networks (ANN) applications have grown exponentially in all areas of science and technology. The advantages are its versatility, speed and ability to aggregate information, perform predictions of a given set of data. These attributes attract the petroleum industry...

... of industry considerably mature, as the oil & gas, shall handle these tools to modernize its processes and enhance their efficiency. The applicable fields are diverse, from the operational realm to management areas. It is remarkable to consider the benefits that the adoption of richer prediction models...

... Libra carbonate reservoirs, besides its great heterogeneity, are also characterized by occurrence of igneous rocks, as a challenge to reservoir modeling and production performance prediction. The objectives of this paper are three fields:1) To better understand the genetic cause of magma...

... Abstract The primary goal of floating systems life extension efforts is to project how the system or components will behave in the future beyond the original design life. This predicted behavior can then be used to determine the practicality of the proposed life extension in terms of safety...

... given the estimated currents show good agreement with the actual streamer positions. Computational time of the algorithm is much less than real time. Hence current predictions can be made available to the streamer control system with little delay. Further, streamer prediction can be performed using...

... equation friction coefficient vehicle drag force friction force experimental test cable upstream oil & gas experimental analysis polymeric coating prediction flow assurance artificial intelligence straight segment duct equation umbilical cable References References Y. Bau...

... on subsequent predictions. To overcome the restrictions of unbiased prediction in conventional approaches, Bayesian Kriging has been recently suggested to take into account the uncertainty about Variogram parameters on subsequent predictions. Bayesian Kriging incorporates a prior knowledge about observations...