Abstract
Chemical Product Engineering (CPE) is marked by numerous challenges, such as the complexity of the properties–structure–ingredients–process relationship of the different products and the necessity to discover and develop constantly and quickly new molecules and materials with tailor-made properties. In recent years, artificial intelligence (AI) and machine learning (ML) methods have gained increasing attention due to their performance in tackling particularly complex problems in various areas, such as computer vision and natural language processing. As such, they present a specific interest in addressing the complex challenges of CPE. This article provides an updated review of the state of the art regarding the implementation of ML techniques in different types of CPE problems with a particular focus on four specific domains, namely the design and discovery of new molecules and materials, the modeling of processes, the prediction of chemical reactions/retrosynthesis and the support for sensorial analysis. This review is further completed by general guidelines for the selection of an appropriate ML technique given the characteristics of each problem and by a critical discussion of several key issues associated with the development of ML modeling approaches. Accordingly, this paper may serve both the experienced researcher in the field as well as the newcomer.
Highlights
While the previously presented state of the art outlined the variety of machine learning (ML) methods applied in diverse applications of Chemical Product Engineering (CPE) for solving different types of problems, this section aims at providing some general guidelines for applying ML in relevant problems
Artificial intelligence (AI) and ML techniques have been increasingly applied in CPE in order to solve the numerous complex challenges: the complexity of the structure-process
Special emphasis was given to four selected domains, namely the design/discovery of new molecules/materials, the prediction of chemical reactions/retrosynthesis, the modeling of processes and the support for sensorial analysis
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Given the dataset the user will provide to the algorithm, the latter will identify on its own, without being explicitly programmed by the user, eventual mathematical correlations and patterns among them This current great popularity of AI and ML is mostly driven by the increasingly facilitated access to large amounts of data of diverse variety along with the major advances in modern computational systems that are becoming more powerful and affordable every day. In parallel to the above, the design of new materials and products must take into account the important sustainability challenges of the modern industrial production paradigm, as well as the competitive environment and dynamic market demands that necessitate constant development and production-on-demand readiness In this sense, the increasing interest in ML techniques for CPE applications comes as a natural consequence, since these techniques are adapted to the increased complexity of these systems, as will be illustrated in the rest of this report. The large number of abbreviations that are used throughout the discussion is listed at the end of the paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
