Runjing Guan

Nanoconfined fluid is central to many engineering applications such as shale energy production, carbon sequestration, and molecular separations. While classical molecular dynamics (MD) simulation provides essential atomistic detail, its prohibitive computational cost severely limits accessible time and length scales. Hybrid MD-Monte Carlo (MDMC) methods accelerate sampling but lack generality beyond their trained conditions. In this work, we introduce an AI-assisted MDMC framework that overcomes this limitation by learning local, conditional transition statistics directly from MD trajectories. Our method encodes molecular motion into a compact set of neural network-predicted displacement actions, preserving MD-level accuracy within a drastically reduced dimensionality. This approach enables efficient sampling with robust generality. We systematically demonstrate the framework's accuracy and transferability across diverse thermodynamic conditions (temperature, pressure), spatial scales, and complex nano-scale geometries, establishing a versatile path for simulating confined fluid phenomena relevant to engineering applications.

Addressing the bottleneck of low efficiency in traditional pore network extraction within CCS dynamic simulation, this paper systematically reviews the evolution of algorithm technology, focusing on elucidating the continuous-space-based pixel-free flashlight searching medial axis algorithm. Through comparative research with SNOW and MAGNET algorithms, it validates that FSMA possesses superior computational efficiency and physical stability when processing the subtle evolution of pore structure. Finally, the paper discusses the future development direction of pore network extraction technology represented by FSMA, aiming to provide a new technical path for constructing next-generation dynamic pore network models capable of real-time response.