ForecastWatch has launched a new independent platform for weather forecast verification and market intelligence.

The release brings an expansion to the company’s verification capabilities, introduces an anonymized participation model supported by like-to-like benchmarking groups called Markets, and adds new API and data integration tools. The platform now covers more than 50 forecast producers over 2,400 weather stations worldwide.

The verification upgrade is the most significant aspect of the new release. Where the previous platform focused on post-forecast-day analysis, the new platform extends verification across the full forecast lifecycle – adding pre-Forecast Day risk detection through Forecast Risks, Forecast Watchlist and Forecast Email Alerts, and isolating station-level issues through a new Station Watchlist.

Continue reading ForecastWatch expands with launch of new independent platform for weather forecast verification at Meteorological Technology International.

Researchers at the USC Viterbi School of Engineering have developed an artificial intelligence model capable of predicting wildfire spread in near real time by combining satellite data, terrain information and fire simulations.

The system builds on earlier work led by Assad Oberai, Hughes Professor of Aerospace and Mechanical Engineering, and the Computation and Data Driven Discovery (CD3) group. The updated model integrates multiple satellite data sources to improve accuracy and reduce uncertainty in forecasting fire behavior.

The research follows growing concern over increasingly intense wildfires, particularly in regions such as Southern California, where large-scale events have caused widespread damage in recent years.

Continue reading AI model improves real-time prediction of wildfire spread at Meteorological Technology International.

A new open-access tool designed to assess the accuracy of climate models has been launched by an international team of researchers, significantly reducing the time required for evaluation.

The Rapid Evaluation Framework (REF) was developed by scientists involved in the Coupled Model Intercomparison Project (CMIP), a global initiative that supports the development and comparison of climate models used in major assessments, including those by the Intergovernmental Panel on Climate Change (IPCC).

Climate models simulate interactions between the atmosphere, oceans and land surface to help scientists understand past climate trends and project future changes. Evaluating how well these models reflect real-world conditions has traditionally been a time-consuming process, often taking months.

Continue reading New tool speeds up climate model evaluation at Meteorological Technology International.

NASA is trialling a high-resolution weather modeling system from Meteomatics to improve forecasting for launch and facility operations at the Wallops Flight Facility.

Range meteorologists at Wallops are using Meteomatics’ US1k weather model alongside its MetX forecasting platform to gain more detailed insight into local weather conditions that can affect launch activities and site safety.

According to Meteomatics, the US1k model offers a resolution nine times higher than other commonly used weather models, enabling more precise analysis of localized weather phenomena. The data is integrated into the MetX platform, where it is presented through customizable visualizations to support decision-making.

Continue reading NASA tests high-resolution weather model for launch operations at Meteorological Technology International.

The Weather Company has released an updated version of its Storm Radar app, introducing new radar capabilities, redesigned mapping and an AI-powered weather assistant.

The updated app integrates high-resolution radar with customizable data layers, enabling users to track weather conditions including temperature, wind, lightning and tropical systems. A new “high-res single site radar” feature provides more detailed insights into storm rotation, hail and severe weather.

James Belanger, vice president of meteorology at The Weather Company, said, “Storm Radar’s latest update is a gamechanger for anyone interested in the weather, from the casual observer to the seasoned storm chaser.

Continue reading The Weather Company updates Storm Radar app with AI features at Meteorological Technology International.

CenterPoint Energy is integrating a high-resolution weather model from Meteomatics to improve forecasting and operational planning across the Greater Houston area.

The company said the integration of Meteomatics’ US1k weather model will help it better anticipate and respond to severe weather events affecting the approximately 2.9 million electric customers it serves.

The initiative forms part of CenterPoint’s Greater Houston Resiliency Initiative (GHRI), which aims to strengthen the resilience of the region’s electricity grid.

According to the companies, the US1k model provides weather data at a resolution nine times higher than leading public national weather models.

Continue reading CenterPoint Energy integrates Meteomatics high-resolution weather model at Meteorological Technology International.

Artificial intelligence technologies could significantly reshape how national meteorological services deliver forecasts and weather-related services, according to a report from Amazon Web Services (AWS).

The report, titled How innovative technology can transform the delivery of meteorological services, examines how AI, generative AI and agentic AI could complement traditional physics-based forecasting methods such as numerical weather prediction. While NWP models remain central to forecasting, AI systems can rapidly analyze large datasets and identify patterns from historical weather data to produce more detailed and localized forecasts.

According to the report, hybrid forecasting approaches combining AI and traditional modeling are likely to become increasingly common.

Continue reading Amazon report explores how AI could transform national meteorological services at Meteorological Technology International.

Exosens has signed a cooperative research and development agreement (CRADA) with the National Oceanic and Atmospheric Administration (NOAA) to develop new atmospheric profiling applications using its Assist II atmospheric sounder.

The agreement, signed in December 2025, will focus on developing new meteorological applications and algorithms to generate atmospheric profiles. Phase one of the partnership will see Assist II deployed at a National Weather Service (NWS) test site in Virginia in early 2026. The instrument will remain on-site for approximately 10 months to validate operational applications and new software functionalities, including TROPoe atmospheric profiling capabilities to be integrated into Assist II.

Continue reading Exosens partners with NOAA to develop atmospheric profiling applications at Meteorological Technology International.

ERM and Jupiter Intelligence have announced a partnership aimed at helping organizations translate extreme weather risk into business strategy and investment planning.

The collaboration combines Jupiter’s climate risk data and analytics with ERM’s advisory and operational expertise to support organizations in quantifying physical climate risk, prioritizing resilience investments and integrating risk considerations into decision-making.

According to the companies, the increasing frequency and intensity of extreme weather events are affecting operations, asset values and supply chains across multiple industries. The partnership is intended to provide analytics for operational and investment decisions rather than compliance reporting alone.

Jupiter’s analytics are designed to integrate into risk models, investment decisions and adaptation strategies, enabling organizations to quantify exposure and incorporate climate risk into capital planning and operational strategy.

Continue reading ERM and Jupiter Intelligence partner on climate risk analytics and resilience planning at Meteorological Technology International.

Nvidia has launched a new Earth-2 family of open models, libraries and frameworks designed to support AI-based weather and climate forecasting, making advanced weather AI more accessible to organizations worldwide.

The announcement was made at the American Meteorological Society’s annual meeting, where Nvidia described Earth-2 as the world’s first fully open, accelerated software stack covering the full forecasting workflow – from processing observational data to generating medium-range global forecasts and short-term local storm predictions.

Nvidia said the open nature of Earth-2 allows scientists, weather agencies, developers, enterprises and governments to run, fine-tune and deploy production-ready weather AI models on their own infrastructure.

Continue reading Nvidia launches open Earth-2 model family for AI weather forecasting at Meteorological Technology International.