... Abstract The utility of advanced mud gas (AMG) data has been limited to fluid typing and petrophysical correlations. There is the need to extend the utility to real-time reservoir characterization prior to wireline logging and geological core description. Our first attempt to predict reservoir...

... calculation polarization smectite interfacial polarization prediction artificial intelligence dispersion correlation derivative equation geology dispersion curve calibration constant phyllosilicate clay type mineral geologist derivative curve grain size dispersion and derivative curve...

... action from operators that received a quick true alarm of oil leaking. The effectiveness of the proposed method is demonstrated through A proof of concept (POC) based on a realistic dataset that collected history data that our deep learning algorithms achieved the perfect predict the oil leaking before...

... and finally result in motor failure. Therefore, an accurate prediction of motor internal temperature can help not only with expansion of ESP operating envelope, enhancement of motor reliability and run life, but also reduces operating costs and power consumption (carbon reduction). In addition to industry...

... of the field. Therefore, an accurate prediction of sand production volume/rates is essential during the well planning. Having this information upfront will able the operators to select the best sand-management plan for the well and field economically (best productivity and highest ultimate recovery while...

... subsurface storage lstm surrogate machine learning prediction exhibition bayesian optimization geologist artificial intelligence bayesian inversion kwak high-fidelity simulation workflow geology co 2 hoteit alsinan leakage santoso leakage location pressure response computational time...

... for the usage of data from the past time step to predict the current time step. Forecast accuracy for RNNs is limited to a short period due to their inherent vanishing gradient issues. While a majority of VFM applications have been developed for oil and gas systems, little or non is applied to gas condensate...

... to 1600 mPa.s) two-phase upward vertical flow pattern datasets. Their study revealed that all the models predicted annular flow in the entire dataset with error ranging from 80% to 100%, which is the worst performance compared with other flow patterns. Furthermore, examining the performance of each model...

... Abstract The machine learning method, now widely used for predicting well performance from unconventional reservoirs in the industry, generally needs large data sets for model development and training. The large data sets, however, are not always available, especially for newly developed...

... Abstract Predictive models that incorporate physical information or constraints are used for production prediction in subsurface systems. They come in many flavors; some include additional terms in the objective function, some directly embed physical functions and some use neural network layers...

... and variable pressure. Then, the main factors affecting well production are determined by sensitive analysis. Finally, the production prediction model based on a genetic algorithm (GA) is used to optimize the fracture parameters of the Fuling shale gas reservoir. The results show that in the study area...

... parameters were investigated and several iterations with different sets of parameters were attempted to identify those with the most impact on bound fluid volume prediction. Henceforth, the iteration with the lowest root mean square error (RMSE) is to be selected. The model was trained, calibrated...

... the completion designs. Well production trend is predicted against the varying completion designs over the selected asset area and displayed onto the axes of the completion parameters of interest. Optimizing over the selected asset makes a smaller number of data available. Some completion parameters may be fixed...

... on the stimulation treatment. The proposed workflow utilizes supervised machine learning algorithms to train different predictive models to estimate the amount of the produced oil; including but not limited to neural Random Forest, CATboost and XGboost. Additionally, by quantifying each chemicals’ importance on oil...

... recovery climate change prediction numerical simulation saline aquifer permeability hysteresis aquifer geologist saturation simulator geology relative permeability hysteresis geologic formation Introduction Motivation It is now more evident that anytime before that carbon capture...

.... In this work, these hydraulic calculations are coupled with the loss zone behavior. Presence of a loss zone would indicate a potential loss of fluid as a function of fluid properties and wellbore pressures and temperature. This predicted fluid loss is removed from wellbore fluids and its effect is also...

... Abstract Monitoring of Equivalent Circulating Density (ECD) may improve assessment of potential bad hole cleaning conditions if calculated and measured sufficiently accurately. Machine learning (ML) models can be used for predicting ECD integrating both along-string and surface drilling...

..., it is important to evaluate the mud properties while drilling to capture the dynamics of mudflow. Unlike other mud properties, mud density (MD) and Marsh funnel viscosity (MFV) are frequently measured every 15–20 minutes in the field. The objective of this study is to predict the viscometer readings at 300...

... and the validation performance which indicate good generalization without an overfitting problem. Using drilling data to predict rock mechanical parameters allows building a complete geomechanical model at an early time. It also saves the time and cost associated with laboratory tests. decision tree learning...

... and average liquid holdup in slug flow. However, the existing slug length closure relationships developed for low pressure are found to poorly perform in high-pressure conditions, i.e. high gas- to-liquid density ratio high, resulting in high uncertainty predictions of slug length, pressure gradient...