Semiha Ergan ,

Ph.D.

Buildings produce a large share of New York's greenhouse gas emissions, but predicting future energy demand — essential for reducing those emissions — has been hampered by missing data on how buildings currently use energy.

Semiha Ergan in NYU Tandon’s Civil and Urban Engineering (CUE) Department, is pursuing research that addresses the problem from two directions. Both projects, conducted with CUE Ph.D. student Heng Quan, apply machine learning to forecast building energy use, including short-term (day-ahead) predictions to support grid peak management and longer-term (monthly) projections of how climate change may affect energy demand and building-grid interactions.

First, Ergan and Quan introduced STARS (Synthetic-to-real Transfer for At-scale Robust Short-term forecasting), which predicts 24-hour-ahead electricity use across buildings in New York State. The practical problem, Ergan said, is that most buildings lack the historic submetered sensor data that conventional forecasting models require.

"In reality, most buildings only have monthly electricity use data,” said Ergan, noting that detailed sensor data remains rare even in buildings subject to energy reporting requirements like New York City’s Local Law 84 and 87.

STARS sidesteps that limitation by training on thousands of simulated building profiles from the U.S. Department of Energy's ComStock library, then transferring what it learns to real buildings. Tested against actual consumption data from 101 New York State buildings, the model achieved 12.07 percent error in summer and 11.44 percent in winter, below the roughly 30 percent threshold that industry guidelines consider well-calibrated.

The 24-hour forecast window is designed for demand response programs. During heat waves, grid operators need day-ahead predictions to coordinate building energy use — pre-cooling spaces before peak hours, for example — to prevent blackouts. "Eventually, this will help advance grid efficiency and citizen comfort,” said Ergan.

In complementary work with Quan, Ergan is examining how climate change will impact New York City buildings’ energy use over longer timeframes. They developed a physics-based machine learning model to address the poor extrapolation performance of purely data-driven methods.

The model is trained on real building energy consumption data from NYC Local Law 84 covering over 1,000 buildings and projects monthly energy use under warming scenarios of 2 to 4 degrees Fahrenheit. By incorporating physics-based knowledge into the machine learning framework, it enables robust projections even without historical data from the future climate conditions buildings will face.

Their methodology revealed, for example, that a 4-degree increase could raise summer energy use by an average of 7.6 percent.

Together, the two projects address building energy use from complementary time scales: short-term forecasting enables day-ahead grid coordination during peak demand events, while long-term climate projections inform infrastructure planning and policy. Both ultimately support greenhouse gas reduction goals, as operational energy use converts directly to emissions.

The research was funded by NYU Tandon's IDC Innovation Hub.

Heng Quan and Semiha Ergan. 2025. Sim-to-Real Transfer Learning for Large-Scale Short-Term Building Energy Forecasting in Sustainable Cities. In Proceedings of the 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys '25). Association for Computing Machinery, New York, NY, USA, 86–95. https://doi.org/10.1145/3736425.3772006

The United States recorded 28 natural disasters causing at least $1 billion in damages each in 2023, the highest number in the nation's history. Now researchers at NYU Tandon are helping develop a robotic system that could significantly reduce disaster recovery times while improving efficiency for contractors working in confined spaces.

Along with colleagues from New Jersey Institute of Technology, who led the project, and a researcher from The University of Scranton, the Tandon team led by Maurizio Porfiri and Semiha Ergan is part of a three-year, $5 million U.S. National Science Foundation (NSF)-funded project to create the Kastor robotic system. The funding comes from the NSF Directorate for Technology, Innovation and Partnerships, which supports research that brings together multiple disciplines and sectors to solve complex societal and operational challenges.

This Phase 2 award follows a previous $650,000 Phase 1 grant that developed a prototype robot and algorithms.

The Kastor robotic system uses swarms of self-assembling robots to transport equipment and clear debris in disaster zones, addressing a persistent challenge in disaster response: much of the workforce effort goes toward moving supplies and removing debris rather than critical tasks like searching for survivors.

The technology takes its design cues from fire ants and slime molds. Fire ants can link their bodies to form bridges over difficult terrain, while slime molds create efficient transport networks across varied surfaces. The Kastor system applies these biological strategies to create networks of flat metal robotic tiles that can autonomously reconfigure themselves as conditions change.

The tiles move themselves into position and use wheels and treads to transport pallets across disaster sites without human intervention. Algorithms developed by the research team guide their assembly and movement patterns.

Porfiri — who directs NYU's Center for Urban Science + Progress (CUSP) and is Institute Professor in the departments of Mechanical and Aerospace Engineering, Biomedical Engineering, and Civil and Urban Engineering (CUE) — brings expertise in urban science and virtual reality to the project. His role focuses on ensuring the technology integrates with existing disaster response workflows in urban environments.

Ergan — an associate professor in CUE, and on the faculty of CUSP, Institute of Design and Construction (IDC) Innovation Hub, and C2SMARTER transportation center — is leading virtual and on-site pilot studies that will test the system in realistic construction and recovery scenarios.

"Each community faces different challenges when disasters strike, and current response methods often require inefficient manual labor for debris removal and supply transport," Porfiri said. The project team has consulted with police officers, emergency responders, contractors and construction companies to understand operational requirements.

"We want to bring the high-tech automation of distribution facilities and smart warehouses to messy, unstructured outdoor environments," said Petras Swissler, an assistant professor of mechanical and industrial engineering at NJIT and the project's principal investigator.

Beyond disaster response, the researchers found the same challenges exist in construction projects, where efficiency improvements have lagged behind other industries.

"This technology will also assist at construction sites where space is tight and the ability to navigate in multiple directions while carrying dirt and construction materials is limited," Ergan said.  

The project will develop a production-ready robotic system, create interfaces for operators to control the robot swarms, and conduct pilot studies in both disaster response and construction settings. Along with Porfiri and Ergan, the other co-principal investigators are Simon Garnier, a biology professor at NJIT, and Jason Graham, a mathematics professor at The University of Scranton.