PRR Project

Summary

The researcher position required is in the scope of LEPABE – Laboratory for Process Engineering, Environment, Biotechnology and Energy, specifically for the Process Systems Engineering research line. Two research activities included in this line are process modelling and integration and multivariate statistical methods and models. The first activity intends to develop modelling, simulation and optimisation frameworks, integrating sustainability requirements for various industrial sectors. The second activity includes chemometrics applications in various industrial sectors and the development of data-driven models for predicting air pollution. In both activities, machine learning tools are very relevant in achieving disruptive new scientific approaches.Machine learning is the main branch of artificial intelligence focused on building computer systems, which learn from data. Machine learning tools are trained to find relationships and patterns in data. They use historical data to make predictions, classify information, cluster data points, and reduce dimensionality. Machine learning tools have been applied in various sectors after the fourth industrial revolution and with the incentives for implementing digitalisation projects. These tools are taking their first steps in chemical and environmental engineering, and their implementation should be clearly intensified.The researcher will join the team led by Fernando Martins, who has been involved in several research projects, most of them with strict connections with companies and collaborative laboratories, developing scientific advancements using process systems engineering tools, among which, modelling, simulation and optimisation tools to define processes implementing holist methodologies, to answer the emergent challenges of i) enhancing energy efficiency processes, ii) decarbonisation impact and, iii) reductions in greenhouse gas emissions. The approach that has been considered uses first principles models and does not consider hybrid or data-driven models, which are created by applying machine learning tools. Fernando Martins’ team has also been involved in applying machine learning tools, such as supervised modelling approaches, as partial least squares, artificial neural networks and support vector machines in chemometrics (in oil refining and formaldehyde and synthetic resins industrial sectors) and in predicting outdoor and indoor air quality, with successful results.  This team also has significant activity in the provision of services for industrial companies, helping to define better operational scenarios and design revamping processes to answer the actual global challenges.Thus, the researcher will focus on researching and developing machine learning tools in the two activities mentioned above due to their central relevance in obtaining more robust process/system technologies.This application is also totally aligned with strategic areas of ALiCE (Associate Laboratory in Chemical Engineering in whose consortium LEPABE is integrated) through the sub-line Process Analytics, Modelling and Optimization of the thematic line Chemical Industry.The candidate to be selected must have a doctorate in chemical or environmental engineering, with experience in applying machine learning tools to chemical and/or environmental engineering problems. She/He must also have deep knowledge of process simulators and programming languages (such as R, Matlab and Toolboxs, Python and Libraries). The candidate should also demonstrate strong organisational proficiency and experience supervising degree, master´s, and doctorate students and trainees/research fellows.