How Can Business Analytics Enhance Decision-Making in Oil and Gas Surface Facilities?

This systematic literature review examines the application of business analytics in oil and gas surface facilities, analyzing 43 peer-reviewed publications (2012–2025). It identifies three levels of analytics—descriptive, predictive, and prescriptive—each addressing operational challenges through specific technologies. Descriptive analytics enhances visibility via IoT sensors and dashboards. Predictive analytics enables proactive maintenance through machine learning, while prescriptive analytics optimizes operations using simulations and multi-objective decision models. Implementation examples demonstrate efficiency gains, including a 28% reduction in separation unit losses, an 18% decrease in compression system energy consumption, and a 64% improvement in methane emissions detection. However, adoption remains hindered by data integration issues, workforce skill gaps, and organizational resistance. This study proposes a business analytics framework to guide surface facility managers in selecting analytics solutions, with a focus on progressive capability development. Future research should explore digital twins, real-time data integration, ESG reporting, workforce training, and edge computing for remote facilities. This review offers a structured approach to analytics implementation, striking a balance between efficiency, economic performance, and environmental sustainability.