A new study examining tropical cyclone forecasts in the Atlantic Ocean suggests that artificial intelligence could provide valuable additional guidance for predicting when and where tropical disturbances may develop into tropical storms.
Led by Sharan Majumdar, a professor of atmospheric sciences at the University of Miami Rosenstiel School of Marine, Atmospheric, and Earth Science, and others, the study compares the European Centre for Medium-Range Weather Forecasts (ECMWF)'s traditional Integrated Forecasting System (IFS) with its newer Artificial Intelligence Forecasting System (AIFS).
The researchers analyzed African easterly waves and tropical cyclone development across the Atlantic from 2020 through 2024.
African easterly waves are westward-moving atmospheric disturbances that form over sub-Saharan Africa during the boreal summer. Some of them eventually organize into tropical cyclones, making their evolution an important part of hurricane forecasting.
The study, published in the journal Weather and Forecasting, found that ECMWF's conventional forecasting system improved over the period examined. In 2023, the grid spacing of the IFS ensemble was reduced from 18 kilometers to 9 kilometers, while average probabilities of tropical cyclone formation generally increased over the years.
But Majumdar and his collaborators found that ECMWF's new AI system can offer a different and potentially useful perspective.
Among 18 tropical cyclones that developed in 2024, the AIFS ensemble frequently produced higher probabilities of development than the IFS at lead times of roughly 84 to 120 hours, particularly for stronger tropical waves. At shorter lead times of 36 to 48 hours, however, the AIFS ensemble generally produced lower probabilities, especially for weaker systems.
That difference highlights one of the challenges of forecasting tropical cyclogenesis: the signal that a disturbance will become a tropical cyclone can change substantially as the event approaches.
The research team found that conventional IFS probabilities often increased sharply when forecasts moved from three days to two days before a storm was officially named. The study also found considerable variation from storm to storm, depending in part on the wind-speed threshold used to define development.
The AI system also showed advantages in forecasting the location of developing tropical systems. The average position error of the AIFS ensemble mean was often smaller than errors from the AIFS single forecast, the deterministic IFS and the IFS ensemble mean.
The findings do not suggest that AI should replace traditional numerical weather prediction, Majumdar said. Instead, AI forecasts can complement the established IFS, providing forecasters with another source of information when assessing the potential for tropical cyclone formation.
The study, supported by a National Science Foundation (NSF) grant AGS-2438140 and European Centre for Medium-Range Weather Forecasts, comes as ECMWF continues to integrate AI into operational weather forecasting. AIFS became operational in 2025, marking a significant expansion of machine-learning-based forecasting alongside ECMWF's physics-based numerical models.
For Atlantic hurricane forecasting, the potential significance is substantial, Majumdar pointed out. "Better identification of developing systems several days in advance could give forecasters more time to monitor disturbances, assess possible tracks and communicate emerging risks," he said.
Majumdar collaborated on the study with scientists from ECMWF, the NSF National Center for Atmospheric Research, and the University of Bonn. One of the collaborators included Quinton Lawton, a former Ph.D. student of Majumdar's, who is now an assistant professor in the Department of Earth, Atmosphere and Environment at Northern Illinois University.
The study results point toward a future in which traditional physics-based forecasting and AI-generated guidance work side by side or are combined, potentially giving forecasters a more complete picture of which Atlantic tropical waves are most likely to become the next named storm, according to Majumdar.
