Optimization of ionic concentrations in engineered water injection in carbonate reservoir through ANN and FGA

Reginato, Leonardo Fonseca; Pedroni, Lucas G.; Compan, André Luiz Martins; Skinner, Rodrigo; Sampaio, Misako U.

doi:10.2516/ogst/2020094

Cited by 4 publications

(17 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The works that have investigated injection define three ions (SO4 2-, Ca 2+ , and Mg 2+ ) as the principal agents for changes to a more hydrophilic rock condition. Sulfate is the wettability modifying agent in carbonates, and the other two divalent cations (calcium and magnesium), promote strong interactions with the oil components (ADEGBITE et al, 2018;REGINATO et al, 2021;STRAND et al, 2006;YOUSEF et al, 2012).…”

Section: Methods Of Lswi/ewimentioning

confidence: 99%

“…Then, the complete data frame is divided into 3 parts following the labels assigned in the clustering phase. In this stage, we selected the artificial neural networks (ANNs) of the Multi-Layer Perceptron (MPL) type also from Scikit-learn, being able to make a performance comparison with the solution proposed by Reginato et al (2021). Three of this ANN was trained using one of the three new corresponding datasets (Figure 16).…”

Section: Hybrid Machine Learning Methodsmentioning

confidence: 99%

“…Finally, with a total of 1500 simulated cases, we started the phase of structuring and cleaning the dataset. We adapted the methodology using templates to generate synthetic EWI data from Reginato et al (2021). However, we added the variables of formation water salinity and mineralogical content in the initial geochemical modeling.…”

Section: Data Collectionmentioning

confidence: 99%

“…This module works by recursively adjusting the Kr of a model with common waterflooding until yield results like the corresponding case with EWI (Figure 15). KrModule is a solution developed by Reginato et al (2021) and adapted for this work.…”

Section: Krmodule Proceduresmentioning

confidence: 99%

“…That operational limits were used in the optimization phase (Table 9). For better performance, we used a reduced model of Unisim-II, the same one used for Reginato et al (2021). This part of the model has 6x6x30 cells in a representative field location.…”

Section: Unisim-ii Benchmarkmentioning

confidence: 99%

See 4 more Smart Citations

Application of machine learning techniques for modeling of relative permeability in engineered water injection in carbonate reservoirs.

Reginato¹

Self Cite

View full text Add to dashboard Cite

Numerical modeling of advanced production methods is always a challenge to be developed and applied in reservoir simulation. Some approaches, such as the use of laboratory experiments, arise to make this modeling feasible. However, this limits the speed of the solution to obtaining laboratory data and impairs its reproducibility. With the increasing use of Machine Learning (ML) tools to solve complex non-linear problems, we conducted these studies to train these ML tools and couple them to commercial simulation software. The training was based on parameters relevant to Engineered Water Injection (EWI). This advanced injection method seeks to use salinity control in the injection water to promote iterations between its ions and the rock minerals, to facilitate its flow into the porous medium. Thus, we structured a dataset containing salinity, mineralogy, and relative permeability data for the data-driven ML tool to learn the behavior of this data.Thus, this approach achieves accurate predictions, which were used as input data during injection modeling and simulation, validating its results by comparing with production simulation by conventional geochemical modeling. Finally, we performed optimizations with waterflooding injection and EWI, coupling the optimization with the advanced method of the ML pipeline. Thus, we test the efficiency of the ML approach with recursive simulations and compare the efficiency between the injection methods. For this, we apply these optimizations to the UNISIM-II benchmark, a reservoir model with characteristics based on Brazilian Pre-Salt fields. The objective function was Net Present Value maximization, which for the tests performed, EWI presented higher profit, even with a cost margin up to 300% higher than the cost of waterflooding.

show abstract

Section: Methods Of Lswi/ewimentioning

confidence: 99%

Section: Hybrid Machine Learning Methodsmentioning

confidence: 99%

Section: Data Collectionmentioning

confidence: 99%

Section: Krmodule Proceduresmentioning

confidence: 99%

Section: Unisim-ii Benchmarkmentioning

confidence: 99%

See 3 more Smart Citations

Application of machine learning techniques for modeling of relative permeability in engineered water injection in carbonate reservoirs.

Reginato¹

Self Cite

View full text Add to dashboard Cite

show abstract

Modeling alterations in relative permeability curves due to salinity using artificial neural networks

Czarnobay,

Lamas,

Sebrão

et al. 2024

Comput Geosci

View full text Add to dashboard Cite

Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection

2023

Self Cite

View full text Add to dashboard Cite

Advanced production methods utilize complex fluid iteration mechanisms to provide benefits in their implementation. However, modeling these effects with efficiency or accuracy is always a challenge. Machine Learning (ML) applications, which are fundamentally data-driven, can play a crucial role in this context. Therefore, in this study, we applied a Hybrid Machine Learning (HML) solution to predict petrophysical behaviors during Engineered Water Injection (EWI). This hybrid approach utilizes K-Means and Artificial Neural Network algorithms to predict petrophysical behaviors during EWI. In addition, we applied an optimization process to maximize the Net Present Value (NPV) of a case study, and the results demonstrate that the HML approach outperforms conventional methods by increasing oil production (7.3%) while decreasing the amount of water injected and produced (by 28% and 40%, respectively). Even when the injection price is higher, this method remains profitable. Therefore, our study highlights the potential benefits of utilizing HML solutions for predicting petrophysical behaviors during EWI. This approach can significantly improve the accuracy and efficiency of modeling advanced production methods, which may help the profitability of new and mature oil fields.

show abstract

Optimization of ionic concentrations in engineered water injection in carbonate reservoir through ANN and FGA

Cited by 4 publications

References 39 publications

Application of machine learning techniques for modeling of relative permeability in engineered water injection in carbonate reservoirs.

Application of machine learning techniques for modeling of relative permeability in engineered water injection in carbonate reservoirs.

Modeling alterations in relative permeability curves due to salinity using artificial neural networks

Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection

Contact Info

Product

Resources

About