Physics-Guided Machine Learning with Flowing Material Balance Integration: A Novel Approach for Reliable Production Forecasting and Well Performance Analytics

Reliable production forecasting is a critical task for evaluating asset valuation and commercial performance in oil and gas reservoirs. Conventional short-term forecasting methods, such as Arps’ decline curve analysis, rely on simple mathematical curve fitting and often oversimplify reservoir performance. On the other hand, long-term forecasting requires complex multidisciplinary models that integrate geophysics, reservoir engineering, and production engineering, but these approaches are time-consuming and have high turnaround times. To bridge the gap between long and short-term production forecasts, reduced-physics models such as Blasingame type curves have been developed, incorporating transient well behaviour derived from diffusivity equations and Darcy’s law. These models assume homogeneity and uniform reservoir properties, enabling faster results while honouring pressure performance. However, despite their efficiency, they still face limitations in reliability, particularly when extended to long-term forecasts. This paper proposes a hybrid modelling approach that integrates flowing material balance (FMB) concepts into physics-informed neural networks (PiNNs) and machine learning models to improve the accuracy and reliability of production forecasting. The proposed methodology introduces two hybrid strategies: physics-informed models enriched with FMB feature, and PiNNs. The first proposed hybrid model uses a created FMB-derived feature as input to neural networks. The second PiNN model embeds data-driven loss functions with a physics-based envelope to reflect reservoir response into the machine learning model. The primary loss function is mean squared error, ensuring minimization of data misfit between predicted and observed production rates. The study validates both proposed physically informed neural network models through performance metrics such as RMSE, MAE, MAPE, and R2. Results application on field data shows that the integration of FMB into neural network models using the PiNN concept guides the neural network models to predict the production rates with higher reliability over the full span of the tested data period, which was the last year of unseen production data. Additionally, the proposed PiNN model is able to predict the well productivity index via hyper-tuning of the PiNN model. Furthermore, the PiNN is not improving the metric performance of conventional neural networks, as it has to satisfy an additional material balance equation. This is due to a lower degree of freedom in the PiNN models.