The Metropolitan Transportation Authority (MTA) has launched a new pilot program with Google Public Sector that uses artificial intelligence to detect subway track defects before they cause service disruptions.
The program, called TrackInspect, mounts Google Pixel smartphones onto subway cars to capture vibrations and sounds that might indicate track problems. These smartphones, equipped with standard off-the-shelf cases, are currently installed on R46 subway cars running on the A line.
“By being able to detect early defects in the rails, it saves not just money but also time – for both crew members and riders,” said New York City Transit President Demetrius Crichlow. “This innovative program – which is the first of its kind – uses AI technology to not only make the ride smoother for customers but also make track inspector’s jobs safer by equipping them with more advanced tools.”
How the Technology Works
The system relies on sensors built into the smartphones, including accelerometers, magnetometers, gyroscopes, and external microphones. These sensors collect data about track conditions as trains move through the subway system.
When the sensors detect unusual vibrations or sounds, the information is immediately sent to cloud-based systems. There, AI and machine learning algorithms analyze the data to identify potential track issues.
In the initial testing phase, TrackInspect collected 335 million sensor readings, one million GPS locations, and 1,200 hours of audio. This data was combined with the MTA‘s existing database of track problems.
The system has shown promising results. According to Google Public Sector Vice President Brent Mitchell, “The TrackInspect pilot program identified 92% of the defect locations found by track inspectors, illustrating that enhanced data analysis can help expedite problem identification and resolution to improve railway reliability.”
Similar Posts
Human Oversight Remains Essential
While the AI technology is impressive, human inspectors still play a crucial role. New York City Transit Department of Subways Assistant Chief Track Officer Robert Sarno explained the collaboration between technology and human expertise:
“How it works is the prototype sends a soundbite or noise clip showing heavy vibration or noise, and then our inspectors follow up by walking the track and verifying any issue found,” said Sarno. “We then compare that with whatever we find to teach the device noise and decibel levels and then work from there. That’s how we are able to instruct the prototype on what are normal sounds and vibrations, and what are not, and move along through the process.”
This human verification helps train the AI model to become more accurate over time.
Benefits for NYC Subway Riders
The TrackInspect program complements the MTA’s existing track geometry cars, which already collect data on track conditions. When used together, these technologies can help the MTA find and fix track issues faster.
For subway riders, this could mean fewer delays and a smoother ride. By identifying potential problems before they cause service disruptions, the MTA hopes to improve the reliability of its subway system.

The MTA is now looking to expand on the initial success of TrackInspect. The agency has released a Request for Expressions of Interest for other companies that have developed sensors or analytical capabilities that could work with this system.
TrackInspect began as a proof-of-concept prototype developed by Google Public Sector exclusively for the MTA at no cost to the Authority. The results were officially presented by the MTA at a Google Public Sector event in New York City.