Open radar data now powers a unified, real-time national dataset for precipitation forecasting and decision support in Italy.

In its first year of activity, IT4LIA – AI Factory developed a new data infrastructure for monitoring and forecasting precipitation in Italy, addressing a complex challenge: overcoming the historical fragmentation of national radar data to make it accessible and ready for use.

IT-DPC-SRI: Italy’s first radar “Data Cube”

The project, coordinated by Fondazione Bruno Kessler, led to the creation of IT-DPC-SRI, the first public and standardized archive of precipitation radar observations covering the entire national territory. The numbers behind the project point to an unprecedented resource:

• Historical coverage: 16 years of data to date (since 2010).
• High resolution: 1 km spatial resolution.
• Continuous updates: new data integrated every 5 minutes.
• Volume: over one million observations already available.

The initiative also fills a long-standing strategic gap in weather radar monitoring across Europe. Italy has never joined OPERA, the European program for exchanging radar observations, leaving the continental radar composite without coverage over Italian territory. This new dataset finally allows Italy to be integrated into European-scale analyses, aligning the country with the most advanced international standards.

“Analysis-ready” data: from information to action

The innovation lies not only in the quantity and uniqueness of the released data, but in how it is made available to users. The data has been collected, pre-processed and converted into an analysis-ready format designed for use on cloud infrastructure. Information originally scattered across different, hard-to-combine formats has been standardized and organized into a single data cube, easily accessible and usable even by artificial intelligence models. This significantly reduces technical barriers, allowing businesses, public bodies and researchers to work directly with the data without building complex preparation pipelines.

The dataset can be accessed through several complementary channels:

• Static version (Zenodo): designed to ensure scientific reproducibility for studies and analyses; covers the years 2010 to 2025.
• Interactive static version (European Weather Cloud): allows interactive, segmented consultation, removing the need to download the entire archive; covers the years 2010 to 2025 and is accessible via the mlcast-dataset Python package, developed and maintained by the MLCast scientific community under the EUMETNET E-AI Optional Programme.
• Continuously updated version (ArcoDataHub): a “live” dataset refreshed every five minutes to support immediate operational applications; covers the years from 2010 to today and allows interactive, partitioned access.

A strategic asset for the market: value for businesses

Access to such a rich historical archive, combined with a real-time data stream at kilometer-scale resolution, represents a major competitive and operational advantage for industry and services. Until now, the difficulty of accessing consistent radar data has slowed the development of proprietary risk management and optimization solutions. IT-DPC-SRI unlocks this potential across several key sectors:

• Smart agriculture: Cooperatives and farms can use radar data for precision irrigation, tracking rainfall accumulation in fields to prevent water stress or damage from extreme events.
• Water network management: Water utilities can integrate this data into hydrological models to optimize intake, prevent waste, balance reservoirs and efficiently monitor urban drainage systems.
• Mobility and route planning: Transport companies, couriers and logistics firms can use real-time radar maps to reroute vehicles around intense storms, flooding or low visibility, optimizing fleet management.
• Insurance: Insurers can finally rely on standardized historical datasets to quickly and objectively quantify damage from extreme precipitation, speeding up assessments and local claims settlement.
• Renewable energy: Hydroelectric power producers can use precipitation data to forecast water inflow into reservoirs and plan production in advance.

Integrating this open data into business workflows no longer requires long, costly data-cleaning processes. Being natively analysis-ready, IT-DPC-SRI drastically reduces time-to-market for any company looking to develop new digital services.

This standardized data foundation is also the ideal dataset for developing artificial intelligence models dedicated to very short-term forecasting (nowcasting). Businesses can train predictive algorithms and apply them to real-time updated data, triggering automatic alerts within their own systems to protect production sites, construction areas and warehouses before torrential rain hits.

IT4LIA will soon release its own open-source AI-based predictive nowcasting model, called IRENE. We will dedicate a full feature to this innovative technology and its business applications in our next article.

A collaboration of excellence enabled by IT4LIA

This work is the result of a broad collaboration among leading institutions and research centers: Fondazione Bruno Kessler, the Department of Civil Protection, Agenzia ItaliaMeteo, ARPAE Emilia-Romagna, CINECA, together with international partners such as the Danish Meteorological Institute, within the MLCast initiative and the EUMETNET E-AI European program.

In this context, IT4LIA AI Factory provided the enabling framework for bringing together data, models and high-performance computing infrastructure into a single, coherent operational pipeline serving the whole ecosystem.

Overall, IT4LIA’s Earth vertical shows how combining open data, cloud infrastructure and artificial intelligence can accelerate the development of predictive solutions for weather applications. These results represent not only scientific progress, but also cutting-edge technology finally made accessible and scalable for the entire production and industrial system.

Want to find out how to integrate IT-DPC-SRI data into your projects?

Visit ArcoDataHub or get in touch with the IT4LIA AI Factory team for more information.