Petrophysical rock typing (PRT) and permeability prediction are of great significance for various disciplines of oil and gas industry. This study offers a novel, explainable data-driven approach to enhance the accuracy of petrophysical rock typing via a combination of supervised and unsupervised machine learning methods. 128 core data, including porosity, permeability, connate water saturation (Swc), and radius of pore throats at 35% mercury injection (R35) were obtained from a heterogeneous carbonate reservoir in Iran and used to train a supervised machine learning algorithm called Extreme Gradient Boosting (XGB). The algorithm output was a modified formation zone index (FZIM*), which was used to accurately estimate permeability (R2 = 0.97) and R35 (R2 = 0.95). Moreover, FZIM* was combined with an unsupervised machine learning algorithm (K-means clustering) to find the optimum number of PRTs. 4 petrophysical rock types (PRTs) were identified via this method, and the range of their properties was discussed. Lastly, shapely values and parameter importance analysis were conducted to explain the correlation between each input parameter and the output and the contribution of each parameter on the value of FZIM*. Permeability and R35 were found to be most influential parameters, where Swc had the lowest impact on FZIM*.
Understanding the carbon dioxide (CO2) solubility in formation brines is of great importance to several industrial applications, including CO2 sequestration and some CO2 capture technologies, as well as CO2-based enhanced hydrocarbon recovery methods. Despite years of study, there are few literature data on CO2 solubility for the low salinity range. Thus, in this study, the solubility of CO2 in distilled water and aqueous ionic solutions of NaCl, MgCl2, CaCl2 and MgCl2 + CaCl2 were obtained in a low salinity range (0–15,000 ppm) at temperatures from 298–373 K and pressures up to 20 MPa using an accurate and unconventional method called potentiometric titration. An experimental data set of 553 data points was collected using this method. The results of the experiments demonstrate that increasing pressure increases the solubility of CO2 in various brines, whereas increasing temperature and salinity reduces the solubility. The role of different ions in changing the solubility is elaborated through a detailed discussion on the salting-out effect of different ionic solutions. To verify the experimental results of this research, the solubility points obtained by the potentiometric titration method were compared to some of the well-established experimental and analytical data from the literature and a very good agreement with those was obtained.
6 September 2018 in Industrial & Engineering Chemistry Research