- Home
- Conferences
- Conference Proceedings
- Conferences
Data Science in Oil and Gas 2021
- Conference date: August 4-6, 2021
- Location: Online
- Published: 04 August 2021
31 results
-
-
Usage of Machine Learning Algorithms for Structural Boundaries Reconstruction Using The Non-Seismic Methods Data with Feature Selection
SummaryNon-seismic methods (NSM) in geophysics are a crucial addition to classical seismic information. It helps to make decisions at early stages of geological exploration in case of limited information value conditions and provide a new knowledge about geological structure. While seismic exploration remains as the most spreading technique in field geophysics, non-seismic methods predominantly play a role of auxiliary methods, more often particular cases advocate self-sufficiency of NSM in application to exploration geophysical problems. The restoration of structural boundaries is especially important to restore structural boundaries in the space between seismic survey profiles. A simple solution in the form of interpolation does not provide the necessary prediction accuracy, and requires the creation of a complex, often nonlinear model, which is possible using machine learning (ML) methods. There is a large number of features at one measurement point – the values of the geophysical fields and their transformations (derivatives, filters in a window of different widths). The analysis of the importunateness of each feature before training the ML algorithm allows you to increase the accuracy of the constructed model.
-
-
-
Lithology Classification by Depositional Environment and Well Log Data Using XGBoost Algorithm
Authors T. Micić Ponjiger, S. Šešum, M.V. Naugolnov and O. PilipenkoSummaryThe aim of this paper is to obtain an automatic lithology prediction model by using machine learning (ML) algorithms, with selected well log curves, core description data and sedimentary environment information. This model is applicable for several depositional systems for fields in Pannonian Basin and it’s locally integrated in standard software platform for petrophysicist in Company „Naftna Industrija Srbije“.
-
-
-
Technology for Predicting the Lithology Cube Using Kolmogorov Neural Networks
Authors I.I. priezzhev, D.A. Danko and E.E. TaikulakovSummaryFor the prediction of the lithofacies cube, it is proposed to use new age full-functional Kolmogorov neural networks. These three-layer neural networks, which can be positioned as a new generation of neural networks, have a high degree of freedom comparable to deep multi-layer neural networks. For a more accurate lithofacies cube, it is suggested to perform the forecast in two stages. At the first stage, a separate forecast of each lithofacie is made in the form of a probability cube. At the second stage, the connection of such cubes into one lithofacies cube is based on the principle of maximum probability.
-
-
-
Using Unmanned Aircraft for Seismic Acquisition Supervising and Terrain Scouting Case Study in Republic of Serbia
Authors M.V. Naugolnov, I.Yu. Bogatyrev, M. Bozic, K.A. Kultysheva, V. Stevanovic and A. NestorovicSummarySupervision of seismic acquisition is an essential stage in ensuring both the quality of geophysical information and operational safety during field work. The tasks of supervision support include monitoring of seismic equipment, safety rules implementation, such as, for example, wearing personal protective equipment, as well as compliance with environmental protection requirements, i.e. prevention of oil spills, leaving household waste after completion of work, etc. The modern development of unmanned aerial vehicle (UAV) technologies, coupled with machine learning and computer vision methods makes it possible to create a digital seismic supervisor.
-
-
-
The Use of Hybrid Digital Models and Tracer-Based Dynamic Production Profiling in Intelligent Field Development
Authors E.A. Malyavko, D.S. Tatarinov, V.N. Ogienko and S.I. UrvantsevSummaryToday, the global oil and gas industry needs a solution to process huge data arrays due to a growing number of wells studied and emerging technologies that yield a broader range of information about the geological and technical factors of field development. Therefore, digital analytical tools are required enabling quick analysis of the data on production, well interventions, reservoir pressure, well interference, voidage replacement, and field studies. This paper describes the approaches to data processing and analysis employed during marker-based well logging at several large fields in the Russian Federation. The mentioned technology involves the use of quantum dot marker-reporters as high-precision flow indicators to obtain data on the flow profile and composition in horizontal wells for many years without well interventions. Data analysis was performed using hybrid digital models based on geological and reservoir modeling and a simplified physical reservoir model, involving machine-learning algorithms underlain by neural networks. This platform provides for structured storage of geological and engineering data and enables using dynamic production logging data in stochastic and traditional geological and reservoir modeling. A case study is described to demonstrate how the waterflooding system operation was optimized by applying complex analysis algorithms, generating a notable economic effect.
-
-
-
Development of Software for Reserves` Audit
Authors V.O. Dulov, V.M. Khomik, O.N. Gustaia and S.M. ValitovSummaryThe software that performs engineering and economic calculations for reserves' audit has been developed. The calculation process is carried out according to the methodology adopted by the company and meets the official guidelines of SPE (PRMS) and SEC. Modern tools were used for development of the software, including the use of one of the most popular programming languages, well-known libraries and machine learning tools.
-
-
-
Intelligent Technology for Drilling and Well Construction in Russian Oil and Gas Fields
Authors D.S. Filippova, E.A. Safarova, V.E. Stolyarov and N.A. EreminSummaryThe novelty of the implemented solutions lies in the improvement of drilling technologies based on the application of modeling algorithms and finding the optimal network configuration to perform a reliable forecast based on the artificial neural network model. Without comprehensive automation, it is impossible to reduce the role of personnel, which implies the robotization of part of the drilling process and technologies of descent operations. The presented concept of a geographically distributed system of intelligent monitoring and management is easily adaptable to various technological processes when working in emergency situations due to information support of construction processes. The introduction of technologies provides a reduction in operating costs, an increase in gas and oil production of about 10% and a reduction in well downtime of at least 50 % from the classic technologies of drilling, construction and operation in remote fields.
-
-
-
Application of Machine Learning Algorithms for Prediction of Reservoir Properties in Bazhenov Formation from Simultaneous Inversion
Authors A.S Ugryumov, A.V. Kolomytsev, B.S. Plotnikov and A.A KasyanenkoSummaryThe work explores how different machine learning algorithms can be used to predict Bazhenov formation reservoir properties such as rock type, heavy hydrocarbons and kerogen volume fraction, total organic carbon content, total, effective and dynamic porosity and water saturation from the results of simultaneous inversion of seismic data. The workflow for data processing and handling is proposed and application of various machine-learning models is investigated. Finally, practical issues of data interoperability between different pieces of software are discussed and tips on implementation of the obtained trends in reservoir modeling are given.
-
-
-
Application of the principal component analysis for hydrocarbons - source rocks correlation in the Nile Delta Basin, Egypt
Authors K.O. Osipov, M.E. Elsheikh, A.V. Stoupakova, R.S. Sautkin, E.A. Ablya and M.A. BolshakovaSummaryIn this work, the principal components analysis was applied along with a correlation heatmap to determine the relationship between liquid hydrocarbons samples and source rock samples in the Nile Delta Basin. The principal component analysis made it possible to display oil samples with source rock samples in a single space, and the correlation heatmap helped to determine geological factors that stand for axes of this plot. Based on the results of the study, it was possible to determine the characteristics of source rocks for hydrocarbons which are consist of kerogen type III and have an initial hydrogen Index of less than 200 mg HC/g TOC, that produced liquid hydrocarbons at the early and main stages of oil window. The Miocene source rocks are the closest to the studied oils in terms of depositional environment.
-
-
-
Automated Full-Bore Core Description Application for Production Purposes. From an Idea to IT-Product
SummaryThe automatization is a modern trend in various field of geology. In this work we present a system which were constructed based on convolutional neural network (CNN) for automated core description. The system was successfully applied to production data. The application of the system speeds up the core description process in 7x. A sedimetnologist spent 40 minutes to describe 60 meters of core in a scale of 1:10cm instead of 5 hours. The results are stored in digital format which removes all paperwork. The system helps to describe most of required lithologic types (rock type and its structure). In case of missed rare lithotype – user can add it to the system. A pipeline to prepare and train the CNN model described.
-
-
-
Well Clustering for The Subsequent Identification of Candidate Wells for Hydraulic Fracturing
By Ch.R. AitovSummaryThis paper presents a methodology for selecting candidate wells for hydraulic fracturing. The technique is based on well clustering. Allocation of wells into clusters is carried out according to the most coinciding technological indicators of wells operation. Further selection of wells, one cluster or another, for hydraulic fracturing is performed using well-known optimization algorithms
-
-
-
Machine learning for classification of seismic data
Authors S.I. Litvinov, P.S. Bekeshko and O.O. AdamovichSummaryThis paper discusses the possibility of using neural networks to classify seismic data in order to increase the efficiency of data processing, reduce the time for a geophysicist to perform routine tasks and have a positive impact on the economic efficiency of the project. The result of using deep learning for the classification of seismograms in the presence of non-stationary man-made noise in space is presented. The approach made it possible to achieve high classification accuracy. As a result of the work, an important conclusion was made about the possibility of using this approach to search for man-made noise in seismic records.
-
-
-
Development of The Offline Search System for Company Internal Regulatory Documentation for Supervision of Drilling Processes
Authors E.G. Mironov, M.S. Shikhragimov and G.V. SozonenkoSummaryCurrently, the information search in regulatory documentation for well construction and repairs is carried out primarily manually. This imposes restrictions on the convenience and speed of the supervisor’s work, who is controlling these activities. In this article, the development of the offline search system for the oil company internal regulatory documentation is considered and tested on real queries from «Gazprom Neft» production sites. The proposed search system is installed on the supervisor’s automated workplace (tablet) and demonstrates the best results, when using algorithm based on ElasticSearch. This enables successfully process 72,4% of queries with an average processing time of less than 0,9 second.
-
-
-
Application of The Approximation Neural Network Method for Interpretation of Geoelectric Field Data
Authors I.E. Obornev, M.I. Shimelevich, E.A. Obornev and E.A. RodionovSummaryThe paper presents an example of the application of approximation neural network structures to the problem of reconstructing the resistivity distributions of 2D and 3D piecewise linear media from geoelectric data. This problem is reduced to solving a nonlinear operator equation of the first kind. An algorithm was proposed [ Shimelevich et al, 2018 , Obornev et al, 2020 ] for finding an approximate solution of this equation with a total number of parameters of the order of ∼ n 10 ^ 3, based on the use of neural (Kolmogorov) networks of the multilayer perceptron type. This approach, which allows real-time data inversion, is illustrated both on model examples and on profile and areal field survey data.
-
-
-
Approximation Approach to Solving The Inverse Problem of Geoelectrics Using Neural Networks
Authors M.I. Shimelevich, I.E. Obornev, E.A. Obornev and E.A. RodionovSummaryThe paper presents an approximation neural network algorithm for solving conditionally correct coefficient inverse problems of geoelectrics in the class of media with piecewise constant electrical conductivity given on a parametrization grid. It is shown that the degree of ambiguity (error) of solutions monotonically increases with an increase in the dimension of the parametrization grid. A method is proposed for constructing an optimal parametrization grid, which has the maximum dimension provided that the a priori estimates of the ambiguity of the solutions do not exceed a given value. It is shown that the inverse problem in the considered class of media is reduced to the classical approximation-interpolation problem using neural network polynomials, the solution of which is the essence of the approximation neural network (ANN) method. The intrinsic error of the ANS method is determined, a posteriori estimates of the ambiguity (error) of the obtained approximate solutions are calculated with the achieved synthesis discrepancy. The method makes it possible to formalize and uniformly obtain solutions to the inverse problem of geoelectrics with the total number of the required parameters of the medium ∼ n 10 ^ 3.
-
-
-
Using of Machine Learning Algorithms for Development Analysis of a Brown oil Field Located in The Basement Rocks
Authors M.V. Naugolnov, A.V. Antropov and J. ArsićSummaryThe purpose of the work is a new approach to the development analysis of brown oil field, that is located in basement rocks. Analysis is done for the tasks of the future implementation of the pressure maintenance system with the usage of advanced analytics tools and machine learning algorithms. The solution is based on the integration of well performance data and field studies, as well as on the study of the mutual influence of wells as a factor characterizing the fracture throughput, wells clasterisation and production forecast.
-
-
-
Development of an Application for automatic Quality Control of Seismic Data
SummaryThe purpose of seismic survey is to build a depth-velocity geological model based on the joint interpretation of seismic and well data. Seismic surveys provide uniform coverage of the studied area, and well data provide more complete and accurate information about the studied geological medium at a discrete set of points (well locations). Well data in conjunction with the analysis of seismic stacks and various attributes are used within one software on the seismic interpretation stage. At the same time, the stages of seismic processing and interpretation are historically separated by different software packages. This reduces the efficiency of teamwork within the same project. Therefore, a relevant objective is the development of convenient software tools for joint work. Ideally, work should be carried out in a single software environment in order to ensure effectiveness of teamwork during a project. Thus, the purpose of the study is to create a series of software tools whic are designed to facilitate the interaction between the stages of processing and interpretation.
-
-
-
Modeling of Two-Phase Fluid Flow in a Well Using Machine Learning Algorithms
Authors K.A. Pechko, I.S. Senkin and E.V. BelonogovSummaryBottom hole pressure prediction is crucial issue in integrated field modeling. This article proposes a new approach to well modeling implementing machine learning algorithms. In this paper bottomhole pressure is analysed as dependent variable on four parameters such as level of wellhead pressure, flow rate, gas factor and water cut. The model is developed using the "Random forest" approach with gradient boosting. The model was tested on synthetic and real data from different wells and fields. The prediction accuracy satisfies company requirements and is more than 90 times faster than traditional empirical correlations.
-
-
-
Velocity Model Determining on Refracted Wave Data for Accounting of Variations in Upper Part of Seismic-Geological Section
SummaryAn example of building a velocity model of the upper part of a seismic-geological section is given. Under the model constructing the times of the first arrivals of refracted waves are used. The created model is applied in the problem of static correction, but it can also be utilized for data migration. To improve the efficiency of the proposed technological solution, the methods of machine learning, ray seismic tomography and factors decomposition are used.
-
-
-
Application of Modern Mathematical Methods for Detailed Study of Target Objects of Medium
SummaryThe issues of detailed study of target objects of the medium are considered, which are of interest for the processes of exploration and development of oil and gas reservoirs. Consideration is carried out under an example of data preparation for determining the parameters of target fractured objects. It is shown that the use of a set of methods, consisting of ray tracing, 5D interpolation and factor decompositions, made it possible to obtain qualitative data for solving the corresponding inverse problem.
-
-
-
Features of automated preparation of a business plan for the development of an oil and gas asset based on a digital platform
Authors I.I. Frolova, S.A. Frolov, N.K. Kayurov and K.S. SerdyukSummaryThe implemented approach in the software made it possible to integrate disparate data of an oil and gas producing enterprise on the basis of a single digital platform. The goal of automated preparation of a business plan for the development of an oil and gas producing enterprise with the level of downhole detail to the level of contractual terms has been achieved. As a result of the program implementation of the process approach, the calculation of net cash flow for each well and infrastructure facilities was implemented, which made it possible to improve the quality of calculations and the level of justification of the indicators laid down for the calculation of the business plan. Integration within the digital platform with automatic production forecasting based on measurement data, data on technological modes and virtual production electricity consumption depending on planned production. This software product is being implemented at oil and gas producing enterprises in Russia. In the future, it is planned to expand the functionality based on the proposed scalable ontological model. For example, the selection of optimal development options based on the specified time limits, finances, technical characteristics and target function. In addition, it is planned to expand the intellectual analysis of actual data and factor analysis of deviations.
-
-
-
Minimum Viable Product Continuous Creation Strategy of Cloud Solution Using The Example of a New Hybrid Three-Phase Flow Metering Method
Authors A.A. Zhirkina, Y. Pico, L.E. Dovgilovich and A.M. KuvichkoSummaryEvery high-tech digital product at some phase faces a problem of transfer from an internal-use prototype to a functional digital product, that can be implemented and used by the wide audience. This problem becomes even more difficult when it comes to cloud solutions. One of the possible ways to avoid this painful transition is to use the continuous MVP creation and support strategy, with minimum of resources applied. Real life example of new downhole three-phase flowmetering algorithm implemented at one of the North Caspian oilfields, has shown us that by starting developer-client interactions at the very first stages of the algorithm development we achieve several benefits, such as securing the customer interest in the technology being developed, getting extensive feedback on both algorithmic and user-experience parts of the setup, adapting the user interface and demonstrating new cloud approach to the delivery of digital solutions. Moreover, extensive field-test allows the developer to validate the algorithm performance and make necessary corrections in the core technology itself. Web-framework, that has been used for a front-end development also made it possible to create user-friendly interfaces without engaging with a dedicated front-end engineer and create business logic by hands of the technology developer themselves.
-
-
-
An Investigation of Relation of The Attenuation Parameter of Reflected Seismic Signals with Values of Pore Pressure in The Medium
Authors N.A. Goreyavchev, S.S. Sanin, K.A. Kornienko and G.M. MitrofanovSummaryThe paper presents the results of testing the hypothesis that there is a relationship between the value of the attenuation parameter of seismic signals observed at the surface and the pressure measured in the wells. Hypothesis testing was performed on the basis of field seismic data that underwent standard processing. The attenuation parameter values determined from them were used to obtain correlations between attenuation and pressure. Based on these relationships, predicted pressure values were calculated. Comparison of the predicted and measured pressures showed their high accuracy. This confirmed the validity of the hypothesis under consideration.
-
-
-
The Approach to Evaluate The Confidence of Flow Rate Prediction Accuracy in The Tasks of Virtual Flow Metering
Authors E.V. Kupryashin, I.V. Vrabie and D.E. SyresinSummaryThe paper is devoted to computation of the prediction interval and evaluation of regression accuracy, applied for flowrate computation with virtual flowmeters. Our approach is based on ensembles of neural networks known as Mixture Density Networks and minimizing of the negative-log likelihood function. We investigated the advantages of the applied method to calculate the oil rates and prediction interval using synthetic dataset consisting of 180 wells. The approach has demonstrated to be robust and sensitive the presence of signals variability and noise impact, and to the error caused by the model's uncertainty caused by statistical difference between training and testing datasets.
-
-
-
Ground Roll Noise Attenuation in The Low-Frequency Space Using a Heuristic Approach
Authors D.G. Semin, M.V. Shavkunov and L.A. KovalenkoSummarySeismic data processing is a long, complex and iterative process implemented at Gazprom Neft. One of the stages of this process is the ground roll noise attenuation. Implementation requires the presence in the company of specialists-geophysicists with strong mathematical background, who currently solve this problem by manually selecting combinations of various predetermined filters. The company has been dealing with this task for a long time and has accumulated a representative sample of data where manual noise attenuation has been implemented. This information can be used as an automatic hypothesis test for new filtering methods. Based on this approach, we propose a method for obtaining ground roll noise masks and a method for its attenuation in the Fourier frequency domain (FK transform) based on heuristic rules.
-
-
-
Autonomous Reservoir Management with Deep Reinforcement Learning
Authors Y.E. Pico and A.A. LemikhovSummaryThe introduction of intelligent completion systems opens the opportunity to approach reservoir optimization as optimal control problem. Moreover, improving in Deep Reinforcement Learning make viable solving the optimal control problem to achieve autonomous control. We show how using intelligent completions and reservoir modeling, the task of autonomous choke control is solved. The present article is one of the first attempts to analyze and compare efficiency of novel DRL algorithms applied to autonomous reservoir control problem.
-
-
-
Interpretation of Distributed Fluid Temperature Logging in a Producer with Gradient Optimization and Uncertainty Analysis
Authors A.E. Karakulev, L.A. Kotlyar and I.L. SofronovSummaryThe paper provides an approach for interpreting downhole distributed temperature sensing (DTS) and the results of its application in cases of synthetic and real production data. The outcome of such interpretation is a profile of fluid flows from reservoir layers. The given problem, however, is ambiguous, that is why the suggested approach consists of three steps: formulation of the inverse problem based on minimization of the constructed functional with the developed fast gradient optimization method, massive parallel inversions to collect a set of different interpretations and Bayesian inference of the most probable flow profiles incorporating uncertainty. All three issues are discussed in detail. Modifications of gradient optimizer making it fast and robust are described along with regularization allowing us to approach global functional minimum for synthetic data (illustration is provided) and decrease the ambiguity for real data. Explanation and example of how statistical analysis turns a set of interpretations into the most probable flow profiles and corresponding uncertainty with EM-clustering using Dirichlet distribution are included. All in all, the developed approach for effective evaluation of flow profiles and their statistical analysis can become a useful tool in oil and gas industry automating a big part of DTS interpretation process.
-
-
-
Application of Deep Autoencoders for Novelty and Anomaly Detection in Well Testing Data Analysis
Authors A.R. Valeev, D.E. Syresin and I.V. VrabieSummaryThe novelty detection problem is essential for the study of non-stationary processes, in which the received signals have a wide variability in time. Among such problems we can single out the problem of research of non-stationary multiphase flows in wells. Numerical analysis methods are often used to investigate such flows, but does not always allow to reproduce the complexity and features of real systems, especially at its anomalous behavior. To solve this problem in the problems of well tests, we have developed an approach to detect novelty of some data in relation to other. The proposed model is able to detect variations in time series by analysis of magnitude and dynamic characteristics of the flow parameters. The method is robust to outliers in signals, simply interpreted and has a low computational complexity. The model was evaluated on synthetic data obtained with a multiphase non-stationary flow simulator.
-
-
-
Use of Geostatistical Algorithms for Complex Interpretation of Well Data and Prediction of Reservoir Distribution Zones
Authors E. Anokhina, G. Erokhin, A. Kamyshnikov and R. SimonovSummaryThe prospects for the oil and gas potential of the Pre-Jurassic complex in one field in Western Siberia are associated with the weathering crust. To solve the problem of identifying highly productive zones, a complex interpretation of information on the material composition of rocks and the results of clustering of APS and gamma-ray log data was performed
-
-
-
Capabilities of Convolutional Neural Networks Based Algorithms for Solving Resistivity Logging Tasks
Authors K.N. Danilovskiy, A.M. Petrov, A.R. Leonenko and K.V. SukhorukovaSummaryRussian unfocused lateral logs (BKZ) are infamously known for their complexity. However, the BKZ was widely used in the Soviet Union, therefore, a large amount of data was measured at various oilfields. Reinterpretation of these logs using modern processing techniques is an urgent task. In this study, we propose a new approach to Russian resistivity logs modeling and processing, based on fully convolutional networks (FCN). FCN architecture allows taking into account signal-forming media domain for every measurement point. Training datasets are created individually for the task from real and numerically simulated data. The results of the proposed approach applying are demonstrated on the algorithm for transforming BKZ signals into focused lateral log. Application of the algorithm to real data makes it possible to check data conditionality, perform accurate depth matching, and also facilitates cross-well correlation with an incomplete set of logs.
-
-
-
The Lifecycle of a Machine Learning System in Production
By V.I. BulaevSummaryThe paper presents a general view of the pipeline for deploying a machine learning model to production. It is shown that today the infrastructural costs of embedding ML into the production circuit can exceed the costs of creating and training a model by almost an order of magnitude.
-