Forecasting Dead Oil Viscosity Using Machine Learning Processes for Niger Delta Region
Journal Title: International Journal of Current Science Research and Review - Year 2024, Vol 7, Issue 01
Abstract
Prediction of Dead oil viscosity using experimental measurements is highly exorbitant and time consuming, hence the use of forecasting models. Dead oil viscosity is a very important PVT parameter that solve numerous reservoir engineering problems and one of the most required factors for enhanced oil recovery processes. This study utilized two machine learning algorithms of Artificial Neural Network (ANN) and Support Vector Machine (SVM) to predict dead oil viscosity. A total number of 243 data set was obtained from PVT report from Niger-Delta, out of which, 70% were used to train the models, 15% for testing and 15% for validation. Quantitative and qualitative analysis was carried out to compare the performance and reliability of the new developed machine learning models with some selected empirical correlations. The result revealed that the Artificial Neural Network Outperformed Support Vector Machine (SVM) as well as common dead oil viscosity empirical correlations with the best rank of 0.144, highest correlation coefficient of 0.984, Mean Absolute Error (Ea) of 0.205, with a better performance plot, followed by Support Vector Machine model with correlation coefficient of 0.926, Mean Absolute Error (Ea) of 0.199 and the rank of 0.176. The new developed Artificial Neural Network model can potentially replace the empirical models for dead oil viscosity predictions for Niger Delta region.
Authors and Affiliations
Origbo, Oghenechovwe Augustine, Mbachu Ijeoma Irene,
Keywords
Related Articles
- EP ID EP729700
- DOI 10.47191/ijcsrr/V7-i1-81
- Views 64
- Downloads 0
The Determination of Maximum Flow Rate in Well X Layer Y Field Z
The field development target which usually in field X are mostly carried out in gas reservoirs over time, in several candidate wells gas reserves have started to run low so that the remaining oil reserves and pressure in...
Improving Students’ Reading Comprehension by Using Integrated Multimedia in MAN 1 Bandar Lampung
This study examined the impact of integrated multimedia instruction on students’ reading comprehension achievement compared with the traditional print-based instruction. This research applied a quasi-experimental design...
Perspectives of Teaching and Evaluation in Mathematics
Mathematics as a subject is quite unique in its processes and teaching in that it requires the least amount of memorization. Aside from the numbers and the functions of the operators themselves, not much needs to be memo...
Proposed Marketing Strategy to Increase Sales in Indonesia Private Hospitals
The study explores marketing strategies for increasing sales of oncology-based medical equipment in private hospitals in Indonesia. Using qualitative methods, the research analyzes internal and external factors influenci...
Deciding Financial Problem Solution for a Construction Company using Fault Tree Analysis (FTA) and Fuzzy Analytic Hierarchy Process (Fuzzy AHP)
PT X is a construction company with clients spread among Central Java, West Java, Papua, Kalimantan, and Sulawesi. This company experienced financial problem and with the absence of financial bookkeeping, the financial i...