The hidden heatwave: Thermal hazards in the New York City subway system

Authors

• Abdou Rachid Bah, CUNY New York City College of TechnologyFollow
• Maimuna Muntaha, Stanford University
• Lenny L. Metlitsky, Cornell UniversityFollow
• Cesar Pascal Vasquez, CUNY City CollegeFollow
• Tyler Ayala, CUNY City CollegeFollow
• Isaac Morel Lopez, CUNY City CollegeFollow
• Shaquan A. Larose, CUNY New York City College of TechnologyFollow
• Kingston Ditsch, CUNY New York City College of TechnologyFollow
• Kip Nielsen, University of Kansas
• Shaunak Sharma, University of Michigan - Ann Arbor
• Reginald U. Avila-Ortega Blake, CUNY New York City College of TechnologyFollow
• Hamidreza I. Norouzi, CUNY New York City College of TechnologyFollow

Document Type

Article

Publication Date

12-1-2026

Abstract

Underground transit systems (Subway) are susceptible to frequent heat waves, which pose serious health and safety risks to commuters and transit workers. Yet, the patterns and extent of temperature changes within the subway system remain insufficiently understood. To address this gap, we conducted a study of thermal variability across 112 subway stations in New York City. Temperature and relative humidity were measured at both platform and street levels. Results show that during the summer, 70% of subway stations had platform heat index higher than street level heat index. We also developed a machine learning forecasting model to predict platform-level temperatures. The model achieved strong predictive performance of (R² = 0.85 at platform-level). These findings highlight stations where heat management is most needed and demonstrate the potential for predictive tools to inform targeted interventions that improve the resilience and safety of urban transit systems.

Comments

This article was originally published in Building and Environment, available at https://doi.org/10.1016/j.buildenv.2026.115327

This work is distributed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).  

This research was funded by the National Science Foundation Research Experience for Undergraduates (NSF-REU) award 2447604, the NSF Improving Undergraduate STEM Education (NSF-IUSE) award 2327431, Integrated NSF Support Promoting Interdisciplinary Research and Education (INSPIRE) Program award 2228173, and supported by the Center for Remote Sensing and Earth System Sciences (ReSESS) at the New York City College of Technology. We would also like to thank more than 50 high school and undergraduate students involved in the data collection efforts. We especially would like to thank: Paul Malique, Damilola Babs-Ogundeji, Abdoul Nana, Rean Shahidullah, Kiran Maharjan, Kevin Balbuena, Brigette Alejandro, Mojgan, Zamani, Babacar Sarr, Hailah Nagi, Maria Hashmi, Isatu Jalloh, Lou Kale, Alexander Abreu Ramirez, Anton Nikitin, Christ Augustin, Garvey Grandchamps, Dana Michaud, Anthony Gonzalez, Grace Sinhart, Aissatou Bah, Mahin Kamal, Temur Rakhmatov, Cayla Feaster, Aidan Mease, Giorgi Abshilava, Javier Aguilar, Rachel Cheng, Johanna Onofre, Jonathan Pierre, Kayla Punin, Munike Sah, Chloe Wu, Shirley Ricon Padilla, Ryan Guan, Adisa Sokoli, Roberto Zheng Yu, Vivian Yu, Medha Das, Amani Hall, Aida Seck, Genesis Guzman, Ahona Shashee, Brenden Moy, Mohamed Traore, Joshua Munoz, Edison Remache, Delaylaa Polanco, Oliver Steyn-Reimer, Davon Chen, Jaden Wu, and Shelby Chen. We would also like to thank the MTA for their collaboration. The interpretations and conclusions presented in this work are solely those of the authors and do not necessarily represent the official views of MTA and the funding agencies.