Study on the linkages between microstructure and permeability of porous media using pore network and BP neural network

Summary This study analyzes the production behaviors of six deep coalbed-methane (CBM) wells (>1980 m) completed in the Ordos Basin and presents a machine-learning method to predict gas production for six target wells. The production behaviors of target wells are characterized with several months of rapidly declining pressure, following by several years of stabilized gas rate and pressure. Production data analysis suggests a relatively large amount of free gas (but limited free water) in coal seams under in-situ condition. The production mechanisms generally transit from free-gas expansion and fracture/cleat closure at early stage to gas desorption at later stage. We treated the target wells’ production data as time-series data and applied the Long Short-Term Memory (LSTM) model on the target wells for gas-rate predictions. We also employed a Bayesian-probabilistic method to optimize the LSTM model (BO-LSTM). Our results demonstrate the BO-LSTM model’s robustness in gas-rate predictions for target wells. Also, treating casing pressure and liquid level as inputs is sufficient for the BO-LSTM model to reach a reliable production forecast. This study provides a promising tool to forecast the gas production of deep-CBM wells using surface rates and pressure data. The findings of this study may guide the reservoir management and development-strategy optimizations of deep-CBM reservoirs.

show abstract

Study on the Impact of Microscopic Pore Structure Characteristics in Tight Sandstone on Microscopic Remaining Oil after Polymer Flooding

Zhao,

Sun,

Zhang

et al. 2024

Polymers

View full text Add to dashboard Cite

As a non-renewable resource, oil faces increasing demand, and the remaining oil recovery rates in existing oil fields still require improvement. The primary objective of this study is to investigate the impact of pore structure parameters on the distribution and recovery of residual oil after polymer flooding by constructing a digital pore network model. Using this model, the study visualizes the post-flooding state of the model with 3DMAX-9.0 software and employs a range of simulation methods, including a detailed analysis of the pore size, coordination number, pore–throat ratio, and wettability, to quantitatively assess how these parameters affect the residual oil distribution and recovery. The research shows that the change in the distribution of pore sizes leads to a decrease in cluster-shaped residual oil and an increase in columnar residual oil. An increase in the coordination number increases the core permeability and reduces the residual oil; for example, when the coordination number increases from 4.3 to 6, the polymer flooding recovery rate increases from 24.57% to 30.44%. An increase in the pore–throat ratio reduces the permeability and causes more residual oil to remain in the throat; for example, when the pore–throat ratio increases from 3.2 to 6.3, the total recovery rate decreases from 74.34% to 63.72%. When the wettability changes from oil-wet to water-wet, the type of residual oil gradually changes from the difficult-to-drive-out columnar and film-shaped to the more easily recoverable cluster-shaped; for example, when the proportion of water-wet throats increases from 0.1:0.9 to 0.6:0.4, the water flooding recovery rate increases from 35.63% to 51.35%. Both qualitative and quantitative results suggest that the digital pore network model developed in this study effectively predicts the residual oil distribution under different pore structures and provides a crucial basis for optimizing residual oil recovery strategies.

show abstract

Study on the linkages between microstructure and permeability of porous media using pore network and BP neural network

Cited by 3 publications

References 40 publications

Breeding model of Bumblebee based on linear regression and BP neural network

Breeding model of Bumblebee based on linear regression and BP neural network

Production Forecast of Deep-Coalbed-Methane Wells Based on Long Short-Term Memory and Bayesian Optimization

Study on the Impact of Microscopic Pore Structure Characteristics in Tight Sandstone on Microscopic Remaining Oil after Polymer Flooding

Contact Info

Product

Resources

About