石油与环境生物技术杂志

抽象的

Exploring the Usefulness of Gaussian Process Regression for the Prediction of Oil, Water and Gas Production Rates

Etinosa Osaro*, Vivian Okorie, Sonia Alornyo

This study evaluated the performance of Gaussian Process Regression (GPR) models for predicting the production rates of oil, gas, and water in the energy industry. GPR is a non-parametric, Bayesian-based machine learning technique that models the uncertainty in the predictions, providing not only a prediction but also a confidence interval for the prediction. This study analyzed the impact of various input features on the production rates, including choke size, tubing head pressure, flow line pressure, basic sediment and water, net Application Programming Interface (API), well flowing pressure, and static pressure. The result of this study provides valuable insights into the potential of GPR for improving production forecasting and resource management in the oil and gas industry. The findings also shed light on the suitability of different kernels in modeling the production rates and the significance of each input feature in production forecasting and optimization. The use of GPR in production forecasting has the potential to increase efficiency, improve productivity, and reduce costs in the oil and gas industry.