Waterflood is well-known as the cost effective secondary recovery mechanism to improve oil recovery. With current challenging oil price environment, waterflood continues to be one of the main candidate of choice. Hence, it is very important to maximize by optimizing the process. The objective of this paper is to propose a rapid technique to evaluate and optimize current matured waterflooding project in an offshore brown field with complex stacked reservoirs and production system through dynamic data analyses. Interwell connectivity evaluation can assist in reservoir characterization, well placement, and evaluate waterflooding performance. Therefore, dynamic data analytics workflow applying interwell connectivity evaluation and Streamline as implicit approach are proposed. The importance of clustering each area become important to raise particular issues such as poor properties and connectivity. The production and injection points are evaluated and unswept area can be identified. Therefore, waterflood can be optimized. This study resulted if current waterflooding can be optimized and new potential well placement can be identified to increase oil recovery. Compared with no further action case, oil recovery can be potentially improved 3-4% based on numerical full-field modelling prediction. The technique will be very useful to have business decision rapidly in weeks. With current oil price situation, it can be as a cost-effective technique, especially for brown fields with mature waterflood projects and have complexity in geological and production system that commonly time consumption. The proposed workflow can be deployed to other neighbor mature fields.
The numbers of machine learning technologies used in subsurface characterization work is increasing with more company rely on data driven to assist in performing any evaluation. In this study, a supervised random forest machine learning approach was utilized in two stages; first stage was to predict static reservoir using well logs and core as inputs. The output is then used as the basis in the second stage to predict initial oil rate (Qi) and subsequently to determine estimated ultimate recovery (EUR) at targeted interval as proposed in the first stage. Static reservoir machine learning prediction outputs were benchmark with available routine core analysis with the result showed R2 of 88% respectively. For initial oil rate (Qi) prediction, a total of 9000 observation points from 20 wells were extracted for training and blind testing process by using variables such as permeability, net thickness, well choke size, well flowing pressure, average pressure, water cut, irreducible water saturation (Swi), and historical production rate. The estimated ultimate recovery (EUR) is then predicted utilizing the thickness of that unit and the decline rate that is obtained from the neighboring wells that has produced from the said reservoir as the analogue. The Qi and EUR results from machine learning is compared with the estimated Qi and EUR using conventional methods for verification purpose. The results from machine learning dynamic properties prediction showed 97% R2 for training while the testing score mean is 87% against the historical data. High R2 from static and dynamic machine learning prediction indicated that the method was reliable and able to assist petroleum engineer in reservoir potential evaluation process.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.