Effective monitoring of CO 2 plume is critical to environmental safety throughout the life-cycle of a geologic CO 2 sequestration project. Although full physics-based techniques such as history matching with numerical simulations can be used for predicting the evolution of underground CO 2 saturation, the computational cost of the high-fidelity simulations can be prohibitive. Recent development in data-driven models can provide a viable alternative for rapid prediction of the CO 2 plume based on readily available pressure and temperature measurements. In this study, we present a novel deep learning-based workflow that can efficiently visualize CO 2 plume in near real-time with considering the uncertainties of CO 2 plume images. ‘Deep learning’ refers to a data-driven input-output model development approach involving artificial neural networks with many hidden layers. Our deep learning workflow utilizes field measurements, such as downhole pressure, temperature, and flowrates as input to visualize the subsurface CO 2 plume images as a propagating CO 2 saturation front in terms of ‘onset time’. The ‘onset time’ is the calendar time when the CO 2 saturation at a given location exceeds a specified threshold value. Rather than storing CO 2 saturation at multiple time steps, the onset time compresses the data into a single image of CO 2 front propagation. To start with, we generate a comprehensive training dataset using flow simulation with diverse geologic model realizations and fluid models. The training data consists of injection rate/pressure at the injection well and measurements in monitoring wells (e.g., distributed pressure and temperature data) and the corresponding CO 2 plume propagation onset time maps.