Machine Learning Applied to Multiwell-Test Analysis and Flow-Rate Reconstruction

Abstract

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 175059, “Machine Learning Applied to Multiwell-Test Analysis and Flow- Rate Reconstruction,” by Chuan Tian and Roland N. Horne, Stanford University, prepared for the 2015 SPE Annual Technical Conference and Exhibition, Houston, 28–30 September. The paper has not been peer reviewed. Permanent downhole gauges (PDGs) can provide a continuous record of flow rate and pressure, which provides extensive information about the reservoir and makes PDG data a valuable source for reservoir analysis. In previous work, it has been shown that kernel-ridge regression-based machine learning is a promising tool to interpret pressure transients from a single PDG. In this work, the machine-learning framework was extended to two applications: multiwell testing and flow-rate reconstruction. Introduction Analysis of PDG data is challenging because of the inherent characteristics of the data, including continuously variable flow rate, noise, and the large data volume. Until now, most efforts in PDG-data analysis have been concentrated on pressure-transient analysis on single wells, although there have also been some studies on temperature-transient analysis and multiwall-data analysis. Recently, however, there have been some attempts to apply machine-learning techniques for PDG-data analysis. The fundamental idea is to learn the patterns behind PDG data, where the patterns contain the reservoir information implicitly. A previous study on single-well pressure analysis showed that machine learning has the potential to handle the complexities in PDG-data analysis, and learn the reservoir model successfully. In this work, the authors use machine learning as the tool for investigation, but address two different problems—namely, multiwell testing (multiwell pressure-transient analysis) and flow-rate reconstruction. Both topics are important in PDG-data analysis in practical engineering. The authors have developed a machine-learning model for each problem and have tested the models on different real and synthetic data sets. The test results validated the developed approach, and illustrated the flexibility of the machine-learning framework for different applications by adapting the features and the targets. Problem Statement. On the basis of the background information and literature review, the objectives of this research were to Extend the machine-learning framework for pressure analysis on a single well to multiwell systems. The framework should capture the well interference accurately and be able to test a greater area of the reservoir. Develop a machine-learning model to reconstruct the flow-rate history by use of pressure data. Ensure that both models maintain the advantages of the machine-learning- based single-well pressure interpretation in terms of the accuracy of prediction, computational efficiency, and tolerance to noise. A review of methodologies, including machine-learning concepts (linear regression, kernel method, and model regularization), multiwell testing, and flowrate reconstruction, is provided in the complete paper.