Akhil Datta Gupta

CO2 Plume Imaging with Accelerated Deep Learning-based Data Assimilation Using Distributed Pressure and Temperature Measurements.

Underground carbon dioxide (CO2) sequestration is widely accepted as an established technology to respond to global warming from greenhouse gas emissions. Effective monitoring of CO2 plume is critical to CO2 storage safety throughout the life cycle of a geologic CO2 sequestration project. Although simulation-based techniques such as history matching can be used for predicting the evolution of underground CO2 saturation, the computational cost of high-fidelity simulations can be prohibitive and is not amenable to real time plume monitoring and management. We present a deep learning–based workflow that can efficiently visualize CO2 plume in near real time. Our deep learning framework utilizes field measurements, such as distributed pressure, and temperature sensor data as input to visualize the subsurface CO2 plume image and associated uncertainties. The power and efficacy of our approach are demonstrated using field applications in saline aquifers and depleted oil and gas reservoirs.