Related papers: From ionic surfactants to Nafion through convoluti…

Permeability is a central concept in the macroscopic description of flow through porous media, with applications spanning from oil recovery to hydrology. Traditional methods for determining the permeability tensor involving flow simulations…

This paper introduces a blind watermarking based on a convolutional neural network (CNN). We propose an iterative learning framework to secure robustness of watermarking. One loop of learning process consists of the following three stages:…

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state…

Machine learning algorithms have been available since the 1990s, but it is much more recently that they have come into use also in the physical sciences. While these algorithms have already proven to be useful in uncovering new properties…

We present a hybrid Volume-of-Fluid (VoF) Phase-Field method for general soluble surfactant-laden interfacial flows. The scheme retains the VoF method for interface tracking and momentum solution, while a diffused Phase-Field serves as a…

Nanopores are both a tool to study single-molecule biophysics and nanoscale ion transport, but also a promising material for desalination or osmotic power generation. Understanding the physics underlying ion transport through nano-sized…

It has been recently shown that a viscosity gradient could drive electrical current through a negatively charged nanochannel (Wiener and Stein, arXiv: 1807.09106). To understand the physics underlying this phenomenon, we employed the…

Helium is recognized as a model system for the study of phase transitions. Of particular interest is the superfluid phase in two dimensions. We report measurements on superfluid helium films adsorbed on the surface of a suspended carbon…

We use molecular dynamics simulations to probe hydration, ion spacing, and cation-anion interaction in two sulfonated polysulfones with different ion distributions along the polymer backbone. At room temperature, these polymers remain in a…

Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter…

Since the wide employment of deep learning frameworks in video salient object detection, the accuracy of the recent approaches has made stunning progress. These approaches mainly adopt the sequential modules, based on optical flow or…

Unlike molecular crystals, soft self-assembled fibres, micelles, vesicles, etc., exhibit a certain order in the arrangement of their constitutive monomers, but also high structural dynamicity and variability. Defects and disordered local…

Transformer, which originates from machine translation, is particularly powerful at modeling long-range dependencies. Currently, the transformer is making revolutionary progress in various vision tasks, leading to significant performance…

A physics-informed convolutional neural network is proposed to simulate two phase flow in porous media with time-varying well controls. While most of PICNNs in existing literatures worked on parameter-to-state mapping, our proposed network…

It is well known that Convolutional Neural Networks (CNNs) have significant redundancy in their filter weights. Various methods have been proposed in the literature to compress trained CNNs. These include techniques like pruning weights,…

When a hydrophilic solute in water is suddenly turned into a hydrophobic species, for instance, by photoionization, a layer of hydrated water molecules forms around the solute on a time scale of a few picoseconds. We study the dynamic…

Feature foundation models - usually vision transformers - offer rich semantic descriptors of images, useful for downstream tasks such as (interactive) segmentation and object detection. For computational efficiency these descriptors are…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

Accurate simulation of fluid flow in porous media is challenging due to complex pore-space geometries and the computational cost of solving the Navier-Stokes equations. This difficulty is particularly important when repeated simulations are…

Identifying relevant machine-learning features for multi-sensing platforms is both an applicative limitation to recognize environments and a necessity to interpret the physical relevance of transducers' complementarity in their information…