The Technical University of Crete (TUC), proud member of the European University on Responsible Consumption and Production (EURECA-PRO), organizes a series of open scientific lectures in the context of faculty exchange visits. The 4th lecture of this series is titled
"A Machine Learning approach in product engineering
for the prediction of the properties of molecules"
and will be delivered by
Dr. Dimitrios Meimaroglou
Associate Professor and Director of International Partnerships
in the Chemical Engineering Department (ENSIC)
University of Lorraine, Nancy, France
on the following date/time
Tuesday 4 June 2024 | 13:00 EEST (12:00 CEST)
and can be attended either physically or virtually
Lecture Hall K2.A1 "Panagiotis Manolopoulos" @ TUC Campus
https://tuc-gr.zoom.us/j/95208088832?pwd=d1Y4VjlkU0dKUzdFWDdlK0dxN2pMUT09
Live stream will be available through the official TUC facebook page.
The lecture is open to all interested members of TUC and EURECA-PRO.
Abstract
This work investigates the use of machine learning (ML) methods for the prediction of thermodynamic properties (i.e. enthalpy and entropy of formation) of molecules from their molecular descriptors. Although quantum chemistry (QC) or group contribution (GC) methods have been commonly employed to calculate these properties, they have shown limitations in their applicability to more complex or larger chemicals and/or computational costs. Inversely, ML methods, based solely on data, have already demonstrated their ability to tackle complex problems in other fields when classical approaches fail or are inefficient. However, their implementation is often mistakenly considered as plug-and-play, overlooking or underestimating the effect of the different choices that are adopted along the development and application of these techniques on the final model performance. Accordingly, the contribution of this work is rather a methodologically-driven investigation of these effects and an attempt to understand how to follow an optimal path - if any - during the implementation of ML techniques to similar problems.
Short Bio
Dr. Dimitrios Meimaroglou is currently an associate professor in the Chemical Engineering Department (ENSIC) of the University of Lorraine. He was awarded the Chair of Excellence in Polymer Reaction Engineering from 2011 to 2016. His main research interests, within the group of "Product Engineering" of the Laboratory of Reactions and Chemical Engineering (LRGP), are focused on developing mathematical models with applications both in the fields of polymers as well as within a general Product Design framework. Both knowledge-based and data-driven techniques are implemented in this sense, with a special emphasis on the use of stochastic Monte Carlo algorithms and Machine Learning methods.
The event will be broadcast live through the official TUC and EURECA-PRO facebook pages and will be recorded, while photographic material will be taken. The digital material will be displayed on the websites and on the official channels of the Technical University of Crete and the European University EURECA-PRO and will be published on social media, press releases and newsletters. For any issue, which concerns your personal data, you can be informed through the page with TUC's privacy policy.
