Geological carbon storage (GCS) is the process of injecting and storing carbon dioxide (CO2) in the subsurface to reduce greenhouse gas emissions. Safe and profitable GCS operations require effective decision-making in the presence of uncertain geological models, a process which can often be facilitated with geophysical monitoring. In this study, we examine how sequential decision-making algorithms can be combined with geophysical measurements for the optimal control of GCS operations. Specifically, we develop an artificial intelligence model using deep reinforcement learning (DRL) that takes geophysical time-lapse gravity and well pressure monitoring data as input and delivers an optimal CO2 injection policy. The objective of the problem at hand is to maximize the profit of a hypothetical GCS operation while mitigating the potential for induced seismicity, by training DRL agents using combined geostatistical, reservoir and geophysical simulation. Comparisons against two benchmarks – a constant injection strategy and an injection schedule optimized using a commercial reservoir simulator toolbox – show that the stochastic control of such operations from subsurface monitoring data using deep reinforcement learning is feasible. Evaluation results show that DRL agent behavior generates profits which are on average 1 to 8 percent higher than what is possible through a constant injection approach. Furthermore, we show that DRL can generate optimal injection policies applicable to the true (yet previously unseen) subsurface given carefully managed levels of uncertainty.
Carbon capture, utilization, and storage (CCUS) technology is effective and value-adding solution for reducing emissions. However, the development and commercialization of these technologies are challenging due to high investment costs and several uncertainties. This study develops a novel comprehensive real-options-based model to evaluate investment in CCUS projects considering the technical risk and the investor's risk aversion. This study proposed an exotic compound real options model that combines American and barrier options. First, applying the Poison process, the technical risk is explicitly modeled. Secondly, the investor's risk aversion is defined as a barrier level for the barrier option part of the proposed model. Thirdly, the value of the project is evaluated through the exotic compound real option. Finally, we assess the economic viability of the project under multiple scenarios. The results of implementing the model for a real case show that the integrated technical risk assessment and the barrier option appropriately address investors' risk aversion. Furthermore, the comparison indicates that the proposed compound real options model is more effective than the traditional NPV (Net Present Value). Regarding policymaking, the results reveal that setting an appropriate carbon tax that considers the costs of carbon capture would be more beneficial. Further, the model provides investors helpful guidance to make proper investment decisions for CCUS technology projects under uncertainties.