Arpad Toldy

Arpad Toldy serves as Visitor Faculty in the Department of Energy and Mechanical Engineering and Energy Conversion and Systems research group, focusing on sustainable energy systems and computational methods for fuel engineering.

His academic credentials include:

• Doctoral degree in Engineering and Technology from Singapore-MIT Alliance (awarded May 13, 2014)
• Bachelor's degree in Engineering and Technology from Budapest University of Technology and Economics (awarded January 7, 2010)

Dr. Toldy's research centers on green hydrogen cost reduction strategies, dynamic operation of proton exchange membrane electrolyzers, and machine learning applications for fuel property prediction. His work addresses techno-economic assessments of $$\text{CO}_2$$-based methanol synthesis and low-carbon fuel adoption in marine transportation, contributing directly to UN Sustainable Development Goals for affordable clean energy (SDG 7) and climate action (SDG 13). Key methodologies integrate support vector machines with industrial fuel data and analyze revenue streams for hydrogen production systems.

Analysis of his 2021-2025 publications reveals accelerating focus on green hydrogen economics and electrolyzer operational challenges, with machine learning consistently applied to complex energy system optimization. His critical review on proton exchange membrane electrolyzers has become a high-impact reference (86+ Scopus citations), while recent work examines behavioral economics of low-carbon fuel adoption.

Dr. Toldy participated in the EU Recovery and Resilience Facility project 'AI-guided $$\text{CO}_2$$ Conversion' (2022-2024) as project member, developing artificial intelligence frameworks for $$\text{CO}_2$$-to-methanol conversion processes. This collaborative initiative involved cross-institutional teams focusing on stability optimization and learning system integration.

His research activities are anchored in the Energy Conversion and Systems group, which investigates advanced energy technologies through experimental and computational approaches. Current projects emphasize real-world integration of renewable hydrogen systems and machine learning-driven fuel characterization for decarbonized transportation sectors.