The UK Met Office has launched an aviation weather platform designed to support the needs of the aviation industry as it rapidly evolves.

The Met Office Aeronautical Visualisation Service (MAVIS) is said to be the most significant modernization of the UK’s regulated aviation weather services in more than two decades. Bringing together multiple legacy platforms into a single, intuitive interface, it can support traditional operations ranging from crewed aircraft through to spacecraft missions.

The platform was developed in close collaboration with the Civil Aviation Authority (CAA) and shaped using user research and feedback from airlines, airports, pilots, emergency responders, offshore helicopter operators, balloonists and the general aviation community, to ensure it reflects the needs of the entire sector.

Continue reading Met Office launches platform to support needs of evolving aviation industry at Meteorological Technology International.

The Chongqing Meteorological Bureau is expanding the use of artificial intelligence and digital weather services as part of efforts to improve forecasting and warning capabilities across the Chinese megacity.

The bureau has reported deploying the Tianzi 12h (2.0) AI model, which provides hourly updated forecasts for the Chengdu-Chongqing region at a spatial resolution of 1km. The system forms part of a 0-60-day gridded forecasting network covering both weather and climate predictions. 

Authorities said forecasting accuracy for several indicators – including 24-hour maximum temperature, sunshine or rain forecasts, heavy rainfall and monthly temperature predications – ranks among the top five nationally. 

Continue reading Chongqing expands AI-powered weather services to improve warning times at Meteorological Technology International.

The UK Met Office has launched a significant upgrade to its forecasting system, introducing new modeling capabilities designed to improve forecast accuracy, clarity and usability across multiple sectors.

The update is the most substantial scientific improvement to the agency’s forecasting systems in more than three years and is the first major advancement delivered using its new supercomputer. The Met Office said the changes will produce forecasts that more closely reflect real-world conditions, particularly for precipitation, cloud and fog.

Forecasts will now show rain and snow with greater realism, while improved modeling of cloud and fog is expected to provide more accurate guidance for travel planning and operations.

Continue reading Met Office rolls out major forecasting system upgrade at Meteorological Technology International.

A team of scientists led by the Euro-Mediterranean Center on Climate Change (Centro Euro-Mediterraneo sui Cambiamenti Climatici – CMCC) has developed a machine-learning (ML) prediction system capable of outperforming traditional forecasting systems, helping to protect vulnerable areas of Europe from heatwaves – one of the continent’s most pressing climate challenges.

Trained on data from centuries of climate analysis up to recent years, the system has demonstrated an increase in forecasting efficiency by significantly reducing the computational resources required. This makes it more cost-effective and accessible for a broader number of researchers and institutions.

The new model is said to be able to deliver forecasting insights 4-7 weeks before summer, in mid-March, providing a strong lead time for preparation measures.

Continue reading CMCC develops machine-learning model that delivers improved heatwave forecasting accuracy at Meteorological Technology International.

Vaisala is debuting its new, customizable software solution to share clear, real-time and operation-specific weather insights from automatic weather stations and sensors at Meteorological Technology World Expo 2025, which is taking place October 14-16 In Vienna, Austria.

The software, named Elements Lite, is said to be optimized for accessibility – providing live, customizable conditions from desktop, tablet and smartphone devices. It supports a variety of Vaisala’s weather sensors, including those measuring air temperature, wind speed and direction, visibility, barometric pressure, humidity and precipitation. Users can also configure alarm thresholds tailored to their specific operational requirements.

Elements Lite also integrates with Vaisala Elements Online cloud platform to share weather observations beyond the local network.

Continue reading Vaisala unveils Elements Lite software for real-time, customizable weather insights at Meteorological Technology International.

The European Centre for Medium-Range Weather Forecasts (ECMWF) has said that Europe’s first exascale supercomputer, Jupiter, can bring a “fundamental step-change” to the products it delivers, after the system went into operation on September 5.

Jupiter is designed to be Europe’s first supercomputer capable of reaching exascale performance, meaning it can achieve at least one exaflop – one quintillion (1018) calculations per second. It is the fourth most powerful supercomputer in the world.

Director of forecasts and services and ECMWF’s director-general elect, Florian Pappenberger, said, “It is very important that Europe is entering the era of exascale computing.

Continue reading Europe’s first exascale computer for weather prediction enters service at Meteorological Technology International.

Global leaders in science, technology and climate services will convene in Abu Dhabi this week to explore how AI can improve weather prediction in a three-day event organized by the World Meteorological Organization (WMO) and the National Centre of Meteorology (NCM) of the United Arab Emirates.

The meeting will discuss the potential for AI to strengthen weather, climate, hydrological and marine services to help WMO members improve forecasting, hazard warning and data-driven decisions.

The WMO AI Conference: AI for Weather Prediction, Advances, Challenges & Future Outlook takes place September 9-11 at NCM’s headquarters in Abu Dhabi.

Continue reading AI weather prediction potential to be explored in WMO-UAE workshop at Meteorological Technology International.

UK startup TransZero has unveiled a new online platform aimed at helping companies manage their property portfolios for extreme weather risks associated with climate change.

The TransZero platform models how multiple extreme weather events – including floods, windstorms, droughts, hail, subsidence and heatwaves – are expected to change throughout the 21st century, using advanced climate risk models, artificial intelligence and geospatial technology. This enables businesses and investors to explore targeted resilience and risk mitigation strategies through a cloud hosted service.

With 2024 recognized as the hottest year since records began in 1850 and global average temperatures now 1.46°C above pre-industrial levels, extreme weather events are increasingly being linked to climate change.

Continue reading TransZero launches AI-powered climate risk platform to help businesses safeguard global supply chains at Meteorological Technology International.

NOAA’s Global Systems Laboratory (GSL) is to release an experimental, AI-powered short-term weather forecast model trained on three years of High Resolution Rapid Refresh (HRRR) short-term weather forecast model data, for testing by NOAA’s National Weather Service (NWS) in August.

Developing the AI-powered model

The model, named HRRR-Cast, is NOAA’s first regional experimental AI forecast system and a key component of NOAA’s broader Project EAGLE, a long-term project to provide NOAA and the US weather enterprise with the ability to rapidly test, develop and identify the most promising AI models for global to regional ensemble forecasting.

“HRRR-Cast has been shared with colleagues in NOAA’s Environmental Modeling Center for evaluation and potential integration into a demonstration forecast system,” said project manager Isidora Jankov, GSL’s scientific computing branch chief.

Continue reading NOAA Research develops AI-powered weather forecast model at Meteorological Technology International.

A research team led by associate professor Yosuke Matsumoto from the Institute for Advanced Academic Research at Chiba University in Japan has begun testing the use of soft x-ray imaging to measure magnetic reconnection rates in Earth’s magnetosphere, which, it says, could pave the way to more accurate space weather predictions.

The study, co-authored by Ryota Momose from Chiba University and Prof. Yoshizumi Miyoshi from Nagoya University, was made available online on June 23, 2025, and was published in Volume 52, Issue 12 of the journal Geophysical Research Letters on June 28, 2025.

Supercomputer simulations

In the study, the researchers proposed leveraging the soft x-rays that are naturally emitted when solar wind particles interact with the boundaries of the magnetosphere to remotely measure reconnection rates across much larger regions than previously possible.

Continue reading Chiba University-led research team uses x-ray imaging to improve space weather predictions at Meteorological Technology International.