15 ongoing and 15 completed projects. A project moves to the completed list on its own once its end date has passed.
Finds where synthetic data can enable or improve AI along a space mission, with priority to ground segment engineering, operations and space safety. DSIP develops and validates methods for selected data types in minimum viable products and drafts the roadmap towards operational products.
Two AI algorithms for road safety. The first estimates whether a driver's behaviour, from floating car data, is consistent with the safe speed, using accident statistics, weather, traffic and road geometry from OpenStreetMap; the second warns the driver in real time about the speed to keep before and through a bend.
The Italian AI Factory: high-performance computing and AI services for start-ups, SMEs, public administrations and research. OpenIoT develops AI models for climate-resilient and resource-efficient agriculture.
Software components that combine machine learning with symbolic models of systems and faults to make FDIR more accurate and efficient. The goal is more autonomous and reliable aerospace systems, such as satellites and exploration vehicles, over a 24-month project.
A deep-learning model on weather-radar data forecasts thunderstorms, heavy rain, snow and hail at 500 m and 5-minute steps up to 100 minutes ahead, in under 10 seconds. The system gathers radar, satellite, lightning and ground-station data and issues automatic alerts by SMS, email, phone and the IO app.
An intelligent digital twin for mission operations, developed with the support of ESA's European Space Operations Centre. It keeps itself synchronised and calibrated with the physical asset, forecasts its state by combining simulation and machine learning, including physics-informed models, and uses AI for planning, what-if analysis, fault detection and diagnosis.
A prototype service for the climate resilience of critical infrastructures, with the national transmission grid as test case. In pilot areas it studies geotechnical hazards, such as landslides, and weather and climate extremes, and builds resilience scenarios by joining climate information with complex-network models.
Stationary PEM fuel cells above 100 kW running on industrial-grade hydrogen without repurification. DSIP uses machine learning to model how hydrogen impurities degrade the electrochemical parameters, the performance and the durability of the cells.
Tools and methods for industrial users to quantify the impact of extreme natural events on the Italian territory: risk factors, medium-term forecasts of the events and impact assessment after a disaster. Scientific visualisation and AI help evaluate the assets at risk.
AI-based predictive models and IoT data architectures to optimise production in hollow-glass manufacturing plants.
European testing and experimentation facilities where companies validate their AI and robotics solutions for agriculture and food.
European testing and experimentation facility for AI in manufacturing, with 24 organisations from eight countries.
National Research Centre in HPC, Big Data and Quantum Computing: an interdisciplinary network for advanced Earth system modelling.
Unlocking the EU renovation wave with standardised and integrated processes: digitalisation, new technologies and materials, industrialisation. 23 partners from 7 countries.
A management tool to monitor stationary fuel cell units and improve their performance and durability.
A multi-source system (radar, satellite, lightning, ICON model) for probabilistic forecasts of precipitation and lightning at 0.5 km and 5 minutes, up to about 1.5 hours ahead.
AI to plan the daily operation and the maintenance of an electric bus fleet, and to anticipate unexpected events.
A strategic partnership of 33 research and industrial organisations for innovation in space exploration.
AI for the diagnosis and prognosis of railway track degradation, such as corrugation and critical points at joints.
AI-driven solutions to automate mission operations in four use cases across two domains.
Online detection and recognition of insect pests on sticky traps.
Autonomous on-board software with machine learning, to give space systems high-level reasoning capabilities.
Monitoring the safety of mining tailings dams: 3D image acquisition and processing by 3DOM, data analytics and forecasting models by DSIP.
Consumption forecasting and operation planning for industrial plants with cogeneration of electricity, heat and cooling.
A robotic digital twin that combines data-based, physics-based and symbolic models, fitted at runtime on real data.
Predicting the duration of (bio)chemical reactions in pharmaceutical manufacturing by combining finite state machines and deep learning when data are scarce.
On-edge anomaly detection and remaining-useful-life estimation for gearmotors.
Deep learning to improve weather nowcasting.
Models and algorithms for prediction on an integrated platform for modern agriculture.
Pre-harvest analytics for winemaking with a miniature spectrometer and AI trained on more than 20,000 spectra.
