Hyperparameter Tuning of Artificial Neural Networks for Well Production Estimation Considering the Uncertainty in Initialized Parameters

Abstract

A well production rate is an essential parameter in oil and gas field development. Traditional models have limitations for the well production rate estimation, e.g., numerical simulations are computation-expensive, and empirical models are based on oversimplified assumptions. An artificial neural network (ANN) is an artificial intelligence method commonly used in regression problems. This work aims to apply an ANN model to estimate the oil production rate (OPR), water oil ratio (WOR), and gas oil ratio (GOR). Specifically, data analysis was first performed to select the appropriate well operation parameters for OPR, WOR, and GOR. Different ANN hyperparameters (network, training function, and transfer function) were then evaluated to determine the optimal ANN setting. Transfer function groups were further analyzed to determine the best combination of transfer functions in the hidden layers. In addition, this study adopted the relative root mean square error with the statistical parameters from a stochastic point of view to select the optimal transfer functions. The optimal ANN model’s average relative root mean square error reached 6.8% for OPR, 18.0% for WOR, and 1.98% for GOR, which indicated the effectiveness of the optimized ANN model for well production estimation. Furthermore, comparison with the empirical model and the inputs effect through a Monte Carlo simulation illustrated the strength and limitation of the ANN model.

Development of Empirical and Artificial Neural Network Model for the Prediction of Sorption Time to Assess the Potential of CO2 Sequestration in Coal

“…Machine learning techniques such as ANN have been utilized in solving complex nonlinear problems for CBM gas content prediction; reservoir analysis and prediction of production from well; – prediction of key reservoir properties; prediction of coal properties; and analysis of factors affecting productivity of CBM and factors controlling CO 2 sequestration …”

Analysis of design-for-safety implementation factors in the Indonesian construction industry: A two-staged SEM-artificial neural network approach

“…The strategic choice of ANN was motivated by its inherent capability to discern intricate patterns and discern non-linear relationships amid variables, thus enabling predictions of complex systems. To engender optimal performance, the hyperparameters governing the ANN analysis were meticulously fine-tuned based on adjustment on previous research that used ANN model to analyze [ 41 ]. The architecture encompassed 7 nodes, while the learning rate was precisely set at 0.05 [ 42 ].…”

Expansion of Nanotechnology-Based Chemically Enhanced Oil Recovery Field Applications in Colombia: An Approach from Laboratory Experiments, Effluent Follow-Up, and Machine Learning

“…This is similar to what was reported by other authors. 89,90 Acknowledging the importance of a robust data division strategy, a sensitivity analysis is performed on the effect of splitting the training and testing data sets. This analysis confirmed the stability of the model's performance across various data splits, ensuring that predictive insights are reliable and robust.…”