Unleashing the Potential of Relative Permeability Using Artificial Intelligence

2021 ◽  
Author(s):  
Abdur Rahman Shah ◽  
Kassem Ghorayeb ◽  
Hussein Mustapha ◽  
Samat Ramatullayev ◽  
Nour El Droubi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Dynamic Model ◽  
Relative Permeability ◽  
Full Potential ◽  
Fully Integrated ◽  
Digital Twin ◽  
Rock Types ◽  
Rock Typing ◽  
Artificial Intelligence Models ◽  
Permeability Data

Abstract One of the most important aspects of any dynamic model is relative permeability. To unlock the potential of large relative permeability data bases, the proposed workflow integrates data analysis, machine learning, and artificial intelligence (AI). The workflow allows for the automated generation of a clean database and a digital twin of relative permeability data. The workflow employs artificial intelligence to identify analogue data from nearby fields by extending the rock typing scheme across multiple fields for the same formation. We created a fully integrated and intelligent tool for extracting SCAL data from laboratory reports, then processing and modeling the data using AI and automation. After the endpoints and Corey coefficients have been extracted, the quality of the relative permeability samples is checked using an automated history match and simulation of core flood experiments. An AI model that has been trained is used to identify analogues for various rock types from other fields that produce from the same formations. Finally, based on the output of the AI model, the relative permeabilities are calculated using data from the same and analog fields. The workflow solution offers a solid and well-integrated methodology for creating a clean database for relative permeability. The workflow made it possible to create a digital twin of the relative permeability data using the Corey and LET methods in a systematic manner. The simulation runs were designed so that the pressure measurements are history matched with the adjustment and refinement of the relative permeability curve. The AI workflow enabled us to realize the full potential of the massive database of relative permeability samples from various fields. To ensure utilization in the dynamic model, high, mid, and low cases were created in a robust manner. The workflow solution employs artificial intelligence models to identify rock typing analogues from the same formation across multiple fields. The AI-generated analogues, combined with a robust workflow for quickly QC’ing the relative permeability data, allow for the creation of a fully integrated relative permeability database. The proposed solution is agile and scalable, and it can adapt to any data and be applied to any field.

A Machine Learning Methodology for Rock-Typing Using Relative Permeability Curves

2021 ◽  
Author(s):  
Carlos Esteban Alfonso ◽  
Frédérique Fournier ◽  
Victor Alcobia
Keyword(s):  
Machine Learning ◽  
Capillary Pressure ◽  
Relative Permeability ◽  
Fractional Flow ◽  
Flow Curves ◽  
Rock Types ◽  
Rock Typing ◽  
Relative Permeability Curves ◽  
Permeability Data

Abstract The determination of the petrophysical rock-types often lacks the inclusion of measured multiphase flow properties as the relative permeability curves. This is either the consequence of a limited number of SCAL relative permeability experiments, or due to the difficulty of linking the relative permeability characteristics to standard rock-types stemming from porosity, permeability and capillary pressure. However, as soon as the number of relative permeability curves is significant, they can be processed under the machine learning methodology stated by this paper. The process leads to an automatic definition of relative permeability based rock-types, from a precise and objective characterization of the curve shapes, which would not be achieved with a manual process. It improves the characterization of petrophysical rock-types, prior to their use in static and dynamic modeling. The machine learning approach analyzes the shapes of curves for their automatic classification. It develops a pattern recognition process combining the use of principal component analysis with a non-supervised clustering scheme. Before this, the set of relative permeability curves are pre-processed (normalization with the integration of irreducible water and residual oil saturations for the SCAL relative permeability samples from an imbibition experiment) and integrated under fractional flow curves. Fractional flow curves proved to be an effective way to unify the relative permeability of the two fluid phases, in a unique curve that characterizes the specific poral efficiency displacement of this rock sample. The methodology has been tested in a real data set from a carbonate reservoir having a significant number of relative permeability curves available for the study, in addition to capillary pressure, porosity and permeability data. The results evidenced the successful grouping of the relative permeability samples, according to their fractional flow curves, which allowed the classification of the rocks from poor to best displacement efficiency. This demonstrates the feasibility of the machine learning process for defining automatically rock-types from relative permeability data. The fractional flow rock-types were compared to rock-types obtained from capillary pressure analysis. The results indicated a lack of correspondence between the two series of rock-types, which testifies the additional information brought by the relative permeability data in a rock-typing study. Our results also expose the importance of having good quality SCAL experiments, with an accurate characterization of the saturation end-points, which are used for the normalization of the curves, and a consistent sampling for both capillary pressure and relative permeability measurements.

Rock Typing as an Effective Tool for Permeability and Water-Saturation Modeling: A Case Study in a Clastic Reservoir in the Oriente Basin

2007 ◽  
Vol 10 (06) ◽  
pp. 730-739 ◽  
Author(s):  
Genliang Guo ◽  
Marlon A. Diaz ◽  
Francisco Jose Paz ◽  
Joe Smalley ◽  
Eric A. Waninger
Keyword(s):  
Relative Permeability ◽  
Reservoir Simulation ◽  
Water Saturation ◽  
Rock Type ◽  
Permeability Model ◽  
Initial Water ◽  
Rock Types ◽  
Rock Typing ◽  
Relative Permeability Curves ◽  
Clastic Reservoirs

Summary In clastic reservoirs in the Oriente basin, South America, the rock-quality index (RQI) and flow-zone indicator (FZI) have proved to be effective techniques for rock-type classifications. It has long been recognized that excellent permeability/porosity relationships can be obtained once the conventional core data are grouped according to their rock types. Furthermore, it was also observed from this study that the capillary pressure curves, as well as the relative permeability curves, show close relationships with the defined rock types in the basin. These results lead us to believe that if the rock type is defined properly, then a realistic permeability model, a unique set of relative permeability curves, and a consistent J function can be developed for a given rock type. The primary purpose of this paper is to demonstrate the procedure for implementing this technique in our reservoir modeling. First, conventional core data were used to define the rock types for the cored intervals. The wireline log measurements at the cored depths were extracted, normalized, and subsequently analyzed together with the calculated rock types. A mathematical model was then built to predict the rock type in uncored intervals and in uncored wells. This allows the generation of a synthetic rock-type log for all wells with modern log suites. Geostatistical techniques can then be used to populate the rock type throughout a reservoir. After rock type and porosity are populated properly, the permeability can be estimated by use of the unique permeability/porosity relationship for a given rock type. The initial water saturation for a reservoir can be estimated subsequently by use of the corresponding rock-type, porosity, and permeability models as well as the rock-type-based J functions. We observed that a global permeability multiplier became unnecessary in our reservoir-simulation models when the permeability model is constructed with this technique. Consistent initial-water-saturation models (i.e., calculated and log-measured water saturations are in excellent agreement) can be obtained when the proper J function is used for a given rock type. As a result, the uncertainty associated with volumetric calculations is greatly reduced as a more accurate initial-water-saturation model is used. The true dynamic characteristics (i.e., the flow capacity) of the reservoir are captured in the reservoir-simulation model when a more reliable permeability model is used. Introduction Rock typing is a process of classifying reservoir rocks into distinct units, each of which was deposited under similar geological conditions and has undergone similar diagenetic alterations (Gunter et al. 1997). When properly classified, a given rock type is imprinted by a unique permeability/porosity relationship, capillary pressure profile (or J function), and set of relative permeability curves (Gunter et al. 1997; Hartmann and Farina 2004; Amaefule et al. 1993). As a result, when properly applied, rock typing can lead to the accurate estimation of formation permeability in uncored intervals and in uncored wells; reliable generation of initial-water-saturation profile; and subsequently, the consistent and realistic simulation of reservoir dynamic behavior and production performance. Of the various quantitative rock-typing techniques (Gunter et al. 1997; Hartmann and Farina 2004; Amaefule et al. 1993; Porras and Campos 2001; Jennings and Lucia 2001; Rincones et al. 2000; Soto et al. 2001) presented in the literature, two techniques (RQI/FZI and Winland's R35) appear to be used more widely than the others for clastic reservoirs (Gunter et al. 1997, Amaefule et al. 1993). In the RQI/FZI approach (Amaefule et al. 1993), rock types are classified with the following three equations: [equations]

scholarly journals Artificial intelligence predicts the immunogenic landscape of SARS-CoV-2 leading to universal blueprints for vaccine designs

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Brandon Malone ◽  
Boris Simovski ◽  
Clément Moliné ◽  
Jun Cheng ◽  
Marius Gheorghe ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Monte Carlo ◽  
Cell Surface ◽  
Antigen Presentation ◽  
Human Population ◽  
Host Immune System ◽  
T Cell Epitopes ◽  
Digital Twin ◽  
Novel Coronavirus ◽  
Global Population

AbstractThe global population is at present suffering from a pandemic of Coronavirus disease 2019 (COVID-19), caused by the novel coronavirus Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). The goal of this study was to use artificial intelligence (AI) to predict blueprints for designing universal vaccines against SARS-CoV-2, that contain a sufficiently broad repertoire of T-cell epitopes capable of providing coverage and protection across the global population. To help achieve these aims, we profiled the entire SARS-CoV-2 proteome across the most frequent 100 HLA-A, HLA-B and HLA-DR alleles in the human population, using host-infected cell surface antigen presentation and immunogenicity predictors from the NEC Immune Profiler suite of tools, and generated comprehensive epitope maps. We then used these epitope maps as input for a Monte Carlo simulation designed to identify statistically significant “epitope hotspot” regions in the virus that are most likely to be immunogenic across a broad spectrum of HLA types. We then removed epitope hotspots that shared significant homology with proteins in the human proteome to reduce the chance of inducing off-target autoimmune responses. We also analyzed the antigen presentation and immunogenic landscape of all the nonsynonymous mutations across 3,400 different sequences of the virus, to identify a trend whereby SARS-COV-2 mutations are predicted to have reduced potential to be presented by host-infected cells, and consequently detected by the host immune system. A sequence conservation analysis then removed epitope hotspots that occurred in less-conserved regions of the viral proteome. Finally, we used a database of the HLA haplotypes of approximately 22,000 individuals to develop a “digital twin” type simulation to model how effective different combinations of hotspots would work in a diverse human population; the approach identified an optimal constellation of epitope hotspots that could provide maximum coverage in the global population. By combining the antigen presentation to the infected-host cell surface and immunogenicity predictions of the NEC Immune Profiler with a robust Monte Carlo and digital twin simulation, we have profiled the entire SARS-CoV-2 proteome and identified a subset of epitope hotspots that could be harnessed in a vaccine formulation to provide a broad coverage across the global population.

scholarly journals Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Albert T. Young ◽  
Kristen Fernandez ◽  
Jacob Pfau ◽  
Rasika Reddy ◽  
Nhat Anh Cao ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
Stress Testing ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Skin Lesions ◽  
Stress Tests ◽  
Performance Metric ◽  
Intelligence Models ◽  
Artificial Intelligence Models

AbstractArtificial intelligence models match or exceed dermatologists in melanoma image classification. Less is known about their robustness against real-world variations, and clinicians may incorrectly assume that a model with an acceptable area under the receiver operating characteristic curve or related performance metric is ready for clinical use. Here, we systematically assessed the performance of dermatologist-level convolutional neural networks (CNNs) on real-world non-curated images by applying computational “stress tests”. Our goal was to create a proxy environment in which to comprehensively test the generalizability of off-the-shelf CNNs developed without training or evaluation protocols specific to individual clinics. We found inconsistent predictions on images captured repeatedly in the same setting or subjected to simple transformations (e.g., rotation). Such transformations resulted in false positive or negative predictions for 6.5–22% of skin lesions across test datasets. Our findings indicate that models meeting conventionally reported metrics need further validation with computational stress tests to assess clinic readiness.

Sign in / Sign up

Export Citation Format

Share Document