New York City transit agencies are expanding artificial intelligence (AI) pilots aimed at detecting subway infrastructure problems before they cause delays, targeting a maintenance challenge that has persisted across one of the world’s most heavily used rail networks.
The initiative comes at a key moment. A 2025 State Comptroller Report found that roughly 82% of New York City’s 2.7 million trains ran on time, with nearly half of the year’s delays caused by infrastructure and equipment problems. Current monitoring practices remain manual, reactive and resource intensive. The pilots now underway aim to change that.
The Use Cases
The Metropolitan Transportation Authority (MTA), which serves commuters around New York and Connecticut, partnered with Google Public Sector on a program called TrackInspect. Through the program, Google Pixel smartphones are retrofitted onto subway cars. The phones capture vibrations and sound patterns through built-in sensors during normal service. That data goes in real time to cloud-based AI systems that generate predictive maintenance insights. Track inspectors then physically verify locations the system flags, keeping humans in the decision loop.
According to a May 14 report from StateScoop, the Port Authority of New York and New Jersey are working with Delphisonic to install onboard AI-powered vibration and temperature sensors on railcars to detect mechanical issues and help prevent failures.
Meanwhile, Ontra Mobility will use AI to analyze subway ridership and operations data to predict travel demand, recommend service design changes and keep trains punctual, StateScoop reported.
How Other Networks Are Solving the Same Problem
New York is not alone. In Singapore, SMRT in April unveiled JARVIS, an AI platform that consolidates nearly 40 years of operational and engineering data.
Advertisement: Scroll to Continue
Maintenance teams in Singapore are limited to a narrow three-hour nightly window to perform essential repairs, according to an April report from ComputerWeekly. JARVIS geo-tags faults in real time, allowing engineers to go directly to the equipment that needs attention within that window. The platform uses machine learning and generative AI to spot early signs of equipment faults and helps technicians analyze issues through a natural-language interface, TechGoondu reported. SMRT’s rail network supports more than two million passenger journeys each day, according to a press release from Oracle.
In Germany, Deutsche Bahn uses AI-driven forecasting to schedule wheelset replacement and track maintenance on its S-Bahn network, moving from fixed calendar cycles to data-driven intervention. The program analyzes sensor data from trains and infrastructure to proactively schedule maintenance, with the goal of minimizing disruptions and improving service reliability across one of Europe’s largest rail networks.
Back in New York, the MTA says its vision is to scale AI-driven track inspections across the entire subway system, using real-time insights to reduce unplanned service disruptions. Right now, each of the current pilots is only a short-term proof of concept.
What New York’s efforts and Singapore’s JARVIS share is the same underlying principle: surface the problem before it surfaces itself. The question for the MTA is whether the solution will hold at scale.
For all PYMNTS AI and digital transformation coverage, subscribe to the daily AI and Digital Transformation Newsletters.
Can AI Prevent the Next Subway Delay? | PYMNTS.com Top World News Today.
Hence then, the article about can ai prevent the next subway delay pymnts com was published today ( ) and is available on TOP world News today ( Middle East ) The editorial team at PressBee has edited and verified it, and it may have been modified, fully republished, or quoted. You can read and follow the updates of this news or article from its original source.
Read More Details
Finally We wish PressBee provided you with enough information of ( Can AI Prevent the Next Subway Delay? .. PYMNTS.com )
Also on site :