4th Green AI Webinar: Hybrid AI and Physics-informed Machine Learning

The environmental impact of AI has exploded due to the popularity of large-scale generative AI models. At the same time, many AI methods can deliver high performance with much lower computational requirements, especially when they are designed to make use of existing domain knowledge. In this webinar, scientists from the ENFIELD project will present research related to hybrid AI and physics-informed machine learning. These are approaches for building efficient and reliable AI systems that combine data-driven learning with physical principles and expert knowledge.

Participation is free!

Date: 3^rd June 2026, 14:00-15:00 CEST
Location: Online (Teams)
To register, you must fill in the following form by 2^nd June 2026 (23:29 CEST) .

This webinar is part of a series of online AI events organised by ENFIELD, a project co-funded by the European Union.

Target audience

The target audience includes young researchers, AI developers and data scientists, AI professionals, members of Digital Innovation Hubs, participants from related initiatives and projects, and anyone interested in sustainable AI, Green AI, and the societal and environmental impacts of AI.

Speakers

Seyyed Mahyar Tofighi Milani, Doctoral Researcher, Aalto University, Finland.

Peter Pavlík, Researcher, Kempelen Institute of Intelligent Technologies, Slovakia.

Moderator

Erik Johannes Husom, Research Scientist, SINTEF, Norway.

Program

Date 3^rd June 2026 14:00-14:45 CEST	Time	Presentation title
	14:00-14:05	Welcome and introduction
	14:05-14:25	Inertia-Aware Optimal Power Flow Using Physics-Informed Neural Networks in IBR-Dominated Power System
	14:25-14:45	How Green is Physics-Informed Machine Learning for Solar Power Forecasting?
	14:45-15:00	Closing remarks and additional time for questions

Topics & Abstracts

Title:	Inertia-Aware Optimal Power Flow Using Physics-Informed Neural Networks in IBR-Dominated Power System
Speaker:	Seyyed Mahyar Tofighi Milani
Bio:	Mahyar is a PhD researcher in electrical engineering, working on the modeling, control, and market integration of low-inertia power systems with high penetration of renewable energy resources.
Abstract:	The Optimal Power Flow (OPF) problem is central to the secure and economic operation of modern power systems. However, increasing renewable energy penetration, and decreasing system inertia pose significant challenges to conventional optimization-based OPF solvers. While machine learning approaches have demonstrated substantial computational speed-ups, purely data-driven methods often suffer from data dependency, limited generalization, and lack of guaranteed physical feasibility. This paper proposes a physics-informed neural network (PINN) framework for solving the OPF problem in renewable energy–dominated, low-inertia power systems. In contrast to conventional OPF formulations, the model explicitly incorporates a location-aware inertia constraint based on the concept of system inertia strength, which accounts for the electrical distance between generation units and disturbance locations. Simulation results on a 6 GW test system demonstrate high accuracy. The mean absolute error (MAE) for both the training and testing datasets is approximately 0.045% of the total system capacity. These results confirm that the proposed PINN framework can achieve highly accurate OPF solutions while explicitly enforcing physical and inertia-related constraints. Overall, the findings highlight the potential of physics-informed learning to enable secure, efficient, and computationally scalable OPF for future low-inertia power systems.

Title:	How Green is Physics-Informed Machine Learning for Solar Power Forecasting?
Speaker:	Peter Pavlík
Bio:	Peter is a researcher focused on physics-informed machine learning and its applications in weather, climate, and geosciences. His work incorporates physical and domain knowledge into data-driven models with the aim of making them more accurate, trustworthy and less energy-demanding. He is particularly interested in environmentally responsible applications of AI, including improving renewable energy systems, enhancing early warning systems for extreme weather, and supporting climate change mitigation and adaptation strategies. Peter holds a Master’s degree in Intelligent Software Systems from the Faculty of Informatics and Information Technologies at the Slovak University of Technology. He is currently a PhD candidate at the Faculty of Information Technology at Brno University of Technology, where his research focuses on physics-informed machine learning for forecasting tasks. As part of his doctoral work, he developed and published a novel physics-informed neural network architecture for precipitation nowcasting – LUPIN. During his PhD, Peter has completed a research visit at Delft University of Technology (Faculty of Civil Engineering and Geosciences) and at is currently on a research visit at Know Center in Graz, working on interdisciplinary problems in geoscience and applied machine learning. He has presented his work at venues such as the EGU General Assembly and the ESA-ECMWF Machine Learning Workshop, among others.
Abstract:	Physics-informed machine learning (PIML) has emerged as a promising paradigm that integrates physical laws with data-driven models to improve accuracy and generalization while promising reducing data and computation needs. This project examines the claim of environmental and computational efficiency of PIML in the context of solar power forecasting, a domain essential for maintaining grid stability amid the growing share of renewables. Using a real-world solar irradiance and power output dataset, we will develop and compare data-driven, physics-based, and hybrid forecasting models in terms of predictive accuracy, training energy consumption, and carbon footprint to guide responsible AI deployment in renewable energy forecasting.