Two years after the U.S. Department of Energy’s Oak Ridge National Laboratory provided a model of nearly every building in America, commercial partners are using the tool for tasks ranging from designing energy-efficient buildings and cities to linking energy efficiency to real estate value and risk. International companies like Google and SmithGroup are sharing the benefits by making the resulting data publicly available. Since the buildings sector accounts for 40% of American energy consumption, increasing its efficiency is vital to national decarbonization goals.

Dozens of companies have requested data from ORNL’s Automatic Building Energy Modeling software suite, or AutoBEM, said project leader Joshua New. He and his team developed AutoBEM using high-performance computing to process layers of imaging data with information about individual buildings, such as their size, use, construction materials and heating and cooling technologies.

“The unifying theme is to create a digital twin of our nation’s buildings,” New said. “We can simulate market-relevant ways to reduce energy use and offset with renewable sources.”

The software has simulated energy use for 123 million structures, representing 98% of U.S. buildings. New’s team is updating the software this year for even greater building detail and accuracy.

Google is using AutoBEM to improve its free Environmental Insights Explorer tool, which launched in 2018 to help cities worldwide recognize sources of greenhouse gas and reduction opportunities. Saleem Van Groenou, product manager for Environmental Insights Explorer, said Google wants to incorporate more precise energy efficiency simulations for buildings.

“Oak Ridge has much deeper expertise in building energy systems and modeling management and action than we do,” Van Groenou said. “We can now help cities focus more on what changes should be made, then track the impact of those changes over time.”

Google is combining its trove of building data with ORNL’s ability to scale up energy models and develop machine-learning algorithms, Van Groenou said.

Google is one of five major companies contributing data, staff time and equipment to AutoBEM partnerships.