The Research Unit aims to explore and develop cutting-edge Machine and Deep Learning techniques, along with their applications in climate science.

The activities focus on: (i) investigating neural networks to develop foundation models for the ocean and atmosphere at weather and climate time scales; (ii) leveraging generative AI models for downscaling and data assimilation; (iii) analyzing the predictive capabilities of neural networks for extreme events such as windstorms, cyclones, wildfires, droughts, floods, and heat waves; and (iv) exploring the application of ML/DL techniques to assess the impact of climate change on society, the economy, agriculture, coastal regions, vegetation, land use, and marine ecosystems.

Leader: Italo Epicoco

The main goal of the Research Unit concerns the design and implementation of Data Science open source solutions and strategies for addressing efficient access, analysis and mining of scientific data in the climate change and environmental domains.

In particular, the activities focus on: (i) managing scientific data and services in the context of major international initiatives and research infrastructures like the ENES Climate Data Infrastructure, the Earth System Grid Federation, and the European Open Science Cloud; (ii) defining optimized storage models and approaches for efficient organization, storage, access and delivery of climate data; (iii) designing efficient lossy and lossless data-driven compression algorithms; (iv) deploying advanced Data Science environments for climate scientists on top of HPC/Cloud infrastructures, by integrating High Performance Data Analytics and machine learning frameworks to accelerate scientific discovery; (v) developing AI-enabled workflow automation tools and applications for weather and climate use cases (e.g., digital twins) addressing scalability and reproducibility; (vi) designing and implementing innovative platforms and services for end-to-end data management, including data collection from multiple sources (e.g., IoT, drones, EO, ESMs), advanced analytics (e.g., image processing, data mining) and results visualization (e.g., interactive dashboards).

Leader: Donatello Elia

The research unit focuses on analyzing and optimizing the main computational kernels used in CMCC climate models on modern high performance computing platforms, including multi-core CPUs, GPUs, hybrid and exascale architectures. Activities target the improvement of computational performance, scalability, accuracy, reproducibility, and energy efficiency of numerical models through the use of optimized compilers, numerical libraries, advanced memory hierarchies, and emerging parallel programming paradigms.

Specifically, research efforts include: (i) leveraging advanced parallel algorithmic structures and specialized GPU hardware to mitigate communication overheads in “dynamical cores”; (ii) optimizing the management of large-scale “multi-model” and “multi-emission” ensemble experiments on hybrid systems; (iii) optimizing memory hierarchies and data locality across GPU and CPU components; (iv) rationalizing I/O operations; (v) employing new parallel communication paradigms and efficient synchronization mechanisms tailored to GPU-accelerated tasks; (vi) exploring innovative approaches for climate modelling based on differentiable physics; and (vii) investigating green computing methodologies reinforcing CMCC’s commitment to sustainable and responsible computational practices.  

Leader: Francesca Mele

The Research Unit aims to strengthen CMCC’s capacity for scientific digital innovation and strategic technological coordination by optimizing and aligning digital tools, software, and services across the Foundation. It enhances CMCC’s software assets by promoting standardized processes for design, development, testing, and documentation, ensuring quality, reusability, and sustainability of digital solutions as a strategic lever to consolidate CMCC’s role within the international climate research community. The R.U. acts as a facilitator to harmonize digital approaches across the research environment and enable the effective adoption of innovative technologies supporting scientific activities.

The activities focus on streamlining digital tools and workflows to ensure interoperability and integration across institutes, programs, and centers, while supporting the implementation of a cohesive digital strategy for CMCC. The R.U. promotes shared methodologies and best practices for software development and quality assurance, coordinates multidisciplinary teams aligned with CMCC’s research priorities, and contributes to the evolution of specific internal software products to strengthen them as structured and standardized digital assets. It also fosters knowledge exchange between developers, engineers, and scientists to improve collaboration between technical and research communities.

Leader: Matteo Scuro