Utilizing machine learning for flow zone indicators prediction and hydraulic flow unit classification
Tengku Astsauri1, Muhammad Habiburrahman1, Ahmed Farid Ibrahim2,3
1Department of Petroleum Engineering and Geosciences, King Fahd University of Petroleum & Minerals, 31261, Dhahran, Saudi Arabia.
Scientific Reports
|February 20, 2024
Summary
Machine learning accurately predicts Flow Zone Indicator (FZI) for reservoir characterization. This approach efficiently identifies high-quality reservoir zones, improving field development decisions.
Area of Science:
- Petroleum Geoscience
- Machine Learning Applications
- Reservoir Engineering
Background:
- Reservoir characterization is crucial for understanding subsurface heterogeneity, but faces challenges due to scale-dependent variations.
- Hydraulic Flow Unit (HFU) zonation groups rocks by similar petrophysical and flow characteristics.
- Flow Zone Indicator (FZI) is a key parameter for HFU determination, but its measurement is costly and time-consuming.
Purpose of the Study:
- To employ supervised and unsupervised machine learning algorithms for predicting FZI and classifying reservoirs into distinct HFUs.
- To develop and optimize predictive models using various machine learning techniques.
- To identify high-quality reservoir zones using the developed models.
Main Methods:
- Utilized unsupervised K-means clustering and supervised algorithms (Random Forest, XGBoost, SVM, ANN) for FZI prediction and HFU classification.
- Trained and tested models using FZI values from Reservoir Core Analysis Laboratory (RCAL) data.
- Applied 3-fold cross-validation and random search cross-validation for hyper-parameter tuning and model optimization.
Main Results:
- Supervised algorithms achieved high performance, with R-squared values of 0.89 (training) and 0.91 (testing).
- Random Forest demonstrated superior performance with R-squared values of 0.957 (training) and 0.908 (testing).
- K-means clustering and Gaussian mixture models successfully classified data into 10 HFUs, identifying specific high-potential reservoir zones.
Conclusions:
- Machine learning provides a rapid, cost-effective, and precise alternative to conventional methods for reservoir characterization.
- The developed models successfully predict FZI and classify HFUs, enabling efficient identification of high-quality reservoir potential.
- This approach revolutionizes decision-making in field development by offering accurate subsurface insights.
Related Concept Videos
01:24Rapidly Varying Flow
62
Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...
62
01:23Plane Potential Flows
386
Plane potential flows simplify fluid motion by assuming the fluid to be irrotational and incompressible. These characteristics allow these flows to be described by a velocity potential function, ϕ, representing the flow speed in a given direction, and a stream function, ψ, that visualizes the flow path, both governed by Laplace's equation. These parameters help in estimating flow patterns, velocity distributions, and pressure fields around various hydraulic structures.
Uniform...
Uniform...
386
01:27Laminar Flow
1.1K
Laminar flow represents a smooth, orderly fluid motion where particles move along parallel paths, resulting in minimal mixing between layers. Streamlined particle paths characterize this flow regime and occur under conditions where viscous forces dominate over inertial forces. The distinction between laminar, transitional, and turbulent flow is primarily determined by the Reynolds number, a dimensionless quantity calculated as:
1.1K
01:21Design Example: Creating a Hydraulic Model of a Dam Spillway
169
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
169
01:22General Characteristics of Pipe Flow I
1.2K
Pipe flow refers to the movement of fluids within fully enclosed conduits, typically cylindrical in shape, such as water pipes or hydraulic hoses. These conduits are designed to withstand high-pressure gradients that drive fluid movement, contrasting with open-channel flows, where gravity is the primary driving force. Rectangular conduits, like air conditioning and heating ducts, generally operate at lower pressures and are less suited for high-pressure applications.
The classification of fluid...
The classification of fluid...
1.2K
01:27Uniform Depth Channel Flow
74
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
74