Carbon footprint forecasting of IOR activities via an intelligent NARX framework for promoting greener reservoir management

Abstract

Summary Introduction: Sustainability is increasingly considered a key strategic driver across all industries including oil and gas, and its upstream sector. We continuously thrive to maximize hydrocarbon production while minimizing the associated carbon footprint. In water flooding oilfield operations, the primary driver of carbon emissions is actually water – usage, production, and disposal. The required energy to transport and process the water is considerable, and it is therefore the major carbon emitter. Forecasting carbon emissions from oilfield operations challenges our ability to optimize field development plans in light of carbon footprint besides profit or recovery. Method: In this work, we present an innovative approach for forecasting the carbon footprint of a reservoir in terms of the associated development and production activities. We use an advanced nonlinear autoregressive neural network approach integrated with time-lapse electromagnetic data to forecast the carbon emissions from the reservoir in real-time under uncertainty. Within this artificial intelligence (AI) framework, we also incorporate the ability to study the adoption of a circular carbon approach. For this scenario, the AI framework allocate the reinjection of produced greenhouse gases while adjusting water injection levels and forecasts the impact of such circular development plan. Results: We tested the framework on a synthetic reservoir encompassing a complex fracture system and well setup. The carbon emissions were forecasted in real-time based on the previous production levels and the defined injection levels. The forecasted carbon emissions were then integrated into an optimization technique in order to adjust injection levels to minimize water cut and overall carbon emissions, while optimizing production levels. Results were promising and highlighted the potential significant reductions in carbon emissions for the studied synthetic reservoir. Moreover, the deployment of deep electromagnetic surveys was found particularly beneficial as a deep formation evaluation method for tracking the injected waterfront inside the reservoir and optimizing the sweep efficiency. Accordingly, such integrated AI approach has a twofold benefit: maximizing the hydrocarbon productivity, while minimizing the water consumption and associated carbon emissions. Future Outlook: Such framework represents a paradigm shift in reservoir management and improved oil recovery operations under uncertainty. It proposes an innovative technique to reduce the carbon footprint and attain at real-time an efficient circular injection development plan.