Liang Zhang

Liang Zhang is a Researcher at the University of Arizona, specializing in text- and image-based scientific knowledge extraction, deep reinforcement learning, network security, and signal processing. His work focuses on integrating large language models (LLMs) into building energy modeling, automation, and predictive systems. He leads efforts in developing automated workflows for energy analysis, fault detection, and data-driven decision-making in smart building systems. His research bridges AI, computational physics, and building science to enhance energy efficiency and sustainability.

Key projects include the EPlus-LLM platform for automated building simulations, ComStock™ energy data releases, and studies on sensor impacts in building controls. His methodologies combine physics-informed models with machine learning to address challenges in energy systems. Zhang collaborates across disciplines to advance AI applications in energy sectors, emphasizing scalable solutions and interpretability in control systems.

His publications highlight innovation in LLM-based automation, feature selection for predictive models, and energy load profiling for sustainable urban systems. He actively engages in developing open data standards and simulation testbeds for energy research communities.