Generative Quasi-Continuum Modeling of Confined Fluids at the Nanoscale
This work addresses a computational bottleneck in nanoscale fluid modeling for researchers in materials science and physics, offering a more efficient alternative to existing simulation methods.
The paper tackles the problem of predicting density profiles of confined fluids at the nanoscale, which is computationally expensive with existing methods, by proposing a conditional denoising diffusion probabilistic model (DDPM) based quasi-continuum approach; it demonstrates that this method recovers density profiles with ab initio accuracy, achieving orders-of-magnitude speed-up in runtime and requiring significantly less training data compared to AIMD and MLMD simulations.
We present a data-efficient, multiscale framework for predicting the density profiles of confined fluids at the nanoscale. While accurate density estimates require prohibitively long timescales that are inaccessible by ab initio molecular dynamics (AIMD) simulations, machine-learned molecular dynamics (MLMD) offers a scalable alternative, enabling the generation of force predictions at ab initio accuracy with reduced computational cost. However, despite their efficiency, MLMD simulations remain constrained by femtosecond timesteps, which limit their practicality for computing long-time averages needed for accurate density estimation. To address this, we propose a conditional denoising diffusion probabilistic model (DDPM) based quasi-continuum approach that predicts the long-time behavior of force profiles along the confinement direction, conditioned on noisy forces extracted from a limited AIMD dataset. The predicted smooth forces are then linked to continuum theory via the Nernst-Planck equation to reveal the underlying density behavior. We test the framework on water confined between two graphene nanoscale slits and demonstrate that density profiles for channel widths outside of the training domain can be recovered with ab initio accuracy. Compared to AIMD and MLMD simulations, our method achieves orders-of-magnitude speed-up in runtime and requires significantly less training data than prior works.