Based on the results of research works reflected in the scientific literature, the main examples, methods and approaches to the development of polymer inorganic nanocomposite materials for target membranes are considered. The focus is on membranes for critical technologies with improved mechanical, thermal properties that have the necessary capabilities to solve the problems of a selective pervaporation. For the purpose of directional changes in the parameters of membranes, effects on their properties of the type, amount and conditions of nanoparticle incorporation into the polymer matrix were analyzed. An influence of nanoparticles on the structural and morphological characteristics of the nanocomposite film is considered, as well as possibilities of forming transport channels for separated liquids are analyzed. Particular attention is paid to a correlation of nanocomposite structure-transport properties of membranes, whose separation characteristics are usually considered within the framework of the diffusion-sorption mechanism.
The identification of a compound's chemical structure remains one of the most crucial everyday tasks in chemistry. Among the vast range of existing analytical techniques NMR spectroscopy remains one of the most powerful tools. As a step towards structure prediction from experimental NMR spectra, this article introduces a novel machine-learning (ML) Structure Seer model that is designed to provide a quantitative probabilistic prediction on the connectivity of the atoms based on the information on the elemental composition of the molecule along with a list of atom-attributed isotropic shielding constants, obtained via quantum chemical methods based on a Hartree–Fock calculation. The utilization of shielding constants in the approach instead of NMR chemical shifts helps overcome challenges linked to the relatively limited sizes of datasets comprising reliably measured spectra. Additionally, our approach holds significant potential for scalability, as it can harness vast amounts of information on known chemical structures for the model's learning process. A comprehensive evaluation of the model trained on the QM9 and custom dataset derived from the PubChem database was conducted. The trained model was demonstrated to have the capability of accurately predicting up to 100% of the bonds for selected compounds from the QM9 dataset, achieving an impressive average accuracy rate of 37.5% for predicted bonds in the test fold. The application of the model to the tasks of NMR peak attribution, structure prediction and identification is discussed, along with prospective strategies of prediction interpretation, such as similarity searches and ranking of isomeric structures.