Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR. (October 2022)

• Record Type: Journal Article
• Authors: Tang, Hewei; Fu, Pengcheng; Jo, Honggeun; Jiang, Su; Sherman, Christopher S.; Hamon, François; Azzolina, Nicholas A.; Morris, Joseph P.
• Is Part Of: International journal of greenhouse gas control. Volume 120(2022)
• Publication Date: 2022-10
• Subjects: Data assimilation -- Deep learning -- InSAR data -- Reservoir pressure forecast -- ES-MDA; Greenhouse gases -- Environmental aspects -- Periodicals; Air -- Purification -- Technological innovations -- Periodicals; Gaz à effet de serre -- Périodiques; Gaz à effet de serre -- Réduction -- Périodiques; Air -- Purification -- Technological innovations; Greenhouse gases -- Environmental aspects; Periodicals; 363.73874605
• DOI: 10.1016/j.ijggc.2022.103765
• Languages: English
• ISSNs: 1750-5836

Abstract

Highlights: Developed a 3D data assimilation workflow for reservoir pressure forecasting in GCS. InSAR data are used to infer reservoir pressure build up. A 3D-to-2D residual U-Net structure is applied to accelerate the workflow. The workflow can achieve a 1500-time speedup compared to a traditional approach. Abstract: Fast forecasting of the reservoir pressure distribution during geologic carbon storage (GCS) by assimilating monitoring data is a challenging problem. Due to high drilling cost, GCS projects usually have spatially sparse measurements from few wells, leading to high uncertainties in reservoir pressure prediction. To address this challenge, we use low-cost Interferometric Synthetic-Aperture Radar (InSAR) data as monitoring data to infer reservoir pressure build up. We develop a deep learning-accelerated workflow to assimilate surface displacement maps interpreted from InSAR and to forecast dynamic reservoir pressure. Employing an Ensemble Smoother Multiple Data Assimilation (ES-MDA) framework, the workflow updates three-dimensional (3D) geologic properties and predicts reservoir pressure with quantified uncertainties. We use a synthetic commercial-scale GCS model with bimodally distributed permeability and porosity to demonstrate the efficacy of the workflow. A two-step CNN-PCA approach is employed to parameterize the bimodal fields. The computational efficiency of the workflow is boosted by two residual U-Net based surrogate models for surface displacement and reservoir pressure predictions, respectively. The workflow can complete data assimilation and reservoir pressure forecasting in half an hour on a personal computer.