The Successful Prediction of Waterflooding Using a Feed-Forward Algorithm

Waterflooding is one of the most frequently used Enhanced Oil Recovery (EOR) methods to increase oil recovery because it can increase 30% -60% of total production. It is necessary to apply a production system performance prediction approach to minimize uncertainty in increasing production figures, s...

Full description

Saved in:
Bibliographic Details
Main Authors: Qunazatul Shima Batubara*, Tomi Erfando
Format: Article
Language:English
Published: Syiah Kuala University 2023-08-01
Series:Aceh International Journal of Science and Technology
Subjects:
Online Access:https://jurnal.usk.ac.id/AIJST/article/view/30813
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849243032693506048
author Qunazatul Shima Batubara*
Tomi Erfando
author_facet Qunazatul Shima Batubara*
Tomi Erfando
author_sort Qunazatul Shima Batubara*
collection DOAJ
description Waterflooding is one of the most frequently used Enhanced Oil Recovery (EOR) methods to increase oil recovery because it can increase 30% -60% of total production. It is necessary to apply a production system performance prediction approach to minimize uncertainty in increasing production figures, such as analytical and numerical methods. Artificial Intelligence in oil and gas is not new, but it has often been used in various fields such as exploration, drilling, production, and reservoirs. This is the basis for the Prediction of the success of waterflooding research carried out. This research aimed to predict the success rate of waterflooding using an Artificial Neural Network (ANN). The method used in this study is the simulation research method using CMG Imex for reservoir simulation modeling, running CMG CMOST for 500 sensitivity data with the input of seven parameters of compressibility, horizontal permeability, vertical permeability, pressure injection, injection rate, thickness, oil saturation, and the output is recovery factor using Artificial Neural Network (ANN) with a ratio of 70% of calculation model results for training and 30% model results for testing. In order to get optimal prediction results, trial, and error were carried out on the number of hidden layer nodes so that optimal and stable hidden layer nodes were obtained at node 10 with RMSE values of 0.339035 for training and 0.442663 for testing and MAPE for training 1.15% and 1.62% for testing. The statistical analysis value is 0.906139 for training and 0.899525 for testing data. It can be concluded from this study that the use of ANN in predictions using ten hidden layer nodes proved to be very good and successful, and predictions in this study were classified as highly accurate Predictions.
format Article
id doaj-art-98ee6e18bc5f48c7b5837bd090b89558
institution Kabale University
issn 2088-9860
language English
publishDate 2023-08-01
publisher Syiah Kuala University
record_format Article
series Aceh International Journal of Science and Technology
spelling doaj-art-98ee6e18bc5f48c7b5837bd090b895582025-08-20T03:59:37ZengSyiah Kuala UniversityAceh International Journal of Science and Technology2088-98602023-08-0112218819610.13170/aijst.12.2.3081316489The Successful Prediction of Waterflooding Using a Feed-Forward AlgorithmQunazatul Shima Batubara*0Tomi Erfando1Universitas Islam RiauUniversitas Islam RiauWaterflooding is one of the most frequently used Enhanced Oil Recovery (EOR) methods to increase oil recovery because it can increase 30% -60% of total production. It is necessary to apply a production system performance prediction approach to minimize uncertainty in increasing production figures, such as analytical and numerical methods. Artificial Intelligence in oil and gas is not new, but it has often been used in various fields such as exploration, drilling, production, and reservoirs. This is the basis for the Prediction of the success of waterflooding research carried out. This research aimed to predict the success rate of waterflooding using an Artificial Neural Network (ANN). The method used in this study is the simulation research method using CMG Imex for reservoir simulation modeling, running CMG CMOST for 500 sensitivity data with the input of seven parameters of compressibility, horizontal permeability, vertical permeability, pressure injection, injection rate, thickness, oil saturation, and the output is recovery factor using Artificial Neural Network (ANN) with a ratio of 70% of calculation model results for training and 30% model results for testing. In order to get optimal prediction results, trial, and error were carried out on the number of hidden layer nodes so that optimal and stable hidden layer nodes were obtained at node 10 with RMSE values of 0.339035 for training and 0.442663 for testing and MAPE for training 1.15% and 1.62% for testing. The statistical analysis value is 0.906139 for training and 0.899525 for testing data. It can be concluded from this study that the use of ANN in predictions using ten hidden layer nodes proved to be very good and successful, and predictions in this study were classified as highly accurate Predictions.https://jurnal.usk.ac.id/AIJST/article/view/30813waterfloodingartificial intelligenceartificial neural network (ann)feedforward
spellingShingle Qunazatul Shima Batubara*
Tomi Erfando
The Successful Prediction of Waterflooding Using a Feed-Forward Algorithm
Aceh International Journal of Science and Technology
waterflooding
artificial intelligence
artificial neural network (ann)
feedforward
title The Successful Prediction of Waterflooding Using a Feed-Forward Algorithm
title_full The Successful Prediction of Waterflooding Using a Feed-Forward Algorithm
title_fullStr The Successful Prediction of Waterflooding Using a Feed-Forward Algorithm
title_full_unstemmed The Successful Prediction of Waterflooding Using a Feed-Forward Algorithm
title_short The Successful Prediction of Waterflooding Using a Feed-Forward Algorithm
title_sort successful prediction of waterflooding using a feed forward algorithm
topic waterflooding
artificial intelligence
artificial neural network (ann)
feedforward
url https://jurnal.usk.ac.id/AIJST/article/view/30813
work_keys_str_mv AT qunazatulshimabatubara thesuccessfulpredictionofwaterfloodingusingafeedforwardalgorithm
AT tomierfando thesuccessfulpredictionofwaterfloodingusingafeedforwardalgorithm
AT qunazatulshimabatubara successfulpredictionofwaterfloodingusingafeedforwardalgorithm
AT tomierfando successfulpredictionofwaterfloodingusingafeedforwardalgorithm