The work was led by Sharan Majumdar, a professor of atmospheric sciences at the University of Miami’s Rosenstiel School of Marine, Atmospheric, and Earth Science, in collaboration with scientists from ECMWF, the NSF National Center for Atmospheric Research, and the University of Bonn. Among the collaborators was Quinton Lawton, a former doctoral student of Majumdar’s who is now an assistant professor in the Department of Earth, Atmosphere and Environment at Northern Illinois University. The team focused their analysis on the Atlantic basin from 2020 through 2024, a five-year window that captures both steady improvements in conventional forecasting and the dramatic arrival of AI-based alternatives.

At the heart of the study is a comparison between two ECMWF systems. The first is the Integrated Forecasting System, or IFS, the center’s traditional numerical weather prediction model, which simulates the atmosphere by solving the physical equations that govern fluid motion, thermodynamics, and moisture on a three-dimensional grid. The second is the Artificial Intelligence Forecasting System, or AIFS, a machine-learning model trained on decades of historical atmospheric data to learn the patterns of atmospheric evolution directly. Rather than stepping forward through time with explicit physics calculations, the AIFS produces forecasts in a fundamentally different way, and ECMWF made it operational in 2025, marking a significant expansion of machine-learning-based forecasting alongside its physics-based numerical models.

The specific targets of the analysis were African easterly waves, the westward-moving atmospheric disturbances that form over sub-Saharan Africa during the boreal summer. These waves are the seedlings of many Atlantic hurricanes. As they roll off the West African coast and cross the tropical Atlantic, only some of them manage to organize into tropical cyclones, and identifying which ones will succeed is a central challenge of hurricane forecasting. The timing and location of this transition, known as tropical cyclogenesis, can determine how much warning coastal populations receive, which makes any improvement in lead time potentially life-saving.

The researchers first established a baseline by examining how the conventional IFS performed across the study period, and the results show genuine progress. In 2023, the grid spacing of the IFS ensemble was reduced from 18 kilometers to 9 kilometers, effectively doubling the model’s resolution and allowing it to represent smaller-scale tropical features with greater fidelity. Over the same years, the average probabilities of tropical cyclone formation produced by the conventional system generally increased, indicating growing confidence and skill in detecting developing systems. These improvements reflect the steady, incremental gains that operational forecasting centers have delivered through better observations, more sophisticated model physics, and finer computational grids.

But the more striking findings emerged when the team turned to the AI system. Among the 18 tropical cyclones that developed in the Atlantic in 2024, the AIFS ensemble frequently produced higher probabilities of development than the IFS at lead times of roughly 84 to 120 hours, which corresponds to about three and a half to five days before formation. This advantage was particularly pronounced for stronger tropical waves, the very systems that forecasters most want to flag early. In other words, when a disturbance showed signs of being a serious candidate for development, the AI model often recognized that potential days sooner than the traditional ensemble did.

The picture reversed at shorter lead times. At 36 to 48 hours before formation, the AIFS ensemble generally produced lower probabilities of development than the IFS, especially for weaker systems. This contrast highlights one of the fundamental challenges of forecasting tropical cyclogenesis: the signal that a disturbance will become a tropical cyclone can change substantially as the event approaches. A wave that looked promising five days out may struggle to consolidate, while a seemingly innocuous disturbance can rapidly organize. The study also found that conventional IFS probabilities often increased sharply when forecasts moved from three days to two days before a storm was officially named, and that there was considerable variation from storm to storm, depending in part on the wind-speed threshold used to define development. Cyclogenesis, it turns out, is not a single crisp event but a process whose detectability depends on both the system and the definition applied to it.

The AI system also showed advantages in forecasting where developing tropical systems would be located. The average position error of the AIFS ensemble mean was often smaller than the errors from the AIFS single forecast, the deterministic IFS, and the IFS ensemble mean. Position accuracy matters enormously in practice, because a disturbance’s location relative to warm ocean waters, wind shear, and dry air strongly influences its chances of survival, and because forecasters use position guidance to decide where to focus monitoring resources, aircraft reconnaissance, and public communications. An ensemble mean that consistently pins down the location of a developing system gives forecasters a more reliable anchor for their assessments.

Importantly, the findings do not suggest that AI should replace traditional numerical weather prediction. Majumdar emphasized that AI forecasts can complement the established IFS, providing forecasters with another source of information when assessing the potential for tropical cyclone formation. This framing reflects a growing consensus in the operational meteorology community: machine-learning models trained on historical reanalyses can capture large-scale patterns with remarkable efficiency and at a fraction of the computational cost of physics-based simulation, but the two approaches have different failure modes, and agreement or disagreement between them is itself informative. A forecaster seeing high development probabilities from both systems at a four-day lead time has a very different situation than one seeing a divergence between the two.

The study was supported by a National Science Foundation grant, AGS-2438140, and by the European Centre for Medium-Range Weather Forecasts, and it arrives at a moment of rapid institutional change. ECMWF’s decision to make the AIFS operational in 2025 signals that machine-learning forecasting has moved from research curiosity to production tool at one of the world’s leading centers. For Atlantic hurricane forecasting, Majumdar pointed out, the potential significance is substantial. Better identification of developing systems several days in advance, he said, could give forecasters more time to monitor disturbances, assess possible tracks and communicate emerging risks. 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. As the 2020s progress and both classes of models continue to improve, the practical question is shifting from whether AI belongs in the hurricane forecaster’s toolkit to how best to blend its strengths with the physics-based systems that have anchored tropical cyclone prediction for decades.

Subject of Research: Artificial intelligence and numerical model forecasting of Atlantic tropical cyclogenesis from African easterly waves

Article Title: AI’s eye on the tropics

Article References: AI’s eye on the tropics. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: tropical cyclones, hurricane forecasting, artificial intelligence, ECMWF, African easterly waves, tropical cyclogenesis, ensemble forecasting, machine learning, Atlantic basin, Weather and Forecasting, numerical weather prediction, University of Miami

The announcement positions Mississippi State at the center of one of the most consequential research enterprises in the region. Cooperative Institutes are NOAA’s mechanism for extending its scientific reach into the academic community, pairing federal mission priorities with university expertise in modeling, observations and workforce training. CINGA joins a national network of 16 such institutes, which together encompass 80 universities and research institutions across 33 states and the District of Columbia. Within that network, the new institute will be affiliated with NOAA’s Atlantic Oceanographic and Meteorological Laboratory in Miami, Florida, a facility best known for hurricane research and atmospheric field campaigns.

Steve Thur, NOAA’s assistant administrator for Oceanic and Atmospheric Research, framed the award as a continuation of a proven partnership. “This collaboration builds on the 20-year partnership between NOAA and Mississippi State University through the Northern Gulf Institute,” Thur said. “CINGA will advance and support NOAA’s mission to apply science-based decision-making to the northern Gulf region.” The language reflects the institute’s core mandate: translating research into tools that resource managers, emergency officials and coastal policymakers can actually use when storms, oil spills, harmful algal blooms or shifting fish stocks threaten Gulf communities.

Mississippi State President Mark E. Keenum said the designation reinforces the university’s standing as a national leader in coastal and ocean research while opening new opportunities for Mississippi scientists, students and communities. “Mississippi State University is honored by NOAA’s selection and grateful for the opportunity to continue and expand this important partnership,” Keenum said. “This designation recognizes the world-class expertise of our faculty, researchers and staff, as well as the strength of the partnerships we have built throughout the Gulf region.” He added that the institute’s work is expected to generate discoveries that benefit coastal communities, strengthen economic opportunity and support the long-term sustainability of what he described as one of America’s most important natural resources.

The physical and computational infrastructure underpinning the partnership is substantial. Mississippi State and NOAA share a building at NASA’s Stennis Space Center on the Mississippi Gulf Coast, a site designed to keep federal and academic researchers working side by side rather than across institutional boundaries. NOAA has also invested in supercomputing systems managed by the university, and two of those systems have been ranked among the most powerful in the world. That computing capacity matters enormously for the institute’s scientific agenda, because modern environmental prediction depends on high-resolution numerical models of the atmosphere and ocean that demand enormous processing power to run at operational speeds.

The research portfolio already produced by the partnership illustrates the range of that capability. Among its most visible achievements is the advancement of large uncrewed aircraft systems, or drones, for storm response. These platforms can fly into and around severe weather in ways that are too dangerous or expensive for crewed aircraft, gathering data that helps NOAA and emergency officials better understand which areas face the greatest risk of flooding during weather events. That kind of observational technology feeds directly into the forecasting improvements that CINGA is designed to pursue, closing the gap between raw measurements and actionable warnings for people in the path of a storm.

Through the new institute, Mississippi State researchers and their partners will advance work supporting fisheries, coastal economies, maritime industries, hurricane and weather forecasting, ecosystem health and community resilience across the Gulf Coast, with particular attention to Mississippi’s coastal communities and industries. The institute’s major research themes include advancing environmental modeling and analysis technologies, improving forecasting capabilities for weather, ocean conditions and environmental hazards, promoting sustainable development of marine and coastal resources, and enhancing data stewardship and accessibility across the Gulf ecosystem. The data theme is increasingly central to modern environmental science: observations gathered by satellites, buoys, aircraft and ships are only useful if they can be quality-controlled, archived and delivered to modelers and decision-makers in near real time.

CINGA is structured as a consortium rather than a single-campus operation, bringing together researchers from nine institutions across the Gulf region. In addition to Mississippi State, the partners include Florida A&M University, Florida State University, Jackson State University, Louisiana State University and Texas A&M University, along with the University of Alabama in Huntsville, the University of Southern Mississippi and the Dauphin Island Sea Lab. That geographic and institutional spread matters for a system as large as the Gulf of Mexico, where ocean currents, river plumes, hurricane tracks and fishery stocks ignore state lines. It also embeds historically underrepresented institutions, including two historically Black universities, into the fabric of federally funded ocean and atmospheric research.

Beyond the science itself, the institute carries an explicit workforce mission. CINGA will provide hands-on research experiences and workforce development opportunities for students preparing for careers in science, technology and natural resource management, a pipeline function that NOAA considers central to the Cooperative Institute model. The agency describes its institutes as centers of excellence that leverage university research and educational expertise to support NOAA priorities while developing the next generation of scientists and professionals. For a region whose economy depends heavily on fisheries, shipping, tourism and energy, cultivating homegrown technical talent is arguably as consequential as any individual research finding.

Leadership of the new institute falls to Jamie Dyer, a Mississippi State geosciences professor who was recently named director of the Northern Gulf Institute, the predecessor organization on which CINGA is built. “This award reflects the extraordinary work of our researchers and partner institutions and the confidence NOAA has in our collective ability to serve the Gulf region,” Dyer said. “CINGA creates tremendous opportunities to deepen scientific collaboration, develop future workforce talent and provide actionable research that helps communities, resource managers and policymakers make informed decisions about the Gulf’s future.” The award carries the potential for a five-year renewal based on successful performance, meaning the institute’s trajectory, and its impact on the Gulf Coast, will be judged against the same standard it was created to meet: science that communities can use.

Subject of Research: NOAA's selection of Mississippi State University to host a new Gulf Coast cooperative environmental research institute

Article Title: NOAA selects Mississippi State to host new Northern Gulf research institute with up to $100 million in funding

Article References: NOAA selects Mississippi State to host new Northern Gulf research institute with up to $100 million in funding. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: NOAA, Mississippi State University, Cooperative Institute, Gulf of Mexico, coastal resilience, hurricane forecasting, environmental modeling, uncrewed aircraft systems, supercomputing, fisheries, workforce development, Northern Gulf Institute