(Press-News.org) Embargo Tuesday 1st July 2025 06:00AM BST
Today, just over 100 days after the launch into production of the world first openly available 24/7 operational AI forecast model AIFS-Single, ECMWF (European Centre for Medium-Range Weather Forecasts) is unveiling the first ensemble model using Artificial Intelligence/Machine Learning. The new model, called AIFS ENS, will be available as open source to the user community over the coming weeks.
The new ensemble model outperforms state-of-the-art physics-based models for many measures, including surface temperature, with gains of up to 20%. At the moment, it works at a lower resolution (31km) than the physics-based ensemble system which remains indispensable for high-resolution fields and coupled Earth-system processes; ECMWF is therefore also exploring hybrid systems that leverage the strengths of both approaches.
This high accuracy ensemble model complements the portfolio of ECMWF services by leveraging the opportunities made available by machine learning (ML) and artificial intelligence (AI). The AIFS ENS relies on physics-based data assimilation to generate the initial conditions, but it can generate forecasts over 10 times faster while reducing energy consumption by approximately 1,000 times compared to traditional ensemble forecasting methods.
In February, ECMWF launched the first operational data driven model called AIFS Single. This model runs a single forecast at a time, known as a deterministic forecast. Despite its accuracy, there is much more value to users if they can access the full range of possible scenarios. This is known as ensemble forecasting, a technique developed and implemented by ECMWF more than thirty years ago.
Dr Florence Rabier, Director-General at ECMWF, states: “ECMWF has now created an operational collection of 51 different forecasts with slight variations for our Artificial Intelligence Forecasting System (AIFS), which is a significant achievement and complements our physics-based products. But importantly, it’s not only us who are innovating. We are also working with and for 35 nations to advance weather science to improve global predictions. The availability of the AIFS ENS in conjunction with other ECMWF services will positively impact how national weather and meteorological services in our 35 Member and Co-operating States and beyond will be able to make their predictions and contribute to a safer society.”
ECMWF’s Director of Research, Dr Andy Brown, said: “This new milestone demonstrates our dedication to science-led innovations that are focused on delivering a machine learning forecasting model which pushes the boundaries of efficiency and accuracy, and it underscores our commitment to harnessing the power of machine learning for the weather forecasting community.”
ECMWF is leveraging the potential of what AI/ML can do for weather science with this latest model. This is part of its co-development of the award winning Anemoi framework with many of its Member States, which provides an open-source framework for training AI forecasting systems, including the AIFS.
ECMWF’s Director of Forecasts and Services, Florian Pappenberger, added: “We see the AIFS and IFS as complementary, and part of providing a range of products to our user community, who decide what best suits their needs. Making such a system operational means that it is openly available and comes with 24/7 support for our meteorological community. We will continue to engage with our Member States and our user community to ensure more and more parameters are added to suit their ongoing needs, and we will continue to enhance the model offered in line with how we push the capabilities of our physics-based system.”
For more information, members of the press are welcome to join the user webinar on Tuesday 24 June 10:00 BST. Please register here: https://events.ecmwf.int/event/487/
For interview requests, please contact ECMWF press office at pressoffice@ecmwf.int or Lorna Campbell 0044 (0)7836 625999.
Ends
END
ECMWF - delivering forecasts over 10 times faster and cutting energy usage by 1000
2025-07-01
ELSE PRESS RELEASES FROM THIS DATE:
Brazilian neuroscientist reveals how viral infections transform the brain through microscopic detective work
2025-07-01
DAVIS, California, USA, 1 July 2025 – In a comprehensive Genomic Press Innovators & Ideas interview, Dr. Danielle Beckman reveals how her passion for microscopy has evolved into a mission to understand viral impacts on brain health, offering hope for patients suffering from post-viral neurological symptoms.
From Rio to Revolutionary Research
Dr. Beckman's journey from aspiring writer in Rio de Janeiro to leading neurovirology researcher exemplifies scientific determination. Her journey began to change during an undergraduate physiology course where she discovered her fascination with the brain. "I vividly remember that class and how fascinated I became with the brain," ...
Turning social fragmentation into action through discovering relatedness
2025-07-01
Discovering relatedness outside of a topical issue helps diverse groups to overcome differences and develop action for social change. The Kobe University addition to educational theory offers a framework to analyze and promote intersectional learning.
To achieve social change in a fragmented modern society, individuals from diverse backgrounds need to join together and develop a common plan for action. This is important especially for education related to social change, where groups of varying involvement in a particular issue, e.g., learners and teachers, interact in a structured setting. Current educational theories fall short of offering a framework of how such cultural differences ...
Cheese may really be giving you nightmares, scientists find
2025-07-01
Scientists have found that eating too much dairy could ruin your sleep. Researchers questioned more than 1,000 students about the quality of their sleep, their eating habits, and any perceived link between the two, and found a strong association between nightmares and lactose intolerance — potentially because gas or stomach pain during the night affects people’s dreams.
“Nightmare severity is robustly associated with lactose intolerance and other food allergies,” said Dr Tore Nielsen of Université de Montréal, lead author of the article in Frontiers in Psychology. “These new findings imply that changing eating habits for ...
Study reveals most common medical emergencies in schools
2025-07-01
The three most common reasons schools called emergency medical services (EMS) were for neurological crises such as seizures, psychiatric conditions or substance abuse, and trauma related injuries, according to data from the national EMS registry analyzed by researchers from Ann & Robert H. Lurie Children’s Hospital of Chicago.
During the study period (2018-2022), school-based medical emergencies constituted 11 percent of EMS encounters for children and two-thirds resulted in transport to the hospital. Findings, published in Pediatrics, can help schools prioritize training so staff can respond even before EMS arrival.
“While many schools have taken ...
Breathable yet protective: Next-gen medical textiles with micro/nano networks
2025-07-01
A research team led by Professors Xianfeng Wang and Bin Ding from Donghua University has developed a breakthrough in protective textile technology by engineering highly permeable, liquid-repellent textiles (HPPT) with micro/nano-network structures. Published in Nano-Micro Letters, this innovative work presents a scalable and practical solution to the long-standing challenge of balancing protection and comfort in medical clothing. The newly developed HPPT materials offer superior air and moisture permeability, robust mechanical durability, and exceptional ...
Frequency-engineered MXene supercapacitors enable efficient pulse charging in TENG–SC hybrid systems
2025-07-01
A team of researchers from Yonsei University and Pohang University of Science and Technology, led by Professors Sang-Young Lee, Sang-Woo Kim, and Changshin Jo, has unveiled a groundbreaking strategy to overcome the long-standing challenge of efficient energy storage in triboelectric nanogenerator (TENG) systems. Published in Nano-Micro Letters, this work introduces a system-level solution that leverages frequency modulation to significantly enhance the compatibility and charging efficiency between TENGs and supercapacitors ...
Developed an AI-based classification system for facial pigmented lesions
2025-07-01
A research team led by Haruyo Yamamoto, Chisa Nakashima, and Atsushi Otsuka from Department of Dermatology, Kindai University Faculty of Medicine, in collaboration with the Faculty of Engineering at Kindai University and other institutions, has developed a diagnostic system that uses artificial intelligence (AI) to accurately identify the type of facial pigmented lesions and support laser treatment decisions. A paper on this study was published online in Cureus, an international medical journal on June 5, 2025.
1. Key Points
Demonstrated superior diagnostic accuracy compared to dermatologists, when identifying ...
Achieving 20% efficiency in halogen-free organic solar cells via isomeric additive-mediated sequential processing
2025-07-01
Researchers from Shenzhen Technology University and collaborative institutions, led by Professor Guangye Zhang, have achieved a major milestone in organic solar cell (OSC) technology. Their latest work, published in Nano-Micro Letters, introduces a novel additive engineering strategy that enables 20.0% power conversion efficiency (PCE) in binary OSCs processed entirely with non-halogenated solvents. This advancement not only sets a new benchmark for toluene-processed OSCs but also offers a scalable and eco-friendly approach aligned with industrialization needs.
Why This Innovation Matters
Certified ...
New book Terraglossia reclaims language, Country and culture
2025-07-01
Award-winning author and University of South Australia academic Dr Debra Dank has unveiled her latest work, Terraglossia, a powerful response to colonial oppression that invites all Australians to reimagine how we engage with the world’s oldest living culture.
Dr Dank, a Gudanji/Wakaja and Kalkadoon woman from the Barkley Tablelands in the Northern Territory, launched the compelling follow-up to her acclaimed memoir, We Come With This Place, to challenge entrenched narratives and celebrate the richness of First Nations language and culture.
The title of the small hardback, Terraglossia, ...
The most effective diabetes drugs don't reach enough patients yet
2025-07-01
Subscribe to UCSF News
A UCSF analysis has found that the newer generation of much more effective diabetes medications are reaching only a fraction of the patients who are recommended to take them based on new guidelines.
Type 2 diabetes (T2D), a condition in which the body can’t use insulin to clear sugar from the bloodstream, affects 1 in 10 Americans. It comes with grave health risks, including cardiovascular and kidney disease.
The study assessed medications that patients received within a year of T2D diagnosis. During the period under review — ...