The project is inspired by the increasing development and interest in scientific machine learning applied to multi-fidelity data assimilation and inverse problems. Methods to approximate probability measures have flourished recently also due to the implementation of efficient generative models in machine learning and more principled mathematical methods like diffusion models and transport maps.The target of our studies are inverse problems that concern the environmental sciences, possibly but not necessarily linked to computational fluid dynamics: from the dynamics of polar and continental ice sheets to the oceans acidification and circulation models, to cite a few. SISSA mathLab has a consistent expertise in optimal control and data assimilation for the environmental sciences. The MIT group has several ongoing projects in this area, including an ONR MURI focused on data assimilation for sea ice modeling, and a DOE SciDAC project focused on optimal sensor network design to inform aspects of earth system models. In particular, multi-scale models are sometimes constituted by hybrid systems featuring a coarse scale modeled by a partial differential equation (PDE) and a fine scale modeled by a stochastic differential equation (SDE) expanded on the whole spatial domain. The aim is to develop surrogate models also for this type of multi-scale coupled PDE-SDE systems.The main goals of this project are: (1) leveraging reduced order models in Bayesian inversion or in sequential Bayesian data assimilation; (2) the speed-up of the forward uncertainty propagation with our surrogate and generative models; (3) randomization through PDE-SDE coupled systems; (4) the application of our methodologies to tackle complex and large-scale inverse problems from the environmental sciences.
Supported by the framework of iNEST (https://mathlab.sissa.it/project/interconnected-nord-est-innovation-ecosystem-inest) and organised together with Wärtsilä, the Smart Vibration Assessment Service (SVAS) project aims to develop cutting-edge solutions for predictive maintenance. The study focuses on the diagnostics and health assessment of bearings, as they are mechanical components widely used in industrial equipment.
Vibration analysis is leveraged to monitor the condition of bearings and get information regarding the mechanical behaviour of the system. The identification of patterns associated with incipient faults would allow to foresee failures in advance. This is particularly relevant in industrial settings, where early fault detection enables more efficient maintenance planning, minimizes unexpected downtime, and helps ensure continuous, cost-effective operation.
iNEST (Interconnected Nord-Est Innovation Ecosystem) is a new innovation ecosystem paradigm aimed at creating networks among universities, public research institutes, and highly qualified public and private institutions in Northeastern Italy. The project’s objective is to spread the benefits of digital technologies and develop innovative solutions for cultural dissemination, individual well-being, and economic and entrepreneurial growth. To achieve this, iNEST relies on two key tools: Information and Communication Technologies (ICT) and digitalization. iNEST is structured around a central Hub and 9 Spokes. Each Spoke focuses on a different macro-theme, reflecting the diverse nature of the Italian Northeastern region.
The EU’s 2030 goal is to establish a resilient energy plan that minimises dependence on fossil fuels. This drives demand for sustainable energy sources such as deep geothermal, which has significant potential for long-term heating and electricity generation. In this context, the EarthSafe doctoral network project, funded by the Marie Skłodowska-Curie Actions programme, will develop a data fusion method that remains robust even when data is missing.
To achieve the goals of the European Green Deal on climate neutrality, a 90% reduction in transport emissions is needed by 2050. The automotive industry urgently needs to accelerate the introduction of alternative powertrains for electrified vehicles. Hydrogen-powered Proton Exchange Membrane Fuel Cells (PEMFCs) are carbon-free power devices that meet these goals in both mobile and stationary applications.
The project focuses on fluid-structure interaction (FSI) in the cardiovascular system, with the aim of developing innovative numerical methods, supported by machine learning techniques, to obtain fast and accurate solutions. Three main challenges are addressed: the stability of weakly coupled numerical schemes, the reduction of computational complexity by means of reduced models (ROMs), and the efficient solution of clinically relevant inverse problems (shape optimization and parameter calibration).
The FaReX project aims at developing new numerical methods for the efficient simulation of complex multi-scale and multiphysics problems, such as fluid-structure interaction or phase transition, using non-matching modeling techniques, immersed methods and model reduction techniques, also through machine learning. The involved units (SISSA, PoliTO, UniBS) work jointly on numerical analysis, complexity reduction and open source software development.
