Modeling and scale-bridging using machine learning: nanoconfinement effects in porous media

Abstract

Fine-scale models that represent first-principles physics are challenging to represent at larger scales of interest in many application areas. In nanoporous media such as tight-shale formations, where the typical pore size is less than 50 nm, confinement effects play a significant role in how fluids behave. At these scales, fluids are under confinement, affecting key properties such as density, viscosity, adsorption, etc. Pore-scale Lattice Boltzmann Methods (LBM) can simulate flow in complex pore structures relevant to predicting hydrocarbon production, but must be corrected to account for confinement effects. Molecular dynamics (MD) can model confinement effects but is computationally expensive in comparison. The hurdle to bridging MD with LBM is the computational expense of MD simulations needed to perform this correction. Here, we build a Machine Learning (ML) surrogate model that captures adsorption effects across a wide range of parameter space and bridges the MD and LBM scales using a relatively small number of MD calculations. The model computes upscaled adsorption parameters across varying density, temperature, and pore width. The ML model is 7 orders of magnitude faster than brute force MD. This workflow is agnostic to the physical system and could be generalized to further scale-bridging applications. Multi-scale physics problems are found in all scientific disciplines. Prominent examples can be found in material science 1-3 , biology 4 , chemistry 5-9 , and geosciences 10-12. Typically, information from computationally intensive fine-scale models have to be translated or upscaled into faster coarse-scale models to solve the problem at the scale of interest. A problem of great scientific and economic interest is the flow of hydrocarbon in nanoporous shale. Traditional porous media approaches such as the LBM allow for complex pore geometries but need to be provided with effective properties that account for nanoconfinement effects in order to accurately simulate mass transport at the continuum scale 13. Atomistic simulations such as Molecular Dynamics (MD) capture nanoconfinement effects accurately, but are limited to a few pores as they are computationally intractable to simulate for mesoscopic pore geometries. There is a need for approaches that efficiently bridge these two scales without compromising accuracy. Recently, Machine Learning (ML) has shown great promise in accelerating physics-based models that makes it feasible to build a scale-bridging framework 14-16. The applications include fracture propagation in brittle materials 17 , computational fluid dynamics 18 and molecular dynamics 19. On another dimension, Machine Learning

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

“…The approach of molecular dynamics has been used for nano to continuum scale bridging for developing efficient nano-composites [419,420]. But the molecular dynamics is considered computationally expensive and intractable [421]. Adaptive ML has been successfully used to build efficient scale-bridging models [422,423].…”

Modeling Nanoconfinement Effects Using Active Learning

“…While having a fast proxy for molecular dynamics in nanopores has value in itself (e.g., for estimating gas reserves), we would like to point toward what we believe to be an important future application of our methods: The use of the surrogate for the parametrization of continuum models of nanoscale porous mediatechniques for accomplishing this using machine learning have been recently investigated . A fast surrogate would enable the upscaling of nanoconfinement effects into, for example, an extended LBM formulation that can treat fluid flow as a coupled problem between many pores of spanning many length scales.…”

“…While having a fast proxy for molecular dynamics in nanopores has value in itself (e.g., for estimating gas reserves), we would like to point toward what we believe to be an important future application of our methods: The use of the surrogate for the parametrization of continuum models of nanoscale porous mediatechniques for accomplishing this using machine learning have been recently investigated. 66 A fast surrogate would enable the upscaling of nanoconfinement effects into, for example, an extended LBM formulation that can treat fluid flow as a coupled problem between many pores of spanning many length scales. While this endeavor comes with many challenges related to workflows and code coupling, such a scale-bridging model would enable a fast computational method to address the role of nanoconfinement in porous media for a variety of applications in engineering, energy sciences, and environmental sciences.…”

Nanoscale slip length prediction with machine learning tools

“…These methods are based on data-mining from existing databases, usually enriched by new simulation or experimental data, and can be implemented only with a superficial understanding of the physical problem 29 . In the near future, it is expected that MD simulations will be used to extract training data for ML models, sigificantly reducing the computational cost required 30 and may suggest a joint scheme across scales 31 .…”