Workflow for Predicting Undersaturated Oil Viscosity using Machine Learning
Undersaturated oil viscosity is a dominant fluid parameter to be measured in oil reservoirs due to its direct involvement in flow calculations. Since PVT experimental work is expensive and time costly, prediction methods are essential. This work presents the utilization of viscosity data from more than five hundred fluid reports with the purpose of developing data driven models to predict undersaturated oil viscosity using easy-to-get measurements. The suitability of popular machine learning techniques in performing this task is also examined by comparing the models obtained for each method using several popular statistical metrics. A complete workflow for this process is introduced to demonstrate the integrity of the process followed and to guide in further research in predicting similar PVT properties.The workflow showcases the advantages of combining engineers expertise to the art of data driven models developement, specifically on accuracy and ease of implementation, as well as their limitations.
Copyright (c) 2023 Sofianos Panagiotis Fotias, Vassilis Gaganis
This work is licensed under a Creative Commons Attribution 4.0 International License.