Innovative Solutions For Oil Well Monitoring - Data-Driven Multiphase Virtual Flow Metering Using Ensemble Machine Learning And Historical Field Data

Aug 5, 2026

Upload by Rowan

This paper introduces a data-driven multphase virtual flow meter (DD-MVFM) that estimates oil, gas, and water flow rates and supports real-time monitoring and future production prediction using ensemble machine-learning methods and historical portable well test reports. The approach reuses existing wellhead hardware signals (temperature and pressure) and is designed for verification of multiphase physical flow meters, redundancy during maintenance, and standalone replacement to reduce operating cost and infrastructure needs. Results report about 85% performance, with further gains expected from expanded field data.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Multiphase metering challenges

Test separators and limitations

MPFM technology and drawbacks

Empirical formulas and motivation

Journal of Applied Science and Engineering, Vol. 28, No 12, Page 2427-2438 2427 Innovative Solutions For Oil Well Monitoring: Data-Driven Multiphase Virtual Flow Metering Using Ensemble Machine Learning And Historical Field Data Wael A. Farag1*, Hussein H. Ismail2, and Muhammad Nadeem2 1 Electrical Power Engineering Dept., Cairo University, Giza, Egypt 2 College of Engineering and Technology, American University of the Middle East, Kuwait *Corresponding author. E-mail: [wael.farag@cu.edu.eg](wael.farag@cu.edu.eg)[ ](wael.farag@cu.edu.eg)[Received: Mar](Received: Mar). 05, 2024; Accepted: Feb. 25, 2025 By combining data-driven ensemble machine-learning algorithms and historical oil field portable test reports, this paper proposes a Data-Drive Multiphase Virtual Flow Meter (DD-MVFM) that estimates oil, gas, and water flow rates and provides real-time monitoring, and predicts future production with appropriate accuracy. The proposed DD − MVFM utilizes the existing hardware used for measurements of basic variables such as temperature, and pressure at different locations at the well-head structure. The DD − MVFM can be employed in three ways. The first way is to be used as a verification tool for multiphase physical flow meters (MPFMs), making sure they are working properly and increasing confidence in the collected readings. The second way is to use the DD − MVFM as a redundant tool when the MPFMs are not available or going through maintenance. The third way, which is the main objective of our research, is to employ the proposed DD MVFM as a standalone for the complete replacement of current and future MPFM installments. This, significantly lowers the operating cost, reducing the required portable field tests, and saving the need to build a major infrastructure for the set-up of MPFMs for new oil wells. Consequently, this contributes to the ambitious goal of reducing CO2 emissions. The development of the DD − MVFM encompasses the fusion of multiple data wrangling and machine learning algorithms to achieve the required performance. The testing results of the proposed DD − MVFM and the prediction experiments show that it successfully achieved a performance of 85% . These results will be significantly improved in the future after incorporating more data from the previous and coming field test reports. Keywords: Oil; Gas; Water Cut; GOR; Virtual Meter; Machine Learning; Ensemble Training © The Author(’s) . This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. [http://dx.doi.org/10.6180/jase.202512_28](http://dx.doi.org/10.6180/jase.202512_28)(12).0010 1. Introduction The extracted fluid in oil wells and reserves is often a multiphase mixture (oil, gas, and water) . Metering this combination is challenging, especially when the gas-oil ratio (GOR) and water cut (WC) are high [1] . Precise measurements of the well’s oil output are critical for evaluating well performance [2] . Its significance may be seen in a variety of applications, including oil recovery estimates, reservoir performance measurement, and surface facility pipe design. As a result, reservoir geologists and engineers are always seeking methods to enhance the forecast of oil rates per well based on choke performance [3] . In a typical oil-and-gas production field, many wells are normally linked to a processing plant by flowlines. The flowlines transport the generated fluids, which are frequently multiphased (Oil, gas, and water) [4] . Nevertheless, it is imperative to consider the fluid production of each designated phase for every individual well to opti- 2428 Wael A. Farag et al. mize production effectively. Historically, test separators are often regarded as the most reliable and accurate way of well testing [5] . The volume of the produced fluid is s

FAQs

What does the proposed DD-MVFM estimate and enable for oil well operations?

It estimates oil, gas, and water flow rates, supports real-time monitoring, and predicts future production with appropriate accuracy using historical field test data and ensemble learning.

How is the DD-MVFM implemented using existing measurement hardware?

It uses the existing wellhead measurement setup, relying on recorded basic variables such as temperature and pressure at different wellhead locations.

In what three ways can the DD-MVFM be used in practice?

It can verify multiphase physical flow meters, act as a redundant tool when MPFMs are unavailable or under maintenance, and serve as a standalone replacement for current and future MPFM installations.

Aug 5, 2026

Upload by Rowan