Effective identification of induced seismicity and real-time management of seismic risks are hot topics due to increasing induced seismicity in areas related to energy exploitation. Existing decision-making tool for managing seismic risks, known as the traffic light system, is not robust enough. To meet the increasing needs for safe mining of energy at production sites, finding an advanced and efficient method to improve the traffic light system is essential. In recent years, machine learning, an advanced inductive and analytical method, has been widely used in seismology. In this context, research gaps associated with the identification and management of induced seismicity, as well as the current achievements of machine learning in addressing induced seismicity problems, are reviewed. A basic framework of using machine learning method to optimize the traffic light system in the industrial production process is first proposed. Then, its feasibility and rationality are demonstrated by similar cases. This framework may provide a reference for the development of a risk-based adaptive traffic light management system.

No abstract

Depending on rock pore compressibility, a change in effective confining pressure (ECP) can have a significant influence on supercritical CO 2 (SC-CO 2) migration characteristics in natural reservoirs. In this study, a tight glutenite sample was used to conduct porosity/permeability measurements under different ECPs of 1.5, 5.5, 9.5, 13.5, 17.5 and 21.5 MPa. Then a SC-CO 2 drainage core flooding experiment, which was monitored using nuclear magnetic resonance (NMR) technique, was conducted at an ECP of 5.5 MPa. Measurement results show that the porosity and permeability of the sample were comparatively low (at an ECP of 1.5 MPa, 8.3% and 2.4 mD, respectively). With increasing ECP, the porosity/permeability decreased rapidly initially then more slowly at the larger ECP value. NMR results shows that SC-CO 2 preferentially displaced water creating flow channels inside the sample. At SC-CO 2 breakthrough, the average residual water saturation was 69.86%. Following breakthrough, SC-CO 2 continued to displace the water creating more substantial flow channels until they were sufficient to transport the SC-CO 2 at the fixed flow rate, resulting in a residual water saturation of 42.72%. A two-dimensional computational model was then established based on these experimental results to simulate the fluid behaviors at an ECP of 5.5 MPa, and then the model was

No abstract

No abstract