Inverse analysis of hydraulic fracturing tests based on artificial intelligence techniques

Abstract

In the last decades, the study of fluid flow through discontinuities such as fractures has received significant attention from the petroleum industry owing to the discovery of naturally fractured reservoirs. Predicting the behavior of this type of reservoir is challenging and includes, as a crucial step, determining its geomechanical parameters. Several in situ tests and empirical relationships have been established to estimate these parameters. Nevertheless, these procedures have important limitations. This work proposes an artificial intelligence-based methodology to identify geomechanical parameters from borehole injection pressure curves obtained during hydraulic fracturing tests. This methodology applies a genetic algorithm to minimize the sum of squared differences between the observed and predicted borehole pressure curves. Furthermore, an artificial neural network is adopted to build a proxy model that substitutes hydraulic fracturing numerical simulations, substantially reducing computational time. A proper recursive strategy is adopted to predict the borehole pressure curves.Additionally, a hyperparameter tuning technique selects appropriate neural network hyperparameters based on the multistep-ahead prediction error. Finally, the framework is applied in a KGD problem that models hydraulic fracture propagation. The benchmark confirms the capability of the proposed methodology to identify geomechanical parameters from fracturing tests.

Parameter identification of minifrac numerical tests using a gradient boosting‐based proxy model and genetic algorithm

“…This paper enhances the approach by Abreu et al, 31 proposing a fully automated methodology to identify hydromechanical parameters for finite element simulations of field-measured minifrac experiments. Notably, this methodology also provides helpful information about the importance of each parameter in numerical simulations.…”

“…This paper proposes a novel formulation for this function that aligns with multistep-ahead prediction. This work adopts the real-coded genetic algorithm implemented by Abreu et al 31 to identify hydromechanical parameters, solving problem (1).…”

“…Comparably, Zhao et al 30 proposed an inverse analysis approach based on the support vector machine and Bayesian theory to estimate hydraulic fracturing parameters and their associated uncertainty. Focusing on a synthetic model for a proof of concept, Abreu et al 31 proposed an artificial intelligence-based methodology to identify hydraulic fracturing parameters. Their approach integrated a genetic algorithm and a multilayer perceptron to model borehole pressure curves as time series.…”

Current Status and Prospects of Artificial Intelligence Technology Application in Oil and Gas Field Development

“…63 The goal is to develop more scientific development plans to improve the speed and recovery rate of oil and gas extraction. 64 The future reliable intelligent oil and gas field development plan will be widely applied. 65 Currently, the construction of intelligent oil and gas fields is developing rapidly, 66 but overall it is in the initial stage of exploration.…”

“…Through the intelligent application of multiple links such as dynamic analysis of oil and gas reservoirs, intelligent historical fitting, numerical simulation models, and optimization of production plans, the state of oil and gas can be described more accurately . The goal is to develop more scientific development plans to improve the speed and recovery rate of oil and gas extraction . The future reliable intelligent oil and gas field development plan will be widely applied …”