Hybrid machine learning algorithms to predict condensate viscosity in the near wellbore regions of gas condensate reservoirs

Computational methods in fluid research have been progressing during the past few years, driven by the incorporation of massive amounts of data, either in textual or graphical form, generated from multi-scale simulations, laboratory experiments, and real data from the field. Artificial Intelligence (AI) and its adjacent field, Machine Learning (ML), are about to reach standardization in most fields of computational science and engineering, as they provide multiple ways for extracting information from data that turn into knowledge, with the aid of portable software implementations that are easy to adopt. There is ample information on the historical and mathematical background of all aspects of AI/ML in the literature. Thus, this review article focuses mainly on their impact on fluid research at present, highlighting advances and opportunities, recognizing techniques and methods having been proposed, tabulating, and testing some of the most popular algorithms that have shown significant accuracy and performance on fluid applications. We also investigate algorithmic accuracy on several fluid datasets that correspond to simulation results for the transport properties of fluids and suggest that non-linear, decision tree-based methods have shown remarkable performance on reproducing fluid properties.

/pdf/current-trends-in-fluid-research-in-the-era-of-artificial-3jqcqoaf.pdf

Current Trends in Fluid Research in the Era of Artificial Intelligence: A Review

A robust approach to pore pressure prediction applying petrophysical log data aided by machine learning techniques

Permeability prediction of heterogeneous carbonate gas condensate reservoirs applying group method of data handling

A novel approach to pore pressure modeling based on conventional well logs using convolutional neural network

Predicting oil flow rate through orifice plate with robust machine learning algorithms

Abstract Shear wave velocity ( V S ) data from sedimentary rock sequences is a prerequisite for implementing most mathematical models of petroleum engineering geomechanics. Extracting such data by analyzing finite reservoir rock cores is very costly and limited. The high cost of sonic dipole advanced wellbore logging service and its implementation in a few wells of a field has placed many limitations on geomechanical modeling. On the other hand, shear wave velocity V S tends to be nonlinearly related to many of its influencing variables, making empirical correlations unreliable for its prediction. Hybrid machine learning (HML) algorithms are well suited to improving predictions of such variables. Recent advances in deep learning (DL) algorithms suggest that they too should be useful for predicting V S for large gas and oil field datasets but this has yet to be verified. In this study, 6622 data records from two wells in the giant Iranian Marun oil field (MN#163 and MN#225) are used to train HML and DL algorithms. 2072 independent data records from another well (MN#179) are used to verify the V S prediction performance based on eight well-log-derived influencing variables. Input variables are standard full-set recorded parameters in conventional oil and gas well logging data available in most older wells. DL predicts V S for the supervised validation subset with a root mean squared error (RMSE) of 0.055 km/s and coefficient of determination (R 2 ) of 0.9729. It achieves similar prediction accuracy when applied to an unseen dataset. By comparing the V S prediction performance results, it is apparent that the DL convolutional neural network model slightly outperforms the HML algorithms tested. Both DL and HLM models substantially outperform five commonly used empirical relationships for calculating V S from V p relationships when applied to the Marun Field dataset. Concerns regarding the model's integrity and reproducibility were also addressed by evaluating it on data from another well in the field. The findings of this study can lead to the development of knowledge of production patterns and sustainability of oil reservoirs and the prevention of enormous damage related to geomechanics through a better understanding of wellbore instability and casing collapse problems. Graphical abstract 

/pdf/predicting-shear-wave-velocity-from-conventional-well-logs-pnejm57x.pdf

Predicting shear wave velocity from conventional well logs with deep and hybrid machine learning algorithms

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 BPP was evaluated using Spearman's correlation coefficient, where the API and Rs have the lowest and the highest impact on the BPP.

/pdf/prediction-of-bubble-point-pressure-using-new-hybrid-3lxdct7fss.pdf

Prediction of Bubble Point Pressure Using New Hybrid Computationail Intelligence Models


 Polymers have been used for many years to control the mobility of injected water and increase the rate of oil extraction from unconventional reservoirs. Polymer flossing improves the volume of the broom, reduces the finger effect, creates channels, and delays water breakage. The combination of these processes has the potential to increase oil production and reduce production costs. To carry out this process, various polymers are used alone or in combination with surfactants and alkalis. In this study, a new type of polymer called FLOPPAM 3630 has been used to investigate the overload of very heavy oil reservoirs. For this purpose, six polymer solutions with different concentrations were made, and stability tests on shear rate, time, and temperature were performed. The polymer's stability results indicate that it is stable under other shear rate, temperature, and time passage conditions. As a result, this polymer is a suitable candidate for conducting silicification tests in reservoir temperature conditions. Then three more suitable polymer solutions were selected, and the polymer was polished. The results showed that the solution with a concentration of 1000 ppm has the best yield of about 40%. The reason for the good efficiency of this concentration is that the surface and vertical sweepers are higher than the other concentrations. Also, the difference in efficiency between less than 1000 and 2000 ppm is greater because it is more economical, and its injectability is easier to use with less concentration. Furthermore, the oil efficiency of this type of polymer in sandblasting is higher than that of other polymers tested under these conditions, making its use more economical.


Laboratory study of polymer injection into heavy oil unconventional reservoirs to enhance oil recovery and determination of optimal injection concentration

Pezhman Soltani Tehrani

Papers

Predicting oil flow rate through orifice plate with robust machine learning algorithms

Predicting shear wave velocity from conventional well logs with deep and hybrid machine learning algorithms

Prediction of Bubble Point Pressure Using New Hybrid Computationail Intelligence Models

Laboratory study of polymer injection into heavy oil unconventional reservoirs to enhance oil recovery and determination of optimal injection concentration