Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Results
Abstract Carbon Capture and Sequestration (CCS), which combines capture of CO2 from large stationary sources with geological storage, has emerged as an attractive option for emissions reduction. Hydrogen underground storage (HUS) is viewed as an effective strategy for storing large volumes of surplus electrical energy from renewable sources. The objective of this paper is to discuss the opportunities and challenges for adapting petroleum reservoir engineering techniques for the subsurface aspects of CCS and HUS projects based on a critical review of field projects and conceptual studies. Areas of focus include: (a) storage resource estimation, injectivity analysis from field data, dynamic reservoir modeling, and coupled flow and geomechanics for CCS, and (b) well deliverability, dynamics of fluid withdrawal and reactive transdport of hydrogen in-situ for HUS projects. Specifically, our goal is to discuss how traditional workflows for oil and gas applications have been (or could be) modified for CCS projects in deep saline formations and HUS projects in salt caverns or aquifers. We also identify specific areas where reservoir engineering practitioners can add value in CCS and HUS related reservoir analysis and modeling.
- Europe (1.00)
- North America > Canada (0.67)
- North America > United States > Texas > Harris County > Houston (0.28)
- Research Report (0.68)
- Overview (0.67)
- Geology > Structural Geology (1.00)
- Geology > Geological Subdiscipline > Geomechanics (1.00)
- Geology > Mineral (0.93)
- Energy > Oil & Gas > Upstream (1.00)
- Government > Regional Government > North America Government > United States Government (0.67)
- North America > United States > West Virginia > Appalachian Basin (0.99)
- North America > United States > Virginia > Appalachian Basin (0.99)
- North America > United States > Texas > Anadarko Basin (0.99)
- (49 more...)
- Reservoir Description and Dynamics > Storage Reservoir Engineering > CO2 capture and sequestration (1.00)
- Reservoir Description and Dynamics > Improved and Enhanced Recovery > Waterflooding (1.00)
- Health, Safety, Environment & Sustainability > Sustainability/Social Responsibility > Sustainable development (1.00)
- (2 more...)
An Efficient Deep Learning-Based Workflow Incorporating a Reduced Physics Model for Subsurface Imaging in Unconventional Reservoirs
Onishi, Tsubasa (Texas A&M University) | Chen, Hongquan (Texas A&M University) | Datta-Gupta, Akhil (Texas A&M University) | Mishra, Srikanta (Battelle Memorial Institute)
Abstract We present a novel deep learning-based workflow incorporating a reduced physics model that can efficiently visualize well drainage volume and pressure front propagation in unconventional reservoirs in near real-time. The visualizations can be readily used for qualitative and quantitative characterization and forecasting of unconventional reservoirs. Our aim is to develop an efficient workflow that allows us to โseeโ within the subsurface given measured data, such as production data. The most simplistic way to achieve the goal will be to merely train a deep learning-based regression model where the input consists of some measured data, and the output is a subsurface image, such as pressure field. However, the high output dimension that corresponds to spatio-temporal steps makes the training inefficient. To address this challenge, an autoencoder network is applied to discover lower dimensional latent variables that represent high dimensional output images. In our approach, the regression model is trained to predict latent variables, instead of directly constructing an image. In the prediction step, the trained regression model first predicts latent variables given measured data, then the latent variables will be used as inputs of the trained decoder to generate a subsurface image. In addition, fast marching-method (FMM)-based rapid simulation workflow which transforms original 2D or 3D problems into 1D problems is used in place of full-physics simulation to efficiently generate datasets for training. The capability of the FMM-based rapid simulation allows us to generate sufficient datasets within realistic simulation times, even for field scale applications. We first demonstrate the proposed approach using a simple illustrative example. Next, the approach is applied to a field scale reservoir model built after the publicly available data on the Hydraulic Fracturing Test Site-I (HFTS-I), which is sufficiently complex to demonstrate the power and efficacy of the approach. We will further demonstrate the utility of the approach to account for subsurface uncertainty. Our approach, for the first time, allows data-driven visualization of unconventional well drainage volume in 3D. The novelty of our approach is the framework which combines the strengths of deep learning-based models and the FMM-based rapid simulation. The workflow has flexibility to incorporate various spatial and temporal data types.
- Geology > Rock Type > Sedimentary Rock > Clastic Rock (0.46)
- Geology > Geological Subdiscipline > Geomechanics (0.46)
- Geology > Petroleum Play Type > Unconventional Play (0.46)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (29 more...)
Robust CO2 Plume Imaging Using Joint Tomographic Inversion Of Distributed Pressure And Temperature Measurements
Yao, Changqing (Texas A&M University) | Chen, Hongquan (Texas A&M University) | Datta-Gupta, Akhil (Texas A&M University) | Mawalkar, Sanjay (Battelle Memorial Institute) | Mishra, Srikanta (Battelle Memorial Institute) | Pasumarti, Ashwin (Battelle Memorial Institute)
Abstract Geologic CO2 sequestration and CO2 enhanced oil recovery (EOR) have received significant attention from the scientific community as a response to climate change from greenhouse gases. Safe and efficient management of a CO2 injection site requires spatio-temporal tracking of the CO2 plume in the reservoir during geologic sequestration. The goal of this paper is to develop robust modeling and monitoring technologies for imaging and visualization of the CO2 plume using routine pressure/temperature measurements. The streamline-based technology has proven to be effective and efficient for reconciling geologic models to various types of reservoir dynamic response. In this paper, we first extend the streamline-based data integration approach to incorporate distributed temperature sensor (DTS) data using the concept of thermal tracer travel time. Then, a hierarchical workflow composed of evolutionary and streamline methods is employed to jointly history match the DTS and pressure data. Finally, CO2 saturation and streamline maps are used to visualize the CO2 plume movement during the sequestration process. The power and utility of our approach are demonstrated using both synthetic and field applications. We first validate the streamline-based DTS data inversion using a synthetic example. Next, the hierarchical workflow is applied to a carbon sequestration project in a carbonate reef reservoir within the Northern Niagaran Pinnacle Reef Trend in Michigan, USA. The monitoring data set consists of distributed temperature sensing (DTS) data acquired at the injection well and a monitoring well, flowing bottom-hole pressure data at the injection well, and time-lapse pressure measurements at several locations along the monitoring well. The history matching results indicate that the CO2 movement is mostly restricted to the intended zones of injection which is consistent with an independent warmback analysis of the temperature data. The novelty of this work is the streamline-based history matching method for the DTS data and its field application to the Department of Engergy regional carbon sequestration project in Michigan.
- Asia (1.00)
- North America > United States > Michigan (0.45)
- Geophysics > Seismic Surveying (1.00)
- Geophysics > Time-Lapse Surveying > Time-Lapse Seismic Surveying (0.95)
- North America > Canada > British Columbia > Peace River Field (0.99)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Utsira Formation (0.99)
- Asia > India > Rajasthan > Rajasthan Basin > Barmer Basin > Rajasthan Block > Mangala Field > Fatehgarh Formation (0.99)
- (6 more...)
- Well Completion > Completion Monitoring Systems/Intelligent Wells > Downhole sensors & control equipment (1.00)
- Reservoir Description and Dynamics > Storage Reservoir Engineering > CO2 capture and sequestration (1.00)
- Reservoir Description and Dynamics > Improved and Enhanced Recovery (1.00)
- (3 more...)
Robust Data-Driven Machine-Learning Models for Subsurface Applications: Are We There Yet?
Mishra, Srikanta (Battelle Memorial Institute) | Schuetter, Jared (Battelle Memorial Institute) | Datta-Gupta, Akhil (Texas A&M University) | Bromhal, Grant (National Energy Technology Laboratory, US Department of Energy)
Algorithms are taking over the world, or so we are led to believe, given their growing pervasiveness in multiple fields of human endeavor such as consumer marketing, finance, design and manufacturing, health care, politics, sports, etc. The focus of this article is to examine where things stand in regard to the application of these techniques for managing subsurface energy resources in domains such as conventional and unconventional oil and gas, geologic carbon sequestration, and geothermal energy. It is useful to start with some definitions to establish a common vocabulary. Data analytics (DA)โSophisticated data collection and analysis to understand and model hidden patterns and relationships in complex, multivariate data sets Machine learning (ML)โBuilding a model between predictors and response, where an algorithm (often a black box) is used to infer the underlying input/output relationship from the data Artificial intelligence (AI)โApplying a predictive model with new data to make decisions without human intervention (and with the possibility of feedback for model updating) Thus, DA can be thought of as a broad framework that helps determine what happened (descriptive analytics), why it happened (diagnostic analytics), what will happen (predictive analytics), or how can we make something happen (prescriptive analytics) (Sankaran et al. 2019). Although DA is built upon a foundation of classical statistics and optimization, it has increasingly come to rely upon ML, especially for predictive and prescriptive analytics (Donoho 2017). While the terms DA, ML, and AI are often used interchangeably, it is important to recognize that ML is basically a subset of DA and a core enabling element of the broader application for the decision-making construct that is AI. In recent years, there has been a proliferation in studies using ML for predictive analytics in the context of subsurface energy resources. Consider how the number of papers on ML in the OnePetro database has been increasing exponentially since 1990 (Fig. 1). These trends are also reflected in the number of technical sessions devoted to ML/AI topics in conferences organized by SPE, AAPG, and SEG among others; as wells as books targeted to practitioners in these professions (Holdaway 2014; Mishra and Datta-Gupta 2017; Mohaghegh 2017; Misra et al. 2019). Given these high levels of activity, our goal is to provide some observations and recommendations on the practice of data-driven model building using ML techniques. The observations are motivated by our belief that some geoscientists and petroleum engineers may be jumping the gun by applying these techniques in an ad hoc manner without any foundational understanding, whereas others may be holding off on using these methods because they do not have any formal ML training and could benefit from some concrete advice on the subject. The recommendations are conditioned by our experience in applying both conventional statistical modeling and data analytics approaches to practical problems.
Data-Driven Rate Optimization Under Geologic Uncertainty
Sen, Deepthi (Texas A&M University) | Chen, Hongquan (Texas A&M University) | Datta-Gupta, Akhil (Texas A&M University) | Kwon, Joseph (Texas A&M University) | Mishra, Srikanta (Battelle)
Abstract We propose a novel approach for rate optimization during a waterflood under geologic uncertainty in reservoir properties such as permeability and porosity. The traditional approach typically involves several runs of the forward simulator. This may not scale well when the optimization is to be performed at the full field-level and over multiple geologic realizations. A machine-learning (ML) based approach which is quick and scalable for rate optimization over multiple geologic realizations is proposed instead. The training data for the model is generated by running the forward simulator with randomly assigned well rates using multiple geologic realizations. A reduced order representation of the permeability heterogeneity in each of the realizations is derived using a grid connectivity transformation (GCT). This step involves finding basis functions corresponding to the different modal frequencies of the grid connectivity represented by the grid Laplacian. The projection of the heterogeneous property field along these basis functions gives the basis coefficients that form the reduced order representation. Subsequently, for each training datapoint, streamlines are traced and the minimum time of flight (TOF) representing the tracer breakthrough time at each producer is recorded. The basis coefficients and well rates are fed to a machine learning model as input and the minimum TOF at the producers forms the output of the model. This trained model can then be used along with an optimizer for computing the optimal injection rates to maximize the injection sweep efficiency. This corresponds to minimizing the variance in the minimum TOF within each well group. Different architectures of neural network are tested using 5-fold cross validation to decide the best ML model to compute the streamline time of flight. The trained model is used to perform well rate optimization over multiple realizations of geology by using a risk tolerance penalty. The optimal well rates thus obtained are compared with two cases: a) equal well rates assigned to all injectors and producers and b) well rates obtained by optimizing over a single realization without considering the uncertainty in geology. The optimal well rates are seen to offer better oil recovery and sweep efficiency than both cases. The workflow is tested for a 50x50 two-dimensional (2D) heterogenous permeability field and for the SPE benchmark Brugge field, and is seen to result in significant improvement in oil recovery and sweep efficiency. A single forward run of the trained ML model is faster than the conventional simulator by about 3 orders of magnitude, making the approach suitable for large scale field application accounting for geologic uncertainty. The parsimonious representation of geologic heterogeneity and the use of ML for forward modeling makes the approach highly scalable and well-suited for full field applications.
Modeling Early Time Rate Decline in Unconventional Reservoirs Using Machine Learning Techniques
Vyas, Aditya (Texas A&M University) | Datta-Gupta, Akhil (Texas A&M University) | Mishra, Srikanta (Battelle)
Abstract Decline curves are fast methods to predict production behavior in oil and gas wells. Some of the notable decline curve methods are Arpโs, SEDM (Stretched Exponential Decline Model), Duongโs Model and Weibull decline curves. Available production history data can be used to fit any of these equations and future production decline can thus be extrapolated. However, when limited production data is available during early periods of well history, these equations could be fitted using inaccurate parameters leading to erroneous predictions. Also, the traditional decline curve analysis approach does not account for the complexities related to reservoir description and well completions. This study utilizes publicly available databases of the Eagle Ford formation to develop a novel predictive modeling methodology linking decline curve model parameters to well completion related variables that allows for the rapid generation of synthetic decline curves at potential new well locations. Modern machine learning algorithms such as Random Forests (RF), Support Vector Machines (SVM) and Multivariate Adaptive Regression Splines (MARS) can then be used to model the well decline behavior. Cross-Validation technique such as k-fold cross-validation can be used to quantify the predictive accuracy of these models when applied to new wells. First, production data are fitted to decline curve models to estimate the corresponding model parameters. Next, machine learning models are built for these parameters as a function of initial flow rate, various well completion parameters (i.e., number of hydraulic fracture stages, completed lengths, proppant and fracturing fluid amounts) and well location/depth parameters (i.e., well latitudes, longitudes, total vertical depth of heel and difference between total vertical depths of heel and toe of horizontal wells). These models are used to rapidly predict the decline curves for new or existing wells without the need for costly reservoir simulators. It has been found that accurate prediction of rate decline of new wells can be predicted using this methodology. This method can also predict ultimate recovery of a new well based on data collected from previous wells. To our knowledge, this is the first time machine learning algorithms have been used to predict the decline curve parameters and examine the relative performance of various decline curve models. The power and utility of our approach are demonstrated by successful prediction of the decline behavior of blind wells that were not incorporated in the analysis. We also examine the relative influences of various well design and location variables to determine the hidden correlations or interactions among them which are hard to decipher with other methods.
Summary Predicting permeability from well logs typically involves classification of the well-log response into relatively homogeneous subgroups based on electrofacies, Lithofacies, or hydraulic flow units (HFUs). The electrofacies-based classification involves identifying clusters in the well-log response that reflect "similar" minerals and lithofacies within the logged interval. This statistical procedure is straightforward and inexpensive. However, identification of lithofacies and HFUs relies on core-data analysis and can be expensive and time-consuming. To date, no systematic study has been performed to investigate the relative merits of the three methods in terms of their ability to predict permeability in uncored wells. The purpose of this paper is three-fold. First, we examine the interrelationship between the three approaches using a powerful and yet intuitive statistical tool called "classification-tree analysis." The tree-based method is an exploratory technique that allows for a straight forward determination of the relative importance of the well logs in identifying electrofacies, lithofacies, and HFUs. Second, we use the tree-based method to propose an approach to account for missing well logs during permeability predictions. This is a common problem encountered during field applications. Our approach follows directly from the hierarchical decision tree that visually and quantitatively illustrates the relationship between the data groupings and the individual well-log response. Finally, we demonstrate the power and utility of our approach via field applications involving permeability predictions in a highly complex carbonate reservoir, the Salt Creek Field Unit (SCFU) in west Texas. The intuitive and visual nature of the tree-classifier approach also makes it a powerful tool for communication between geologists and engineers. Introduction The estimation of permeability from well logs has seen many developments over the years. The common practice has been to crossplot core porosity and core permeability and to define a regression relationship to predict permeability in uncored wells based on the porosity from well logs. However, permeability predictions in complex carbonate reservoirs are generally complicated by sharp local variations in reservoir properties caused by abrupt changes in the depositional environment. Another distinctive feature in carbonate reservoirs is the porosity/permeability mismatch (that is, low permeability in regions exhibiting high porosity and vice versa). All these features are extremely important from the point of view of fluid-flow predictions, particularly early-breakthrough response along high-permeability streaks. A variety of approaches have been proposed to partition well-log responses into distinct classes to improve permeability predictions. The simplest approach uses flow zones or reservoir layering. Other approaches have used lithofacies information identified from cores, electrofacies derived from well logs, and the concept of HFUs. However, because of the extreme petrophysical variations rooted in diagenesis and complex pore geometry, reliable permeability predictions from well logs have remained an outstanding challenge, particularly in complex carbonate reservoirs. A major difficulty in this regard has been the proper classification of well logs in uncored wells. Several problems are encountered in practical applications of current methodologies to data classification in uncored wells. These methods generally are based on a specific set of well logs; therefore, any missing well log can result in misclassification. This situation frequently occurs in field applications. Also, the impact of each well log in the final prediction is not clear. The situation is complicated by the fact that very often, the well logs are transformed into new variables such as principal components before classification. Furthermore, discriminant analysis, a statistical technique commonly used to assign classification on the basis of log response, is restricted to simple linear (or quadratic) additive models that may be inadequate, particularly for complex carbonate reservoirs. The current procedure for data partitioning and classifications using multivariate statistical analysis also tends to obscure communication between engineers and geologists. A simple and intuitive approach that works directly with well logs rather than transformed data can significantly improve this communication gap. In this paper, we present a powerful graphical approach for data classification or partitioning for permeability predictions using well logs based on a statistical approach called classification-tree analysis. Tree-based modeling is an exploratory technique for uncovering structures in the data. It is a way to present rules to predict or explain responses both for categorical variables such as lithofacies or electrofacies and for continuous variables such as permeability. When we have continuous data as the response variable, the procedure is called "regression trees"; if the response variable is categorical data, it is called "classification trees." Although tree-based methods are useful for both classification and regression problems, we focus here on the former because our main concern is data partitioning or grouping for permeability predictions. The classification rules are obtained by applying a procedure known as recursive partitioning of the available data, applying splits successively until certain stop criteria are satisfied. Then the rules can be displayed in the form of a binary tree, hence the name.
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (22 more...)