Multi-task learning for virtual flow metering

TL;DR

This paper introduces a multi-task learning approach for virtual flow metering that enhances robustness and reduces error rates across multiple oil and gas wells, outperforming traditional single-task models.

Contribution

The paper presents a novel multi-task learning architecture for data-driven virtual flow metering, enabling cross-well learning and improved robustness over existing methods.

Findings

MTL improves robustness over single-task models.

MTL reduces error by 25-50% on challenging assets.

Model tested on 55 wells from four petroleum assets.

Abstract

Virtual flow metering (VFM) is a cost-effective and non-intrusive technology for inferring multiphase flow rates in petroleum assets. Inferences about flow rates are fundamental to decision support systems that operators extensively rely on. Data-driven VFM, where mechanistic models are replaced with machine learning models, has recently gained attention due to its promise of lower maintenance costs. While excellent performances in small sample studies have been reported in the literature, there is still considerable doubt about the robustness of data-driven VFM. In this paper, we propose a new multi-task learning (MTL) architecture for data-driven VFM. Our method differs from previous methods in that it enables learning across oil and gas wells. We study the method by modeling 55 wells from four petroleum assets and compare the results with two single-task baseline models. Our findings show that MTL improves robustness over single-task methods, without sacrificing performance. MTL yields a 25-50% error reduction on average for the assets where single-task architectures are struggling.