Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Abstract

Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the ’recomposition’ of chemical mixtures. Graph-based representations reveal patterns among mixture components, and deep learning models excel in capturing complexity and symmetries when compared to traditional Quantitative Structure–Property Relationship models. Key components, such as Hamiltonian networks and convolution operations, play a central role in representing multiscale mixtures. The integration of ANNs with Chemical Reaction Networks and Physics-Informed Neural Networks for inverse chemical kinetic problems is also examined. The combination of sensors with ANNs shows promise in optical and biomimetic applications. A common ground is identified in the context of statistical physics, where ANN-based methods iteratively adapt their models by blending their initial states with training data. The concept of mixture recomposition unveils a reciprocal inspiration between ANNs and reactive mixtures, highlighting learning behaviors influenced by the training environment.

Deep Learning for Gas Sensing via Infrared Spectroscopy

“…Deep learning has recently been applied to multi-component gas speciation and concentration predictions [ 17 , 18 ]. The emergence of powerful deep learning pattern recognition in gas speciation applications, as explored here, is expected to benefit IR absorption gas sensing by replacing manual feature selection and spectral interpretation with automated processes [ 19 , 20 ]. Using these learning methods, sensors can learn on large quantities of spectral information (features and their shapes) in frequency bands that are arbitrarily selected and/or imposed by hardware or other constraints and make useful predictions on constituent species and their concentrations [ 17 , 18 , 21 , 22 , 23 , 24 , 25 ].…”