DC13: Machine learning and artificial intelligence for process optimization (WP4)
Host institution: Artificial Intelligence Techniques (Spain)
Supervisor: Roberto Lopez (PhD promoter)
Objectives: (i) Acquire a comprehensive knowledge of wastewater treatment processes through the utilization of artificial intelligence methodologies, (ii) develop an advanced artificial intelligence software designed to simulate and model wastewater treatment processes, aiming to enhance understanding and optimization within this domain.
DC 13 will dedicate efforts to develop specialized software expressly tailored to model and optimize the performance of these energy-neutral wastewater treatment systems. This software will serve as a versatile platform, capable of simulating diverse scenarios and optimizing system parameters based on the insights gleaned from the collected data. Utilizing the wealth of data amassed, DC13 will develop models aimed at formulating responsive optimization algorithms. These algorithms are designed to dynamically fine-tune system configurations, aiming to elevate water quality while concurrently reducing energy consumption within the treatment process. In parallel, DC13 will develop machine learning algorithms specifically tailored to model the intricate dynamics inherent in wastewater treatment processes. Through complementing software development and algorithm construction, DC13 will design a practical tool specifically engineered to simulate real-world applications of these treatment processes.
Expected results: Novel artificial intelligence software and algorithms enable the simulation and optimization of the removal of key priority pollutants and energy carrier generation. Additionally, the development of a machine learning tool aims to apply these algorithms in practical settings.
Planned secondments:
- UT (Sup.: I. Zekker): M12-15, 4 months: Introduction to biological transformation processes for key priority pollutants;
- Biofaction (Sup.: M. Schmidt): M25-28; 4 months: Integration of machine learning and science-society interface analysis.
Enrolment in Doctoral degree: Enrolment in Doctoral degree(s): Doctoral Program in Environmental Sciences and Engineering, University of Aveiro (PT)
Ideal candidate profile:
- Bachelor’s degree in Mathematics, Physics, or a related field.
- Master’s degree in Data Science, Artificial Intelligence, or a related field.
- Strong programming skills, particularly in C++.
- Solid understanding of AI, machine learning, and system modeling techniques.
- Familiarity with the open-source neural networks library OpenNN.
- Experience in process optimization and interdisciplinary projects, especially in wastewater treatment or environmental engineering areas.
- Strong analytical and problem-solving skills.
- Excellent communication abilities and ability to work in a collaborative, international environment.
Recruited candidate: Simone Scala