Machine Learning for Multiple Petrophysical Properties Regression Based on Core Images and Well Logs in a Heterogenous Reservoir

2021 ◽  
Author(s):  
Tao Lin ◽  
Mokhles Mezghani ◽  
Chicheng Xu ◽  
Weichang Li
Keyword(s):  
Machine Learning ◽  
Model Building ◽  
Image Features ◽  
Well Logs ◽  
Model Complexity ◽  
Rock Properties ◽  
Core Analysis ◽  
Petrophysical Properties ◽  
Blind Test ◽  
Porosity And Permeability

Abstract Reservoir characterization requires accurate prediction of multiple petrophysical properties such as bulk density (or acoustic impedance), porosity, and permeability. However, it remains a big challenge in heterogeneous reservoirs due to significant diagenetic impacts including dissolution, dolomitization, cementation, and fracturing. Most well logs lack the resolution to obtain rock properties in detail in a heterogenous formation. Therefore, it is pertinent to integrate core images into the prediction workflow. This study presents a new approach to solve the problem of obtaining the high-resolution multiple petrophysical properties, by combining machine learning (ML) algorithms and computer vision (CV) techniques. The methodology can be used to automate the process of core data analysis with a minimum number of plugs, thus reducing human effort and cost and improving accuracy. The workflow consists of conditioning and extracting features from core images, correlating well logs and core analysis with those features to build ML models, and applying the models on new cores for petrophysical properties predictions. The core images are preprocessed and analyzed using color models and texture recognition, to extract image characteristics and core textures. The image features are then aggregated into a profile in depth, resampled and aligned with well logs and core analysis. The ML regression models, including classification and regression trees (CART) and deep neural network (DNN), are trained and validated from the filtered training samples of relevant features and target petrophysical properties. The models are then tested on a blind test dataset to evaluate the prediction performance, to predict target petrophysical properties of grain density, porosity and permeability. The profile of histograms of each target property are computed to analyze the data distribution. The feature vectors are extracted from CV analysis of core images and gamma ray logs. The importance of each feature is generated by CART model to individual target, which may be used to reduce model complexity of future model building. The model performances are evaluated and compared on each target. We achieved reasonably good correlation and accuracy on the models, for example, porosity R2=49.7% and RMSE=2.4 p.u., and logarithmic permeability R2=57.8% and RMSE=0.53. The field case demonstrates that inclusion of core image attributes can improve petrophysical regression in heterogenous reservoirs. It can be extended to a multi-well setting to generate vertical distribution of petrophysical properties which can be integrated into reservoir modeling and characterization. Machine leaning algorithms can help automate the workflow and be flexible to be adjusted to take various inputs for prediction.

scholarly journals An Integrated Microfacies and Well Logs-Based Reservoir Characterization of Yamama Formation, Southern Iraq

2021 ◽  
pp. 3570-3586
Author(s):  
Mohanad M. Al-Ghuribawi ◽  
Rasha F. Faisal
Keyword(s):  
Reservoir Characterization ◽  
Water Saturation ◽  
Effective Porosity ◽  
Well Logs ◽  
Petrophysical Properties ◽  
Reservoir Properties ◽  
Thin Sections ◽  
Porosity And Permeability ◽  
South Of Iraq ◽  
Southern Iraq

     The Yamama Formation includes important carbonates reservoir that belongs to the Lower Cretaceous sequence in Southern Iraq. This study covers two oil fields (Sindbad and Siba) that are distributed Southeastern Basrah Governorate, South of Iraq. Yamama reservoir units were determined based on the study of cores, well logs, and petrographic examination of thin sections that required a detailed integration of geological data and petrophysical properties. These parameters were integrated in order to divide the Yamama Formation into six reservoir units (YA0, YA1, YA2, YB1, YB2 and YC), located between five cap rock units. The best facies association and petrophysical properties were found in the shoal environment, where the most common porosity types were the primary (interparticle) and secondary (moldic and vugs) . The main diagenetic process that occurred in YA0, YA2, and YB1 is cementation, which led to the filling of pore spaces by cement and subsequently decreased the reservoir quality (porosity and permeability). Based on the results of the final digital  computer interpretation and processing (CPI) performed by using the Techlog software, the units YA1 and YB2 have the best reservoir properties. The unit YB2 is characterized by a good effective porosity average, low water saturation, good permeability, and large thickness that distinguish it from other reservoir units.

Journey From Well Logs/Cores to Integrated Geological and Petrophysical Properties Simulation: A Methodology and Application

2000 ◽  
Vol 3 (05) ◽  
pp. 444-456 ◽  
Author(s):  
A. Bahar ◽  
M. Kelkar
Keyword(s):  
Reservoir Characterization ◽  
Conditional Simulation ◽  
Spatial Relationship ◽  
Low Frequency ◽  
Simulation Technique ◽  
Well Logs ◽  
Petrophysical Properties ◽  
Data Types ◽  
Porosity And Permeability ◽  
A New Technique

Summary Reservoir studies performed in the industry are moving towards an integrated approach. Most data available for this purpose are mainly from well cores and/or well logs. The translation of these data into petrophysical properties, i.e., porosity and permeability, at interwell locations that are consistent with the underlying geological description is a critical process. This paper presents a methodology that can be used to achieve this goal. The method has been applied at several field applications where full reservoir characterization study is conducted. The framework developed starts with a geological interpretation, i.e., facies and petrophysical properties, at well locations. A new technique for evaluating horizontal spatial relationships is provided. The technique uses the average properties of the vertical data to infer the low-frequency characteristics of the horizontal data. Additionally, a correction in calculating the indicator variogram, that is used to capture the facies' spatial relationship, is provided. A new co-simulation technique to generate petrophysical properties consistent with the underlying geological description is also developed. The technique uses conditional simulation tools of geostatistical methodology and has been applied successfully using field data (sandstone and carbonate fields). The simulated geological descriptions match well the geologists' interpretation. All of these techniques are combined into a single user-friendly computer program that works on a personal computer platform. Introduction Reservoir characterization is the process of defining reservoir properties, mainly, porosity and permeability, by integration of many data types. An ultimate goal of reservoir characterization is improved prediction of the future performance of the reservoir. But, before we reach that goal a journey through various processes must come to pass. The more exhaustive the processes, the more accurate the prediction will be. The most important processes in this journey are the incorporation and analysis of available geological information.1–3 The most common data types available for this purpose are in the form of well logs and/or well cores. The translation of these data into petrophysical properties, i.e., porosity and permeability, at interwell locations that are consistent with the underlying geological description is a critical step. The work presented in this paper provides a methodology to achieve this goal. This methodology is based on the geostatistical technique of conditional simulation. The step-by-step procedure starts with the work of the geologist where the isochronal planes across the whole reservoir are determined. This step is followed by the assignment of facies and petrophysical properties at well locations for each isochronal interval. Using these results, spatial analysis of the reservoir attributes, i.e., facies, porosity, and permeability, can be conducted in both vertical and horizontal directions. Due to the nature of how the data are typically distributed, i.e., abundant in the vertical direction but sparse in the horizontal direction, this step is far from a simple task, and practitioners have used various approximations to overcome this problem.4–6 A new technique for evaluating the horizontal spatial relationship is proposed in this work. The technique uses the average properties of the vertical data to infer the low-frequency characteristics of the horizontal data. Additionally, a correction in calculating the indicator variogram, that is used to capture the facies spatial relationship, is provided. Once the spatial relationship of the reservoir attributes has been established, the generation of internally consistent facies and petrophysical properties at the gridblock level can be done through a simulation process. Common practice in the industry is to perform conditional simulation of petrophysical properties by adapting a two-stage approach.7–10 In the first stage, the geological description is simulated using a conditional simulation technique such as sequential indicator simulation or Gaussian truncated simulation. In the second stage, petrophysical properties are simulated for each type of geological facies/unit using a conditional simulation technique such as sequential Gaussian simulation or simulated annealing. The simulated petrophysical properties are then filtered using the generated geological simulation to produce the final simulation result. The drawback of this approach is its inefficiency, since it requires several simulations, and hence, intensive computation time. Additionally, the effort to jointly simulate or to co-simulate interdependent attributes such as facies, porosity, and permeability has been discussed by several authors.11–13 The techniques used by these authors have produced useful results. Common disadvantages of these techniques are the requirement of tedious inference and modeling of covariances and cross covariances. Also, a large amount of CPU time is required to solve the numerical problem of a large co-kriging system. Another co-simulation technique that eliminates the requirement of solving the full co-kriging system has been proposed by Almeida.14 The technique is based on a collocated co-kriging and a Markov-type hypothesis. This hypothesis simplifies the inference and modeling of the cross covariances. Since the collocated technique is used, an assumption of a linear relationship among the attributes needs to be applied. The co-simulation technique developed in this work avoids the two-stage approach described above. The technique is based on a combination of simultaneous sequential Gaussian simulations and a conditional distribution technique. Using this technique there is no large co-kriging system to solve and there is no need to assume a relationship among reservoir attributes. The absence of co-kriging from the process also means that the user is free from developing the cross variograms. This improves the practical application of the technique.

scholarly journals Mechanical Rock Properties Estimation for Carbonate Reservoir Using Laboratory Measurement: A Case Study from Jeribe, Khasib and Mishrif Formations in Fauqi Oil Field

2021 ◽  
Vol 54 (1E) ◽  
pp. 88-102
Author(s):  
Qahtan Abdul Aziz ◽  
Hassan Abdul Hussein
Keyword(s):  
Mechanical Properties ◽  
Bulk Density ◽  
Depositional Environments ◽  
Carbonate Reservoir ◽  
Oil Field ◽  
Well Logs ◽  
Rock Properties ◽  
Petrophysical Properties ◽  
Empirical Correlations ◽  
Rock Mechanical Properties

Estimation of mechanical and physical rock properties is an essential issue in applications related to reservoir geomechanics. Carbonate rocks have complex depositional environments and digenetic processes which alter the rock mechanical properties to varying degrees even at a small distance. This study has been conducted on seventeen core plug samples that have been taken from different formations of carbonate reservoirs in the Fauqi oil field (Jeribe, Khasib, and Mishrif formations). While the rock mechanical and petrophysical properties have been measured in the laboratory including the unconfined compressive strength, Young's modulus, bulk density, porosity, compressional and shear -waves, well logs have been used to do a comparison between the lab results and well logs measurements. The results of this study revealed that petrophysical properties are consistent indexes to determine the rock mechanical properties with high performance capacity. Different empirical correlations have been developed in this study to determine the rock mechanical properties using the multiple regression analysis. These correlations are UCS-porosity, UCS-bulk density, UCS-Vs, UCs-Vp Es-Vs, Es-Vp, and Vs-Vp. (*). For example, the UCS-Vs correlation gives a good determination coefficient (R2= 0.77) for limestone and (R2=0.94) for dolomite. A comparison of the developed correlations with literature was also checked. This study presents a set of empirical correlations that can be used to determine and calibrate the rock mechanical properties when core samples are missing or incomplete.

A NEW OPTIMIZATION METHOD FOR ENHANCED FORMATION EVALUATION AND ROBUST PHYSICS-BASED AUTOMATIC ROCK CLASSIFICATION USING HIGH-RESOLUTION CT-SCAN IMAGE DATA AND CONVENTIONAL WELL LOGS

2021 ◽  
Author(s):  
Andres Gonzalez ◽  
◽  
Zoya Heidari ◽  
Olivier Lopez ◽  
◽  
...  
Keyword(s):  
Ct Scan ◽  
Cost Function ◽  
Bulk Density ◽  
Rock Physics ◽  
Well Logs ◽  
Petrophysical Properties ◽  
Rock Classification ◽  
Formation Evaluation ◽  
Rock Fabric ◽  
Porosity And Permeability

Conventional formation evaluation provides fast and accurate estimations of petrophysical properties in conventional formations through conventional well logs and routine core analysis (RCA) data. However, as the complexity of the evaluated formations increases conventional formation evaluation fails to provide accurate estimates of petrophysical properties. This inaccuracy is mainly caused by rapid variation in rock fabric (i.e., spatial distribution of rock components) not properly captured by conventional well logging tools and interpretation methods. Acquisition of high-resolution whole-core computed tomography (CT) scanning images can help to identify rock-fabric-related parameters that can enhance formation evaluation. In a recent publication, we introduced a permeability-based cost function for rock classification, optimization of the number of rock classes, and estimation of permeability. Incorporation of additional petrophysical properties into the proposed cost function can improved the reliability of the detected rock classes and ultimately improve the estimation of class-based petrophysical properties. The objectives of this paper are (a) to introduce a robust optimization method for rock classification and estimation of petrophysical properties, (b), to automatically employ whole-core two-dimensional (2D) CT-scan images and slabbed whole-core photos for enhanced estimates of petrophysical properties, (c) to integrate whole-core CT-scan images and slabbed whole-core photos with well logs and RCA data for automatic rock classification, (d) to derive class-based rock physics models for improved estimates of petrophysical properties. First, we conducted formation evaluation using well logs and RCA data for estimation of petrophysical properties. Then, we derived quantitative features from 2D CT-scan images and slabbed whole-core photos. We employed image-based features, RCA data and CT-scan-based bulk density for optimization of the number rock classes. Optimization of rock classes was accomplished using a physics-based cost function (i.e., a function of petrophysical properties of the rock) that compares class-based estimates of petrophysical properties (e.g., permeability and porosity) with core-measured properties for increasing number of image-based rock classes. The cost function is computed until convergence is achieved. Finally, we used class-based rock physics models for improved estimates of porosity and permeability. We demonstrated the reliability of the proposed method using whole-core CT-scan images and core photos from two siliciclastic depth intervals with measurable variation in rock fabric. We used well logs, RCA data, and CT-scan-based bulk-density. The advantages of using whole-core CT-scan data are two-fold. First, it provides high-resolution quantitative features that capture rapid spatial variation in rock fabric allowing accurate rock classification. Second, the use of CT-scan-based bulk density improved the accuracy of class-based porosity-bulk density models. The optimum number of rock classes was consistent for all the evaluated cost functions. Class-based rock physics models improved the estimates of porosity and permeability values. A unique contribution of the introduced workflow when compared to previously documented image-based rock classification workflows is that it simultaneously improves estimates of both porosity and permeability, and it can capture rock class that might not be identifiable using conventional rock classification techniques.

A Critical Literature Review on Rock Petrophysical Properties Estimation from Images Based on Direct Simulation and Machine Learning Techniques

2021 ◽  
Author(s):  
Ahmed Samir Rizk ◽  
Moussa Tembely ◽  
Waleed AlAmeri ◽  
Emad W. Al-Shalabi
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Literature Review ◽  
Training Data ◽  
Rock Properties ◽  
Gradient Boosting ◽  
Petrophysical Properties ◽  
Direct Simulation ◽  
Data Set ◽  
Extreme Gradient Boosting

Abstract Estimation of petrophysical properties is essential for accurate reservoir predictions. In recent years, extensive work has been dedicated into training different machine-learning (ML) models to predict petrophysical properties of digital rock using dry rock images along with data from single-phase direct simulations, such as lattice Boltzmann method (LBM) and finite volume method (FVM). The objective of this paper is to present a comprehensive literature review on petrophysical properties estimation from dry rock images using different ML workflows and direct simulation methods. The review provides detailed comparison between different ML algorithms that have been used in the literature to estimate porosity, permeability, tortuosity, and effective diffusivity. In this paper, various ML workflows from the literature are screened and compared in terms of the training data set, the testing data set, the extracted features, the algorithms employed as well as their accuracy. A thorough description of the most commonly used algorithms is also provided to better understand the functionality of these algorithms to encode the relationship between the rock images and their respective petrophysical properties. The review of various ML workflows for estimating rock petrophysical properties from dry images shows that models trained using features extracted from the image (physics-informed models) outperformed models trained on the dry images directly. In addition, certain tree-based ML algorithms, such as random forest, gradient boosting, and extreme gradient boosting can produce accurate predictions that are comparable to deep learning algorithms such as deep neural networks (DNNs) and convolutional neural networks (CNNs). To the best of our knowledge, this is the first work dedicated to exploring and comparing between different ML frameworks that have recently been used to accurately and efficiently estimate rock petrophysical properties from images. This work will enable other researchers to have a broad understanding about the topic and help in developing new ML workflows or further modifying exiting ones in order to improve the characterization of rock properties. Also, this comparison represents a guide to understand the performance and applicability of different ML algorithms. Moreover, the review helps the researchers in this area to cope with digital innovations in porous media characterization in this fourth industrial age – oil and gas 4.0.

scholarly journals Feature Selection and Ensemble-Based Intrusion Detection System: An Efficient and Comprehensive Approach

Symmetry ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 1764
Author(s):  
Ebrima Jaw ◽  
Xueming Wang
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Intrusion Detection ◽  
Model Building ◽  
Detection System ◽  
Probability Distributions ◽  
Ensemble Classifier ◽  
Model Complexity ◽  
Testing Time ◽  
Genetic Search

The emergence of ground-breaking technologies such as artificial intelligence, cloud computing, big data powered by the Internet, and its highly valued real-world applications consisting of symmetric and asymmetric data distributions, has significantly changed our lives in many positive aspects. However, it equally comes with the current catastrophic daily escalating cyberattacks. Thus, raising the need for researchers to harness the innovative strengths of machine learning to design and implement intrusion detection systems (IDSs) to help mitigate these unfortunate cyber threats. Nevertheless, trustworthy and effective IDSs is a challenge due to low accuracy engendered by vast, irrelevant, and redundant features; inept detection of all types of novel attacks by individual machine learning classifiers; costly and faulty use of labeled training datasets cum significant false alarm rates (FAR) and the excessive model building and testing time. Therefore, this paper proposed a promising hybrid feature selection (HFS) with an ensemble classifier, which efficiently selects relevant features and provides consistent attack classification. Initially, we harness the various strengths of CfsSubsetEval, genetic search, and a rule-based engine to effectively select subsets of features with high correlation, which considerably reduced the model complexity and enhanced the generalization of learning algorithms, both of which are symmetry learning attributes. Moreover, using a voting method and average of probabilities, we present an ensemble classifier that used K-means, One-Class SVM, DBSCAN, and Expectation-Maximization, abbreviated (KODE) as an enhanced classifier that consistently classifies the asymmetric probability distributions between malicious and normal instances. HFS-KODE achieves remarkable results using 10-fold cross-validation, CIC-IDS2017, NSL-KDD, and UNSW-NB15 datasets and various metrics. For example, it outclassed all the selected individual classification methods, cutting-edge feature selection, and some current IDSs techniques with an excellent performance accuracy of 99.99%, 99.73%, and 99.997%, and a detection rate of 99.75%, 96.64%, and 99.93% for CIC-IDS2017, NSL-KDD, and UNSW-NB15, respectively based on only 11, 8, 13 selected relevant features from the above datasets. Finally, considering the drastically reduced FAR and time, coupled with no need for labeled datasets, it is self-evident that HFS-KODE proves to have a remarkable performance compared to many current approaches.

Machine Learning for Acute Toxicity Prediction Using High-Throughput Enzyme-Reaction Chip

2019 ◽  
Author(s):  
Qiannan Duan ◽  
Jianchao Lee ◽  
Jinhong Gao ◽  
Jiayuan Chen ◽  
Yachao Lian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Toxicity ◽  
Model Building ◽  
Low Cost ◽  
Enzyme Reaction ◽  
Chemical Effect ◽  
Technological Innovations ◽  
Acute Toxicity Test ◽  
Toxicity Prediction ◽  
Traditional Understanding

<p>Machine learning (ML) has brought significant technological innovations in many fields, but it has not been widely embraced by most researchers of natural sciences to date. Traditional understanding and promotion of chemical analysis cannot meet the definition and requirement of big data for running of ML. Over the years, we focused on building a more versatile and low-cost approach to the acquisition of copious amounts of data containing in a chemical reaction. The generated data meet exclusively the thirst of ML when swimming in the vast space of chemical effect. As proof in this study, we carried out a case for acute toxicity test throughout the whole routine, from model building, chip preparation, data collection, and ML training. Such a strategy will probably play an important role in connecting ML with much research in natural science in the future.</p>

Applications of Quantitative Structure-Activity Relationships (QSAR) based Virtual Screening in Drug Design: A Review

2020 ◽  
Vol 20 (14) ◽  
pp. 1375-1388 ◽  
Author(s):  
Patnala Ganga Raju Achary
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Virtual Screening ◽  
Model Building ◽  
Chemical Space ◽  
Qsar Model ◽  
Quantitative Structure ◽  
Efficient Manner ◽  
Qsar Analysis ◽  
Structure Activity

The scientists, and the researchers around the globe generate tremendous amount of information everyday; for instance, so far more than 74 million molecules are registered in Chemical Abstract Services. According to a recent study, at present we have around 1060 molecules, which are classified as new drug-like molecules. The library of such molecules is now considered as ‘dark chemical space’ or ‘dark chemistry.’ Now, in order to explore such hidden molecules scientifically, a good number of live and updated databases (protein, cell, tissues, structure, drugs, etc.) are available today. The synchronization of the three different sciences: ‘genomics’, proteomics and ‘in-silico simulation’ will revolutionize the process of drug discovery. The screening of a sizable number of drugs like molecules is a challenge and it must be treated in an efficient manner. Virtual screening (VS) is an important computational tool in the drug discovery process; however, experimental verification of the drugs also equally important for the drug development process. The quantitative structure-activity relationship (QSAR) analysis is one of the machine learning technique, which is extensively used in VS techniques. QSAR is well-known for its high and fast throughput screening with a satisfactory hit rate. The QSAR model building involves (i) chemo-genomics data collection from a database or literature (ii) Calculation of right descriptors from molecular representation (iii) establishing a relationship (model) between biological activity and the selected descriptors (iv) application of QSAR model to predict the biological property for the molecules. All the hits obtained by the VS technique needs to be experimentally verified. The present mini-review highlights: the web-based machine learning tools, the role of QSAR in VS techniques, successful applications of QSAR based VS leading to the drug discovery and advantages and challenges of QSAR.

Sign in / Sign up

Export Citation Format

Share Document