Field forecasting and predictive production analysis has tremendous effects on assets planning and allocation and it cannot be over emphasized. For accurate actions to be taken, appropriate forecasts need to be made on each asset, hence the need to develop methods to aid the process. As a tilt from the conventional methodology of forecasting involving use of curve fitting techniques, and multi-level computational analysis, data driven approaches can be employed. This study presents the applications of data driven approaches to forecast production. Deep learning neural network algorithm and statistics- based data driven approach were considered. An LSTM model was developed and for the statistical algorithms, an ARIMA model, and a Holt Winters model was developed. The models were deployed, and the performance of the models were checked to determine more accurate approach for forecasting. Error analysis on the results form the models showed that the deep learning neural network model provided better results in comparison to the statistical models with an MAE of 0.0328. Based on the model performances, LSTM model can be considered for use in forecasting petroleum production overcoming effects of seasonal changes, and production anomalies in the life of the reservoir.

No abstract

Gas hydrate inhibitors, especially those used in offshore environments, are chemicals. These chemicals are synthetic in nature and pose both technical and environmental risks. This study emphasizes the influence of a Plant Extract (PE) on the phase behavior and equilibrium of structure I (SI) gas hydrate and its inhibition efficiency. The PE was screened using a mini flow loop. From the pressure-temperature phase diagram, the various weight percentages of the PE were able to disrupt the thermodynamic equilibrium conditions of the water and gas molecules to lower temperatures and increase pressures, which caused a shift in the equilibrium curve to an unstable hydrate formation zone. The pressure versus time plot as well as the inhibition efficiency plots for the PE and Mono Ethylene Glycol (MEG) were evaluated. Overall, the inhibition efficiency of the PE was higher than that of MEG for 1 wt% (60.53%) and 2 wt% (55.26%) but had the same efficiency at 3 wt% (73.68%). The PE at 1 wt% had the greatest inhibition effect and adjudged the optimum weight percent with a well-regulated phase equilibrium curve. This shows that PE is a better gas hydrate inhibitor than MEG, which is toxic to both human and aquatic life; therefore, it is recommended for field trials.

Hydrate formation in pipelines has been a serious flow assurance issue in the oil and gas industry hence several methods have been developed to predict the conditions which favor its formation in order to develop a proper mitigation plan to control its formation. This study evaluated the inhibition effect of hydrogen gas on a methane / methane gas mixture using UNISIM software and Towler & Mokhatab correlation. After which the effectiveness of this prediction method was determined by comparing their predictions with experimentally obtained data. The predictions of hydrate formation temperature of the methane / methane gas mixtures by Unisim and correlation all showed a decrease in their hydrate formation temperatures when mixed with hydrogen gas. An error evaluation on the two prediction methods showed that the UNISIM prediction has a better prediction than the correlation for all the methane / methane gas mixture because it predicted hydrate formation temperature closer to the experimental predictions.