Jinzhao Tian

Jinzhao Tian is a Ph.D. candidate in Building Performance and Diagnostics at Carnegie Mellon University, specializing in data-driven analytics for smart and healthy buildings. His research focuses on understanding how HVAC system operation and faults affect indoor air quality, energy performance, and occupant well-being at scale.

He develops end-to-end data pipelines and advanced analytics workflows using large, real-world building datasets. His work includes processing over 100 million time-series records from U.S. federal buildings, integrating building automation system data, indoor air quality sensors, energy meters, and weather information. By applying machine learning and causal inference methods, he quantifies the operational impacts of HVAC faults and supports data-driven prioritization of maintenance actions and performance improvements across building portfolios.

His contributions include peer-reviewed publications in building energy analytics and intelligent control, as well as more than 800 pages of technical reports for the U.S. General Services Administration on energy performance, indoor air quality, and building operations. He has also presented this work to both research and industry audiences, including national forums focused on healthy and high-performance buildings.

Through research, teaching support, and collaboration with public-sector partners, Jinzhao aims to advance scalable and trustworthy AI-driven analytics that improve building performance while supporting occupant health and sustainability.

Research Interests

• Indoor Air Quality (IAQ)
• Building Energy Performance
• HVAC Fault Detection and Diagnostics (FDD)
• Data Driven Building Analytics

Affiliation

• Center for Building Performance and Diagnostics