Search

Significant amounts of information are rapidly increasing in bulk as a consequence of the rapid development of unconventional tight reservoirs. The geomechanical and petrophysical characteristics of the wellbore rocks influence the sweet and non-sweet areas of tight unconventional reservoirs. Using standard approaches, such as data from cores and commercial software, it is difficult and costly to locate productive zones. Furthermore, it is difficult to apply these techniques to wells that do not have cores. This study presents a less costly way for the systematic and objective detection of productive and non-productive zones via well-log data using clustering unsupervised and supervised machine learning algorithms. The method of cluster analysis has been used in order to classify the productive and non-productive reservoir rock groups in the tight reservoir. This was accomplished by assessing the variability of the reservoir characteristics data that are forecasted by looking at the dimensions of the well logs. The Support vector machine as a supervised machine learning algorithm is then used to evaluate the classification accuracy of the unsupervised algorithms based on the clustering labels. The application made use of approximately ten different variables of rock characteristics including zonal depth, effective porosity, permeability, shale volume, water saturation, total organic carbon, young's modulus, Poisson's ratio, brittleness index, and pore size. The findings show that both clustering techniques identified the sweet areas with high accuracy and were less time-consuming.

Unconventional reservoirs are the productive zones in other words the rock quality and the mechanical properties of the rocks this process is devastating if humans or people try to search for the best reservoirs. So we can use machine learning (ML) algorithms to help us find and search easily and fast for the best reservoirs with less human interaction as possible. The objectives of this paper is to use machine learning (ML) techniques to predict and classify the reservoirs based on the properties of each reservoirs and choose the best reservoir. In this paper we have made a comparison between the different types of machine learning algorithm and described how we get the best and worst result for each one, the comparison we made gave us that the AdaBoost algorithm gave the worst performance measured in the accuracy while the random forest (RF) algorithm gave the best performance, this paper aim to make improvement of the process of searching for productive zones using ML algorithms.

This paper evaluates the effect of receiving water conditions on offset buoyant jet behavior. Several experiments on the discharge of thermal and nonthermal horizontal buoyant offset jets into stagnant ambient water are conducted. Particle Image Velocimetry (PIV) is used to measure the time history of the jet velocity distribution. Various characteristics of the jet flow, such as the centerline jet trajectory, jet growth rate and jet velocity decay, are discussed. All comparative experiments are conducted with the same densimetric Froude numbers (Frd, ranging from 9.9 to 29.8) and density differences ∆ρ, ranging from 5.1 to 17.41). The results show that the trajectories of thermal jets are not the same as those of nonthermal jets, which suggests that thermal jets travel farther than nonthermal jets. The experimental results were then compared to predictions of three Reynolds-averaged Navier-Stokes (RANS) turbulence models: the standard k-ε, realizable k-ε, and buoyancy-modified k-ε. The best prediction of the centerline jet trajectory was found to be obtained from realizable k-ε. The study results revealed that the source of buoyancy (salinity versus temperature for the same values of Frdand same ∆ρ) affects the trajectory and mixing properties of the jet.