Machine Learning Assisted History Matching to Integrate Fiber Optic Data with Reservoir Simulation

2020 ◽  
Author(s):  
Giuseppe Feo ◽  
Jyotsna Sharma ◽  
Stephen Cunningham
Keyword(s):  
Machine Learning ◽  
Reservoir Simulation ◽  
History Matching ◽  
Fiber Optic ◽  
Assisted History Matching

A Fast Gridding Method for Capturing Geological Complexity and Uncertainty

2021 ◽  
Author(s):  
Yifei Xu ◽  
Priyesh Srivastava ◽  
Xiao Ma ◽  
Karan Kaul ◽  
Hao Huang
Keyword(s):  
Efficient Method ◽  
Reservoir Simulation ◽  
History Matching ◽  
Mapping Method ◽  
Reservoir Properties ◽  
Structural Framework ◽  
Assisted History Matching ◽  
Grid Topology ◽  
Geological Complexity ◽  
Complex Channel

Abstract In this paper, we introduce an efficient method to generate reservoir simulation grids and modify the fault juxtaposition on the generated grids. Both processes are based on a mapping method to displace vertices of a grid to desired locations without changing the grid topology. In the gridding process, a grid that can capture stratigraphical complexity is first generated in an unfaulted space. The vertices of the grid are then displaced back to the original faulted space to become a reservoir simulation grid. The resulting reversely mapped grid has a mapping structure that allows fast and easy fault juxtaposition modification. This feature avoids the process of updating the structural framework and regenerating the reservoir properties, which may be time-consuming. To facilitate juxtaposition updates within an assisted history matching workflow, several parameterized fault throw adjustment methods are introduced. Grid examples are given for reservoirs with Y-faults, overturned bed, and complex channel-lobe systems.

Reservoir Simulation Design Strategy for Next-Generation Multi-level Assisted History Matching

2014 ◽  
Author(s):  
S. Mirzadeh ◽  
R. Chambers ◽  
G. A. Carvajal ◽  
A. P. Singh ◽  
M. Maucec ◽  
...  
Keyword(s):  
Reservoir Simulation ◽  
History Matching ◽  
Design Strategy ◽  
Next Generation ◽  
Simulation Design ◽  
Assisted History Matching ◽  
Multi Level

Reservoir Simulation Design Strategy for Next-Generation Multi-level Assisted History Matching

2014 ◽  
Author(s):  
S. Mirzadeh ◽  
R. Chambers ◽  
G. A. Carvajal ◽  
A. P. Singh ◽  
M. Maucec ◽  
...  
Keyword(s):  
Reservoir Simulation ◽  
History Matching ◽  
Design Strategy ◽  
Next Generation ◽  
Simulation Design ◽  
Assisted History Matching ◽  
Multi Level

Reservoir Simulation, Modeling of a Complex Offshore Field Uses AI and Machine Learning

2021 ◽  
Vol 73 (07) ◽  
pp. 44-45
Author(s):  
Chris Carpenter
Keyword(s):  
Machine Learning ◽  
Reservoir Simulation ◽  
History Matching ◽  
Data Driven ◽  
Flow Through Porous Media ◽  
Reservoir Model ◽  
Full Field ◽  
Flow Through ◽  
Offshore Field ◽  
Dynamic Variables

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 201693, “Subsurface Analytics Case Study: Reservoir Simulation and Modeling of a Highly Complex Offshore Field in Malaysia Using Artificial Intelligence and Machine Learning,” by Rahim Masoudi, SPE, Petronas; Shahab D. Mohaghegh, SPE, West Virginia University; and Daniel Yingling, Intelligent Solutions, et al., prepared for the 2020 SPE Annual Technical Conference and Exhibition, originally scheduled to be held in Denver, 5–7 October. The paper has not been peer reviewed. Using commercial numerical reservoir simulators to build a full-field reservoir model and simultaneously history matching multiple dynamic variables for a highly complex offshore mature field in Malaysia had proved challenging. In the complete paper, the authors demonstrate how artificial intelligence (AI) and machine learning can be used to build a purely data-driven reservoir simulation model that successfully history matches all dynamic variables for wells in this field and subsequently can be used for production forecasting. This synopsis concentrates on the process used, while the complete paper provides results of the fully automated history matching. Subsurface Analytics In the presented technique, which the authors call subsurface analytics, data-driven pattern-recognition technologies are used to embed the physics of the fluid flow through porous media and to create a model through discovering the best, most-appropriate relationships between all measured data in each reservoir. This is an alternative to starting with the construction of mathematical equations to model the physics of the fluid flow through porous media, followed by modification of geological models in order to achieve history match. The key characteristics of subsurface analytics are that no interpretations, assumptions, or complex initial geological models (and thus no upscaling) exist. Furthermore, the main series of dynamic variables used to build this model is measured on the surface, while other major static, and sometimes even dynamic, characteristics are based on subsurface measurements, thereby making this approach a combination of reservoir and wellbore-simulation models rather than merely a reservoir model. The history-matching process of the subsurface analytics process is completely automated. Top-Down Modeling (TDM) TDM is a data-driven reservoir modeling approach under the realm of subsurface analytics technology that uses AI and machine learning to develop full-field reservoir models based on measurements rather than solutions of governing equations. TDM integrates all available field measurements into a full-field reservoir model and matches the historical production of all individual wells in a mature field with a single AI-based model. The model is validated through blind history matching. The approach then can forecast a field’s behavior on a well-by-well basis. TDM is a data-driven approach; thus, the quality assurance/quality control (QA/QC) of the data input is para-mount before embarking on the modeling process to ensure that the artificial neural network (ANN) is taught properly with reliable training of the data set. This includes the understanding of data availability and magnitude, analysis of well-by-well production performance trends, and identification of data anomalies.

Machine learning assisted history matching for a deepwater lobe system

2021 ◽  
pp. 109086
Author(s):  
Honggeun Jo ◽  
Wen Pan ◽  
Javier E. Santos ◽  
Hyungsick Jung ◽  
Michael J. Pyrcz
Keyword(s):  
Machine Learning ◽  
History Matching ◽  
Assisted History Matching

Successful Application of Honey-Bee Optimization Technique in Reservoir Engineering Assisted History Matching: Case Study

2021 ◽  
Author(s):  
Mohamed Shams
Keyword(s):  
Simulation Model ◽  
Reservoir Simulation ◽  
Optimization Algorithm ◽  
History Matching ◽  
Optimization Technique ◽  
Food Sources ◽  
Bee Colony ◽  
Assisted History Matching ◽  
Bee Colony Optimization ◽  
Reservoir Simulation Model

Abstract This paper provides the field application of the bee colony optimization algorithm in assisting the history match of a real reservoir simulation model. Bee colony optimization algorithm is an optimization technique inspired by the natural optimization behavior shown by honeybees during searching for food. The way that honeybees search for food sources in the vicinity of their nest inspired computer science researchers to utilize and apply same principles to create optimization models and techniques. In this work the bee colony optimization mechanism is used as the optimization algorithm in the assisted the history matching workflow applied to a reservoir simulation model of WD-X field producing since 2004. The resultant history matched model is compared with with those obtained using one the most widely applied commercial AHM software tool. The results of this work indicate that using the bee colony algorithm as the optimization technique in the assisted history matching workflow provides noticeable enhancement in terms of match quality and time required to achieve a reasonable match.

Sign in / Sign up

Export Citation Format

Share Document