Prediction of Chromatography Conditions for Purification in Organic Synthesis Using Deep Learning

In this research, a process for developing normal-phase liquid chromatography solvent systems has been proposed. In contrast to the development of conditions via thin-layer chromatography (TLC), this process is based on the architecture of two hierarchically connected neural network-based components. Using a large database of reaction procedures allows those two components to perform an essential role in the machine-learning-based prediction of chromatographic purification conditions, i.e., solvents and the ratio between solvents. In our paper, we build two datasets and test various molecular vectorization approaches, such as extended-connectivity fingerprints, learned embedding, and auto-encoders along with different types of deep neural networks to demonstrate a novel method for modeling chromatographic solvent systems employing two neural networks in sequence. Afterward, we present our findings and provide insights on the most effective methods for solving prediction tasks. Our approach results in a system of two neural networks with long short-term memory (LSTM)-based auto-encoders, where the first predicts solvent labels (by reaching the classification accuracy of 0.950 ± 0.001) and in the case of two solvents, the second one predicts the ratio between two solvents (R² metric equal to 0.982 ± 0.001). Our approach can be used as a guidance instrument in laboratories to accelerate scouting for suitable chromatography conditions.     

Measurement of viscosity of highly viscous non-Newtonian fluids by means of ultrasonic guided waves

In order to perform monitoring of the polymerisation process, it is necessary to measure viscosity. However, in the case of non-Newtonian highly viscous fluids, viscosity starts to be dependent on the vibration or rotation frequency of the sensing element. Also, the sensing element must possess a sufficient mechanical strength. Some of these problems may be solved applying ultrasonic measurement methods, however until now most of the known investigations were devoted to measurements of relatively low viscosities (up to a few Pa s) of Newtonian liquids.     

Mass-transport driven by surface instabilities in metals under reactive plasma/ion beam treatment at moderate temperature

This paper presents a generalized approach to the mechanisms of oxidation, hydrogenation and nitriding of metals under ion irradiation with reactive particles at elevated temperatures. Experimental results on the plasma oxidation of bilayered Y/Zr films, the plasma hydrogenation of Mg films and the ion beam (1.2 keV N ₂ ⁺ ) nitriding of stainless steel are presented and discussed. We make special emphasis on the analysis of surface effects and their role in the initiation of mixing of bilayered films, the ingress of reactive species in the bulk and the restructuring of the surface layers. It is suggested that primary processes driving reactive atoms from the surface into the bulk are surface instabilities induced by thermal and ballistic surface atom relocations under reactive adsorption and ion irradiation, respectively. The diffusion of adatoms and vacancies, at temperature when they become mobile, provide the means to relax the surface energy. It is recognized that the stabilizing effect of surface adatom diffusion is significant at temperatures below 300–350°C. As the temperature increases, the role of surface adatom diffusion decreases and processes in the bulk become dominant. The atoms of subsurface monolayers occupy energetically favorable sites on the surface, and result in reduced surface energy.     

Semiparametric Estimation of the Intensity of Long Memory in Conditional Heteroskedasticity

The paper is concerned with the estimation of the long memory parameter in a conditionally heteroskedastic model proposed by Giraitis et al. (1999b). We consider estimation methods based on the partial sums of the squared observations, which are similar in spirit to the classical R / S analysis, as well as spectral domain approximate maximum likelihood estimators. We review relevant theoretical results and present an empirical simulation study.