Spatio-temporal neural networks for monitoring and prediction of CO2 plume migration from measurable field data

Carbon capture, utilization, and storage (CCUS) technologies are crucial for mitigating greenhouse gas emissions. The success of CCUS projects hinges on accurate prediction and monitoring of the CO${}_2$${}_2$ plume migration during and after injection. To address the computational burden of traditional numerical simulation methods, previous studies have successfully used neural networks as proxy models to expedite the prediction of the CO${}_2$${}_2$ plume migration. However, these models rely on uncertain inputs, such as the distribution of heterogeneous permeability and porosity maps, which can lead to erroneous predictions and pose a significant hurdle for their adoption in real-world applications. To address this issue, this study introduces a framework for reconstruction and short-term prediction of CO${}_2$${}_2$ plume migration based solely on field measurements, which can directly provide information on CO${}_2$${}_2$ plumes, thus eliminating the dependency on uncertain geological information as model input. The framework trains a spatio-temporal neural network model using simulated data under various geologic scenarios to capture the plume evolution dynamics without constraining it to specific geological scenarios. Once trained, the model integrates global and local field measurements from multiple sources to reconstruct the CO${}_2$${}_2$ plume and predict its spatio-temporal evolution. The effectiveness of the proposed framework is tested using two case studies: one using a synthetic dataset and another with data generated from a model of a real field in the Southern San Joaquin Basin. The results show that the proposed framework can accurately reconstruct and perform short-term predictions of the CO${}_2$${}_2$ plume migration by integrating various forms of field measurements.