Optimizing acidizing design and effectiveness assessment with machine learning for predicting post-acidizing permeability

Abstract

Formation damage poses a widespread challenge in the oil and gas industry, leading to diminished permeability, flow rates, and overall well productivity. Acidizing is a commonly employed technique aimed at mitigating damage and enhancing permeability. In this study, to predict the permeability after acidizing in oil and gas reservoirs, three machine learning models, namely artificial neural networks, random forest, and XGBoost, along with genetic programming were used to estimate permeability changes after acidizing. These models are utilized to estimate permeability changes following acidizing operations. Training of the models involved a dataset comprising 218 acidizing operations conducted in diverse reservoirs across Iran. The input parameters, namely permeability, porosity, skin factor, calcite mineral fraction, acid injection rate, and injected acid volume, were optimized through the use of a genetic algorithm. Statistical and graphical analysis of the results demonstrates that genetic programming outperformed the other machine learning techniques, yielding superior performance with R square and RMSE values of 0.82 and 17.65, respectively. Nevertheless, the other models also exhibited commendable performance, surpassing an R square value of 0.73. The post-acidizing permeability data obtained from core flooding experiments conducted on carbonate and sandstone cores was utilized to validate the models. The genetic programming model demonstrates an average error of 21.1%. The evaluation of post-acidizing permeability using genetic programming, in comparison with the results obtained from the core-flood test, revealed errors of 22.95% and 32.4% for carbonate and sandstone cores, respectively. Furthermore, a comparison between the calculated post-acidizing permeability derived from the GP model and previous studies indicated errors within the range of 8.6–26.59%. The findings highlight the potential of genetic programming and machine learning algorithms in accurately predicting post-acidizing permeability, thereby aiding in acidizing design, effectiveness assessment, and ultimately enhancing oil and gas production rates.

Machine learning approaches for estimating interfacial tension between oil/gas and oil/water systems: a performance analysis

“…The normalization process is done by subtracting the minimum value of each index from its actual value, then dividing the result by the range (maximum value minus minimum value) of that index. Normalizing data makes it easier to compare indicators with different units or magnitudes and also helps to speed up the training process 20 , 42 , 46 , 47 . In the exploration of data preparation techniques, the inclusion of tangible examples significantly improves the reader’s understanding of normalization methods.…”

“…Machine learning is a branch of artificial intelligence that enables computers to learn from data without explicit programming. Machine learning algorithms can discover complex patterns and relationships in data, as well as make predictions based on new data 20 – 22 .…”

Sandstone chemical consolidation and wettability improvement using furan polymer-based nanofluid

“…The control of reservoir production rates strongly depends on the permeability of the reservoir rock which indicates the rock capacity to allow fluid to flow through its pores and channels 35 , 36 . Determining the extent of permeability reduction due to the infiltration of chemical fluids in the vicinity of the wellhead is of paramount importance in chemical consolidation procedures, as this determination aids in optimizing the chemical composition of the consolidation agent which is essential for controlling sand production, limiting permeability reduction, and minimizing formation damage.…”

A comprehensive analysis of carbonate matrix acidizing using viscoelastic diverting acid system in a gas field

“…The acid system serves to dissolve formation damage or create new flow channels, ultimately increasing the permeability of the wellbore region. Matrix acidizing, a specific application, targets pressure loss reduction and production rate increase 5 . This method aims to eliminate or prevent damaged zones near the wellbore 6 , 7 .…”