Related papers: How Machine Learning Predicts Fluid Densities unde…
We use machine learning (ML) to infer stress and plastic flow rules using data from repre- sentative polycrystalline simulations. In particular, we use so-called deep (multilayer) neural networks (NN) to represent the two response…
Hydrodynamics is known to have strong effects on the kinetics of phase separation. There exist open questions on how such effects manifest in systems under confinement. Here, we have undertaken extensive studies of the kinetics of phase…
Despite a cost-effective option in practical engineering, Reynolds-averaged Navier-Stokes simulations are facing the ever-growing demand for more accurate turbulence models. Recently, emerging machine learning techniques are making…
The application machine learning (ML) algorithms to turbulence modeling has shown promise over the last few years, but their application has been restricted to eddy viscosity based closure approaches. In this article we discuss rationale…
The structure and dynamics of fluids confined in nanoporous media differ from those in bulk, which can be probed using NMR relaxation measurements. We here show, using atomistic molecular dynamics simulations of water in a slit nanopore,…
Normalizing Flows are a promising new class of algorithms for unsupervised learning based on maximum likelihood optimization with change of variables. They offer to learn a factorized component representation for complex nonlinear data and,…
Media and membranes composed of micrometric-diameter pores are well known in academia and industry to be capable of efficacious nanofiltration of fluids once the pore inner surfaces are coated with nanostructures. Given the large mismatch…
We compared the diffusion of water confined in armchair and zigzag carbon nanotubes for rigid and flexible water models. Using one rigid model, TIP4P/2005, and two flexible models, SPC/Fw and SPC/FH, we found that the number of the number…
The world of nanoscales in fluidics is the frontier where the continuum of fluid mechanics meets the atomic, and even quantum, nature of matter. While water dynamics remains largely classical under extreme confinement, several experiments…
Flooding is a destructive and dangerous hazard and climate change appears to be increasing the frequency of catastrophic flooding events around the world. Physics-based flood models are costly to calibrate and are rarely generalizable…
We have studied the molecular scale hydrophobicity of an apolar solute, argon, confined between hydrophobic planar surfaces with different confinement widths. Specifically, we find that the hydrophobicity exhibits a non-monotonic behavior…
In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…
It has been recently shown that nanobubbles exhibit a remarkable and unexpected stability. The lifetime of nanobubbles, formed either within liquids or on hydrophobic surfaces, can exceed by more than 10 orders of magnitude the theoretical…
In this report, an analytic model to predict phase transitions of confined fluids in nano systems is presented and it is used to predict the behavior of the confined fluid in nanotubes and nanoslits. In our approach besides including a…
We have explored the phase behavior of a set of water-like models in slit pores of nanoscopic dimensions. The interaction between water and pore walls mimics the graphite surface. A version of density functional method is used as…
We present a machine learning-based framework for blending data-driven turbulent closures in the Reynolds-Averaged Navier-Stokes (RANS) equations, aimed at improving their generalizability across diverse flow regimes. Specialized models…
The use of machine learning is becoming ubiquitous in astronomy, but remains rare in the study of the atmospheres of exoplanets. Given the spectrum of an exoplanetary atmosphere, a multi-parameter space is swept through in real time to find…
Conventional fluid simulations can be time consuming and energy intensive. We researched the viability of a neural network for simulating incompressible fluids in a randomized obstacle-heavy environment, as an alternative to the numerical…
The phase behavior of hydrocarbon fluids confined in porous media has been reported to deviate significantly from that in the bulk environment due to the existence of sub-10nm pores. Though experiments and simulations have measured the…
The weights of a deep neural network model are optimized in conjunction with the governing flow equations to provide a model for sub-grid-scale stresses in a temporally developing plane turbulent jet at Reynolds number $Re_0=6\,000$. The…