An efficient deep learning-based workflow for CO2 plume imaging considering model uncertainties with distributed pressure and temperature measurements

• Published in: International journal of greenhouse gas control Vol. 132; no. C; p. 104066
• Main Authors: Nagao, Masahiro, Yao, Changqing, Onishi, Tsubasa, Chen, Hongquan, Datta-Gupta, Akhil, Mishra, Srikanta
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Ltd 01.02.2024; Elsevier
• Subjects: CCS; CO2 plume visualization; Deep learning; DTS; Variational autoencoder decoder; Deep learning; CCS; DTS; Variational autoencoder decoder; CO2 plume visualization
• ISSN: 1750-5836; 1878-0148
• DOI: 10.1016/j.ijggc.2024.104066

•Monitoring CO2 plumes during geologic CO2 sequestration projects is essential.•High-fidelity simulations can be prohibitively expensive for history matching.•A deep learning framework is developed for efficient CO2 plume visualization.•Onset time is used for visualization of a propagating CO2 saturation front.•Variational autoencoder is used to compress high dimentional image data. Monitoring CO2 plumes throughout the operation of geologic CO2 sequestration projects is essential to environmental safety. The evolution of underground CO2 saturation can be predicted using high-fidelity numerical simulations. However, high-fidelity simulations can be prohibitively expensive to compute. As a result of recent developments in data-driven models, rapid predictions of the CO2 plume can now be made using readily available pressure and temperature measurements. This study presents a novel deep learning-based workflow for efficiently visualizing CO2 plumes in near real-time while considering their uncertainties. In our deep learning workflow, we visualize the CO2 plume images in the reservoir as a propagating saturation front, represented by ‘onset time’, using field measurements, including downhole pressure and temperature. At a given location, the ‘onset time’ is the calendar time when the CO2 saturation exceeds a certain threshold. Therefore, a single image of the CO2 front propagation is captured using the ‘onset time’ rather than storing multiple CO2 saturation images at different time steps. The use of ‘onset time’ significantly reduces memory and computational cost of deep learning-based framework, enabling large-scale field applications. We use a variational autoencoder-decoder (VAE) network to compress high dimensional ‘onset time’ images into low dimensional latent variables while considering uncertainties of the predicted images. The use of VAE and onset time, simplifies the overall neural network architecture and significantly enhances the training efficiency. To estimate the latent variables of the VAE network, we train a feed forward neural network model that incorporates available monitoring data such as downhole pressure and temperature measurements. The estimated latent variables are then fed into a trained decoder network to generate 3D onset time images, visualizing the propagation of CO2 plume in near real time. The proposed workflow is applied to both synthetic and field cases, where the field application is a large-scale geological carbon storage project in a carbonate reef reservoir in the Northern Niagaran Pinnacle Reef Trend in Michigan, USA. The field measurements include distributed temperature sensing (DTS) and distributed pressure responses from down-hole gauges along the monitoring well. The predicted CO2 plume images provided by the proposed workflow are shown to be consistent with the simulation results of traditional history matched model using genetic algorithm. Our deep learning-based framework can predict the CO2 front propagation in terms of onset time in seconds, making it well-suited for real time decision-making and operational optimization.