A Machine Learning Based Accelerated Approach to Infer the Breakdown Pressure of the Tight Rocks

Abstract

Unconventional oil reservoirs are usually classified by extremely low porosity and permeability values. The most economical way to produce hydrocarbons from such reservoirs is by creating artificially induced fractures. To design the hydraulic fracturing jobs, true values of rock breakdown pressure is required. Conducting hydraulic fracturing experiments in the laboratory is a very expensive and time consuming process. Therefore, in this study, different machine learning models were efficiently utilized to predict the breakdown pressure of the tight rocks. In the first part of the study, a comprehensive hydraulic fracturing experimental study was conducted on various rock specimens, to measure the breakdown pressure. A total of 130 experiments were conducted on different rock types such as shales, sandstone, tight carbonates, and synthetic cement samples. Rock mechanical properties such as Young's Modulus E, Poisson's ratio, Unconfined Compressive strength (UCS), and indirect tensile strength sigma_t were measured before conducting hydraulic fracturing tests. Machine learning models were used to correlate the breakdown pressure of the rock as a function of fracturing experimental conditions and rock properties. In the machine learning model, we considered experimental conditions including injection rate, overburden pressures, and fracturing fluid viscosity, and rock properties including Young's Modulus, Poisson's ratio, Unconfined Compressive strength (UCS), and indirect tensile strength, porosity, permeability, and bulk density. Machine learning models include Random Forest (RF), Decision Trees (DT), and K-Nearest Neighbor (KNN). During training of ML models, the model hyper-parameters were optimized by grid search optimization approach. With the optimal setting of the ML models, the breakdown pressure of the unconventional formation were predicted with an accuracy of 95%. The proposed methodology to predict the breakdown pressure of unconventional rocks can minimize the laboratory experimental cost of measuring fracture parameters and can be used as a quick assessment tool to evaluate the development prospect of unconventional tight rocks.

Machine Learning in Reservoir Engineering: A Review

“…The challenge of integrating petroleum engineering and machine learning. Currently, most studies use machine learning as a simple tool to address issues in petroleum engineering [8,13,48], and there is hardly any research that combines the two disciplines. Researchers credit the increase in oil rate to the petroleum engineering technology itself, without realizing that machine learning can uncover hidden knowledge, which may lead to new discoveries in petroleum engineering that are hard to achieve with current technology.…”

“…However, obtaining this parameter experimentally is time-consuming and expensive. A machine learning model is constructed by using the Random Forest (RF), Decision Tree (DT) and K Nearest Neighbor (KNN) methods, taking into account experimental conditions such as injection rate, overburden pressure, and fracturing fluid viscosity, as well as some of the key features needed to calculate the breakdown pressure of the rock [8,9]. After optimizing the model parameters using the grid search optimization method, the breakdown pressure prediction accuracy of unconventional formations is 95% [10].…”