Predicting Oil, Gas and Water Production Using Artificial Neural Network in MATLAB: A Data-Driven Approach

Accurate forecasting of oil, gas and water production is a cornerstone of effective reservoir management and optimization in the petroleum industry. As global energy demands increase, ensuring operational efficiency and maximizing resource recovery have become paramount, particularly in countries like Nigeria in Africa, where hydrocarbon reserves are critical to economic development. As such, this study focused on machine learning approach combining supervised and unsupervised methods to model and analyse production behaviour using MATLAB. In the supervised framework, artificial neural network (ANN) regression algorithms of MATLAB were implemented and evaluated. Key reservoir parameters such as pressure, temperature, porosity, permeability and injection rates were utilized as input features, while production rates served as the outputs. In the unsupervised framework, clustering techniques including k-means and Self-Organizing Maps (SOM) were employed to uncover patterns and anomalies in production data. The results demonstrated the effectiveness of the hybrid approach, with ANN achieving the prediction accuracy among supervised models and k-means clustering revealing meaningful production trends. Model performance was evaluated using R² as the primary metric. The ANN-based model demonstrated superior predictive accuracy, achieving R² values of 0.96, 0.92, 0.87 and 0.82. Also, SOM was utilized to visualize production behaviour and detect potential anomalies in well performance. The SOM results provided insightful representations of data patterns, reinforcing the effectiveness of clustering for reservoir diagnostics. The findings highlighted the potential of combining supervised and unsupervised learning methods to improve decision-making, optimize production strategies and enhance operational efficiency in the oil and gas sector. This study underscored the versatility of the Machine Learning Toolbox of MATLAB in addressing complex challenges in reservoir management.