[Paper Review] Deep Learning for Geological CO2 Sequestration; It's up to 250 times faster than full physics reservoir simulation.

Research papers
Due to the inherently strong nonlinearity of CO2 sequestration, a full physics reservoir simulation is usually time-consuming and resource-intensive.
However, the paper "Bicheng Yan et al., 2021, A Robust Deep Learning Workflow to Predict Multiphase Flow Behavior during Geological CO2 Sequestration Injection and post-injection Periods" proposes to predict the temporal-spatial evolution of pressure and saturation during injection and post-injection periods by utilizing Fourier Neuron Operator.
💎 And compared to fully physical reservoir simulation, the suggested Deep Learning method delivers outstanding prediction accuracy across temporal and spatial dimensions and has a speedup of 250 times.

Link for the paper
Link for the LinkedIn post