Diffusion‐Based Subsurface CO2 ${\text{CO}}_{2}$ Multiphysics Monitoring and Forecasting

• Published in: Journal of geophysical research. Machine learning and computation Vol. 2; no. 2
• Main Authors: Huang, Xinquan, Wang, Fu, Alkhalifah, Tariq
• Format: Journal Article
• Language: English
• Published: Wiley 01.06.2025
• ISSN: 2993-5210; 2993-5210
• DOI: 10.1029/2025JH000603

Carbon capture and storage (CCS) plays a crucial role in mitigating greenhouse gas emissions, particularly from industrial outputs. Using seismic monitoring can aid in an accurate and robust monitoring system to ensure the effectiveness of CCS and mitigate associated risks. However, conventional seismic wave equation‐based approaches are computationally demanding, which hinders real‐time applications. In addition to efficiency, forecasting and uncertainty analysis are not easy to handle using such numerical‐simulation‐based approaches. To this end, we propose a novel subsurface multiphysics monitoring and forecasting framework utilizing video diffusion models. This approach can generate high‐quality representations of CO2 evolution and associated changes in subsurface elastic properties. With reconstruction guidance, forecasting and inversion can be achieved conditioned on historical frames and/or observational data. Meanwhile, due to the generative nature of the approach, we can quantify uncertainty in the prediction. Tests based on the Compass model show that the proposed method successfully captured the inherently complex physical phenomena associated with CO2 ${\text{CO}}_{2}$ monitoring, and it can predict and invert the subsurface elastic properties and CO2 ${\text{CO}}_{2}$ saturation with consistency in their evolution. Plain Language Summary The Net zero emission aims to reduce the impact of CO2 ${\text{CO}}_{2}$ on the climate and is a crucial component of sustainable human development. Carbon capture and storage (CCS) is a highly effective method for reducing CO2 ${\text{CO}}_{2}$ emissions and has gained increasing attention. To improve decision‐making in the storage process, such as injection rates, we need to comprehensively monitor and understand the storage status and subsurface geological conditions, thereby mitigating the risk of leakage and secondary disasters. The CCS process involves changes in fluid and elastic parameters, for which seismic monitoring methods provide effective tools. However, traditional wave equation‐based monitoring methods are limited by computational inefficiency, making real‐time monitoring challenging. This paper proposes a novel end‐to‐end monitoring framework for subsurface multiphysical processes. The method treats the evolution of multiphysics processes as a video and models this joint distribution using a video diffusion model, which is a modern machine‐learning technique. Combined with the reconstruction guidance, the proposed method enables forecasting, inversion, and flexible uncertainty estimation. Tests on the Compass model validate the effectiveness of the method, presenting a promising unified framework for monitoring and probabilistic forecasting. Key Points We develop a novel monitoring and forecasting framework using video diffusion models of subsurface changes due to, for example, CO2 ${\text{CO}}_{2}$ injection This approach can be a simulation engine for multiphysics evolution and maintain physical consistency between multiple variables The proposed method is applied to multiphysics monitoring and forecasting for permeability, CO2 ${\text{CO}}_{2}$ saturation, velocity, density, and RTM images