Reliable learning for energy systems
Designing machine learning methods that respect operational constraints and improve decisions in power and energy applications.
Power systems, learning, and reliability
Mohamad Chehade
Ph.D. student in Electrical and Computer Engineering at The University of Texas at Austin.
I work on reliable machine learning for power and energy systems, with a focus on risk-aware transfer in reinforcement learning and physics-aware supervised learning.
About
Building dependable learning tools for grid operations.
Welcome! I am a Ph.D. student in Electrical and Computer Engineering at The University of Texas at Austin, where I am advised by Dr. Hao Zhu. My research sits at the intersection of reliable AI, reinforcement learning, and power system operations.
I earned my B.Eng. in Electrical and Computer Engineering, with a minor in Mathematics, from the American University of Beirut. At AUB, I worked with Dr. Rabih Jabr and Dr. Sami Karaki. I have also interned at Los Alamos National Laboratory, working with Dr. Wenting Li, Dr. Brian Bell, and Dr. Russell Bent.
Current Ph.D. student, UT Austin
Focus Reliable AI for energy systems
Interests Soccer, basketball, Formula 1
Research Focus
Methods that keep performance and reliability in view.
Risk-aware reinforcement learning
Studying transfer, adaptation, and safety-aware policies for sequential decision-making under uncertainty.
Physics-aware supervision
Combining data-driven models with grid structure, optimization, and verifiability for more dependable predictions.
News
Recent updates
Two papers accepted to the 2026 IEEE Power & Energy Society General Meeting: Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid and Carbon-aware Market Participation for Building Energy Management Systems.
NEO-Grid accepted to HICSS 2026.
BOOST accepted to TPEC 2025.
Awarded Best Graduate Presentation Award at NAPS 2024.
Education
Academic path
B.Eng. in Electrical and Computer Engineering
American University of Beirut
Minor in Mathematics