Machine learning based reservoir characterization and numerical modeling from integrated well log and core data

Koray, Abdul-Muaizz; Bui, Dung; Kubi, Emmanuel Appiah; Ampomah, William; Amosu, Adewale

doi:10.1016/j.geoen.2024.213296

Cited by 2 publications

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Predicting Photoelectric Logs in Challenging Conditions Using Machine Learning and Statistical Analysis

Abdullah,

AlYami

2024

SPE Caspian Technical Conference and Exhibition

View full text Add to dashboard Cite

The photoelectric (PEF) log measures the photoelectric absorption factor, pivotal for determining rock matrix properties. High absorption factor values are typical in limestones, dolomites, clay, iron-bearing minerals, and heavy minerals, whereas sandstones exhibit lower values. In this study, actual photoelectric logs were gathered from the field alongside various other logs such as gallons per minute (GPM), standpipe pressure (SPP), rate of penetration (ROP), and bulk density (RHOB). Utilizing a suite of machine learning regression techniques—ridge regression, linear regression, support vector machines (SVM), polynomial regression, random forest, and decision tree—this research aimed to predict the photoelectric logs using porosity and other log data as inputs. The effectiveness of these models was confirmed through their strong predictive accuracy relative to actual log values. The ensemble of regression models demonstrated significant correlation coefficients and low root mean square errors, illustrating their robust capability to predict photoelectric data at various depths based on available drilling data.

show abstract

Predicting Photoelectric Logs in Challenging Conditions Using Machine Learning and Statistical Analysis

Abdullah,

AlYami

2024

SPE Caspian Technical Conference and Exhibition

View full text Add to dashboard Cite

show abstract

A Comparison of Water Flooding and CO2-EOR Strategies for the Optimization of Oil Recovery: A Case Study of a Highly Heterogeneous Sandstone Formation

Bui,

Nguyen,

Ampomah

et al. 2024

Gases

View full text Add to dashboard Cite

This study presents a comparative analysis of CO2-EOR and water flooding scenarios to optimize oil recovery in a geologically heterogeneous reservoir with a dome structure and partial aquifer support. Using production data from twelve production and three monitoring wells, a dynamic reservoir model was built and successfully history-matched with a 1% deviation from actual field data. Three main recovery methods were evaluated: water flooding, continuous CO2 injection, and water-alternating-gas (WAG) injection. Water flooding resulted in a four-fold increase from primary recovery, while continuous CO2 injection provided up to 40% additional oil recovery compared to water flooding. WAG injection further increased recovery by 20% following water flooding. The minimum miscibility pressure (MMP) was determined using a 1D slim-tube simulation to ensure effective CO2 performance. A sensitivity analysis on CO2/WAG ratios (1:1, 2:1, 3:1) revealed that continuous CO2 injection, particularly in high permeability zones, offered the most efficient recovery. An economic evaluation indicated that the optimal development strategy is 15 years of water flooding followed by 15 years of continuous CO2 injection, resulting in a net present value (NPV) of USD 1 billion. This study highlights the benefits of CO2-EOR for maximizing oil recovery and suggests further work on hybrid EOR techniques and carbon sequestration in depleted reservoirs.

show abstract

Machine learning based reservoir characterization and numerical modeling from integrated well log and core data

Cited by 2 publications

References 38 publications

Predicting Photoelectric Logs in Challenging Conditions Using Machine Learning and Statistical Analysis

Predicting Photoelectric Logs in Challenging Conditions Using Machine Learning and Statistical Analysis

A Comparison of Water Flooding and CO2-EOR Strategies for the Optimization of Oil Recovery: A Case Study of a Highly Heterogeneous Sandstone Formation

Contact Info

Product

Resources

About