The National Institute of Solar Energy (NISE) and Grid Controller of India have signed a memorandum of understanding to jointly carry out a research project on hybrid day-ahead and intra-day solar forecasting for large solar parks in India.

The agreement was signed by Prof. Mohammad Rihan, director general of NISE, and Manoj Kumar Agrawal, executive director of the National Load Despatch Centre (NLDC), with representatives from both organizations present, including GRID-India chairman and managing director Samir Chandra Saxena.

The project will be delivered in partnership with renewable energy developers including Adani Green Energy, NTPC Green Energy, Tata Power Renewable Energy, ReNew and Serentica Renewables.

Continue reading India partners on hybrid solar forecasting project for large solar parks 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.

A researcher from the National Satellite Meteorological Centre in China has developed a model that has reportedly extended the effective lead time of nowcasting for severe convective weather to four hours.

Wang Jingson, working with researchers from Harbin Institute of Technology (Shenzhen), Hong Kong University of Science and Technology and Guangzhou Institute of Tropical and Marine Meteorology at the China Meteorological Administration (CMA), engineered the deep diffusion model based on data gathered by the Fengyun (FY) meteorological satellites.

The CMA says it marks an important breakthrough in China’s intelligent forecasting technology based on independent satellite data and will provide stronger technical support for disaster prevention and mitigation.

Continue reading China develops deep diffusion model to extend severe convective weather nowcasting to four hours at Meteorological Technology International.

The WMO has called for the public, private and academic sectors to collaborate on the development and use of artificial intelligence (AI) and machine learning (ML) for environmental monitoring and predication – helping to protect communities and economies from hazards, including extreme heat and rainfall.

The WMO Call to All Stakeholders to Collaborate on the Development of Artificial Intelligence (AI) and Machine Learning (ML) Environmental Monitoring and Prediction Technologies, Tools and Applications was adopted at the Extraordinary session of the World Meteorological Congress in October 2025.

It reaffirms WMO’s mission to facilitate international cooperation and standardization, while also underscoring the vital importance of the single official and authoritative voice of national meteorological and hydrological esrvices (NMHSs).

Continue reading WMO calls for global collaboration on development of AI and machine learning for monitoring and prediction at Meteorological Technology International.

CIRES and CU Boulder have become the first to detect a tsunami caused by a landslide using data from a ship’s satellite receiver. The research, which is published in Geophysical Research Letters, demonstrates that shipborne navigation systems have potential to improve tsunami detection and warning, the institutions say.

Recording the tsunami

On May 8, 2022, a landslide near the port city of Seward, Alaska, sent debris tumbling into Resurrection Bay, creating a series of small tsunami waves. The R/V Sikuliaq was moored 650m (0.4 miles) away. The vessel is a University-National Oceanographic Laboratory System (UNOLS) designated vessel and part of the US Academic Research Fleet (ARF), and is owned by the National Science Foundation and operated by the University of Alaska Fairbanks.

Continue reading Ship’s satellite receiver detects landslide-generated tsunami for the first time at Meteorological Technology International.

A research team from Tianjin University has developed an AI-powered method that turns common surveillance cameras into real-time rainfall sensors. The team’s findings (DOI: 10.1016/j.ese.2025.100562) have been published in Environmental Science and Ecotechnology.

Leveraging deep learning

Tested in the cities of Tianjin and Fuzhou, this system achieved accuracy and robustness in predicting rainfall, even during night-time or under poor visibility conditions, the researchers reported.

The proposed system operates through two key modules: a feature extraction module (FeM) and a rainfall estimation module (RiM). The FeM analyzes video frames using a novel image quality signature (IQS) method that extracts brightness, contrast and texture features to detect rain streaks, even from noisy or low-light footage.

Continue reading Tianjin University AI model turns street cameras into rainfall sensors at Meteorological Technology International.

Vodafone has partnered with River Severn Partnership Advanced Wireless Innovation Region (RSPAWIR) and Wireless DNA to use its mobile network to provide more accurate rain nowcasting.

Electromagnetic rain forecasting

The partnership will use Vodafone’s mobile network as an environmental sensor to monitor rainfall. Electromagnetic waves at certain frequencies are sensitive to precipitation, as water in the air affects the quality of the wireless link between masts. A microwave link can, therefore, function as a virtual rain gauge, providing pinpointed and precise precipitation data.  

Wireless DNA will monitor all signal variations to identify those caused by precipitation and share this data with the River Severn Partnership to enhance early warning systems (EWS) for flooding and improve flood defenses for local residents.

Continue reading VIDEO: Vodafone mobile network used to improve rainfall nowcasting and early warning systems at Meteorological Technology International.

Meteorological Technology International will host an exclusive webinar, in association with Baron Weather, on May 1, 2025, titled ‘State-of-the-art weather visualization and communication in the modern world.’

Weather communication challenges

The expert speakers will delve into audiences’ changing expectations, as traditional text alerts and simplistic diagrams compete for attention against visually appealing, dynamic messages from entertainment and leisure. They’ll also look into how capturing and holding your audience’s attention requires more engaging and impactful messaging in today’s fast-paced communication landscape.

The webinar will explore the difficulty of translating complex data into clear, actionable messages.

Continue reading NEW WEBINAR: State-of-the-art weather visualization and communication in the modern world at Meteorological Technology International.

According to a new study by the UK Centre for Ecology and Hydrology (UKCEH), the University of Leeds (UK) and the Pacific Northwest National Laboratory (USA), measurements of land surface conditions are set to transform early warning systems in tropical regions.

The new study, published in Nature Geoscience, is part of ongoing UKCEH research funded by the Natural Environment Research Council (NERC). A previous study found land surface conditions often affect the direction and intensity of megastorms in the Sahel after they have formed, while a separate paper showed that deforestation increases the frequency of storms in some fast-growing African coastal cities.

Continue reading Land surface conditions research set to transform early warning systems in tropical regions at Meteorological Technology International.

Scientists at the University of Hawaii have developed new wildfire risk maps to better predict fire danger across the state. The Hawaii Emergency Management Agency, Federal Emergency Management Agency and Hawaii State Legislature provided funding to create the fire ignition probability maps.

Real-time weather data

Unlike the current Red Flag Warning system, which relies on weather from a limited number of stations, these maps provide a daily, high-resolution look at the most current fire ignition risks statewide. The maps are generated using real-time data obtained from various weather networks across the state, including the Hawaii Mesonet.

Continue reading University of Hawaii develops wildfire risk warning maps at Meteorological Technology International.