Liquid-Liquid Dispersion Performance Prediction and Uncertainty Quantification Using Recurrent Neural Networks.

We demonstrate the application of a recurrent neural network (RNN) to perform multistep and multivariate time-series performance predictions for stirred and static mixers as exemplars of complex multiphase systems. We employ two network architectures in this study, fitted with either long short-term memory and gated recurrent unit cells, which are trained on high-fidelity, three-dimensional, computational fluid dynamics simulations of the mixer performance, in the presence and absence of surfactants, in terms of drop size distributions and interfacial areas as a function of system parameters; these include physicochemical properties, mixer geometry, and operating conditions. Our results demonstrate that while it is possible to train RNNs with a single fully connected layer more efficiently than with an encoder-decoder structure, the latter is shown to be more capable of learning long-term dynamics underlying dispersion metrics. Details of the methodology are presented, which include data preprocessing, RNN model exploration, and methods for model performance visualization; an ensemble-based procedure is also introduced to provide a measure of the model uncertainty. The workflow is designed to be generic and can be deployed to make predictions in other industrial applications with similar time-series data.

Towards more patient friendly clinical notes through language models and ontologies.

Clinical notes are an efficient way to record patient information but are notoriously hard to decipher for non-experts. Automatically simplifying medical text can empower patients with valuable information about their health, while saving clinicians time. We present a novel approach to automated simplification of medical text based on word frequencies and language modelling, grounded on medical ontologies enriched with layman terms. We release a new dataset of pairs of publicly available medical sentences and a version of them simplified by clinicians. Also, we define a novel text simplification metric and evaluation framework, which we use to conduct a large-scale human evaluation of our method against the state of the art. Our method based on a language model trained on medical forum data generates simpler sentences while preserving both grammar and the original meaning, surpassing the current state of the art.

Simulation of immiscible liquid-liquid flows in complex microchannel geometries using a front-tracking scheme.

The three-dimensional two-phase flow dynamics inside a microfluidic device of complex geometry is simulated using a parallel, hybrid front-tracking/level-set solver. The numerical framework employed circumvents numerous meshing issues normally associated with constructing complex geometries within typical computational fluid dynamics packages. The device considered in the present work is constructed via a module that defines solid objects by means of a static distance function. The construction combines primitive objects, such as a cylinder, a plane, and a torus, for instance, using simple geometrical operations. The numerical solutions predicted encompass dripping and jetting, and transitions in flow patterns are observed featuring the formation of drops, 'pancakes', plugs, and jets, over a wide range of flow rate ratios. We demonstrate the fact that vortex formation accompanies the development of certain flow patterns, and elucidate its role in their underlying mechanisms. Experimental visualisation with a high-speed imaging are also carried out. The numerical predictions are in excellent agreement with the experimental data.

Hysteretic Faraday waves.

We report on the numerical and theoretical study of the subcritical bifurcation of parametrically amplified waves appearing at the interface between two immiscible incompressible fluids when the layer of the lower fluid is very shallow. As a critical control parameter is surpassed, small amplitude surface waves bifurcate subcritically toward highly nonlinear ones with twice their amplitude. We relate this hysteresis with the change of shear stress using a simple stress balance, in agreement with numerical results.

Alternating hexagonal and striped patterns in Faraday surface waves.

A direct numerical simulation of Faraday waves is carried out in a minimal hexagonal domain. Over long times, we observe the alternation of patterns we call quasihexagons and beaded stripes. The symmetries and spatial Fourier spectra of these patterns are analyzed.