iNEST DAY - February 21, 2025
Registration opens at 8:30
9:00 - 9:10
Mattia Fogagnolo, Matteo Zavatteri
Opening
Overview of the results of the iNEST Spoke 9
9:10 - 9:30 - Antonia Larese. RT1 - Mathematical, Numerical, and Data-driven Modeling
9:30 - 9:50 - Niccolò Tonicello. RT2 - Model Order Reduction
9:50 - 10:10 - Francesca Cairoli. RT3 - Automatic Learning for Digital Twins
10:10 - 10:30 - Stefano Salon. RT4 - Applications of Digital Twins in Industry, Medicine, Environmental Sciences, Daily Life
Chair: Mario Putti
10:30 - 11:00
Coffee break
11:00 - 13:00
Round table on the role and function of interconnected research ecosystems
Participants:
Franco Bonollo University of Padova, Italy and President of the iNEST board of directors
Luca Fabbri Consorzio iNEST, General manager
Angelo Montanari University of Udine, Italy and President of the iNEST scientific committee
Cristina Scarpel Almaviva Bluebit, General manager
Giacomo Gentile Collins Aerospace
Moderators: Mattia Fogagnolo, Matteo Zavatteri
13:00 - 14:30
Lunch break*
RT1 scientific session on Mathematical, Numerical, and Data-driven Modeling
14:30 - 14:50 - Raj Narayan Dhara, Mattia Fogagnolo. The inverse problem for the p(x)-laplacian in water distribution models: new mathematical challenges
Abstract: Calderon’s inverse problem consists in determining the value of the weight in model governed by a weighted laplacian PDE from boundary measurements only, that mathematically are represented by the Dirichlet-to-Neumann map. It has been recently observed that the p(x)-laplacian version of this problem emerges when trying to detect losses in water distribution systems. In this talk, we will describe a simplified mathematical framework for this problem, highlight the formidable challenges and present some new results
14:50 - 15:10 - Matteo Zavatteri, Davide Bresolin, Nicolò Navarin. Certified Neural Networks: from Verification to Synthesis
Abstract: Certifying Artificial Intelligence systems has become more and more important, especially when such systems are classified as high-risk. In this talk, we sum up the current results on the automated synthesis of certified neural networks obtained in the contest of iNEST and we discuss challenges, current limitations, open research lines and next steps.
Chair: Mario Putti
RT2 scientific session on Model Order Reduction
15:10 - 15:30 - Niccolò Tonicello, Nicola Clinco, Davide Oberto, Gianluigi Rozza. Challenges for the simulation and model order reduction of turbulent flows: the role of data-enhanced turbulence modelling
Abstract: Turbulence modeling and simulation have long been fundamental in describing a wide range of physical phenomena, from classical aeronautical applications to the dynamics of the entire atmosphere. While significant progress has been made over the years, today's challenge clearly lies in integrating machine learning techniques and, more broadly, leveraging the rapidly growing abundance of data to enhance turbulence modeling, understanding, and simulation. This talk will highlight key areas where machine learning can contribute to turbulence research, including the modeling of coarse-grained solutions, wall modeling, and reduced-order modeling.
15:30 - 15:50 - Guglielmo Padula, Stefano Querin, Stefano Salon, Gianluigi Rozza. A GPR-SDE-based Reduced Order Model for Forecasting and Digital Shadows
Abstract: This talk presents the development of a Digital Shadow of the Mediterranean Copernicus Analysis and Forecast System, a project under the iNEST initiative, jointly developed by SISSA and OGS. A Digital Shadow is a surrogate model designed to replicate the system's behavior efficiently, incorporating data assimilation and uncertainty quantification. The system, consisting of physics and biogeochemistry components, is aimed at improving short-term and long-term forecasts for the Mediterranean region. The methodology is novel and combines three techniques: quadratic manifold dimensionality reduction, Gaussian Process Regression, and Stochastic Differential Equations (SDEs). These methods are employed to approximate system behavior with reduced computational complexity, enabling faster predictions without compromising too much accuracy. The model's performance is validated through the comparison of forecasted and observed data, ensuring that uncertainty quantification aligns with expected confidence intervals. Additionally, parallel computing is utilized by splitting the Mediterranean Sea into different basins to enhance computational efficiency. This approach offers significant potential for both short-term and long-term forecasting applications. The methodology is compared with respect to state of the art techniques.
Chair: Daniela Tonon
15:50 - 16:10
Coffee break
RT3 scientific session on Automatic Learning for Digital Twins
16:10 - 16:30 - Cairoli Francesca, Giacomarra Francesco, Hosseini Mehran, Paoletti Nicola. Certified Guidance for Planning with Deep Generative Model.
Abstract: Deep generative models, such as generative adversarial networks (GANs) and score-based diffusion models, have recently emerged as powerful tools for planning tasks and behaviour synthesis in autonomous systems. Various guidance strategies have been introduced to steer the generative process toward outputs that are more likely to satisfy the planning objectives. These strategies avoid the need for model retraining but do not provide any guarantee that the generated outputs will satisfy the desired planning objectives. To address this limitation, we introduce certified guidance, an approach that modifies a generative model – without retraining it – into a new model guaranteed to satisfy a given specification with probability 1. We focus on Signal Temporal Logic (STL) specifications, which are rich enough to describe non-trivial planning tasks. Our approach leverages neural network verification techniques to systematically explore the generative models' latent spaces, identifying latent regions that are certifiably correct w.r.t. the STL property of interest. We evaluate the effectiveness of our method on four planning benchmarks using GANs and diffusion models. Our results confirm that certified guidance produces generative models that are always correct, unlike existing (non-certified) guidance methods.
16:30 - 16:50 - Camerota Verdù Federico, Castelli Lorenzo, Bortolussi Luca. Scaling Combinatorial Optimization Neural Improvement Heuristic
Abstract: We introduce Limited Rollout Beam Search (LRBS), a beam search strategy for deep reinforcement learning (DRL) based combinatorial optimization improvement heuristics. Utilizing pre-trained models on the Euclidean Traveling Salesperson Problem, LRBS significantly enhances both in-distribution performance and generalization to larger problem instances, achieving optimality gaps that outperform existing improvement heuristics and narrowing the gap with state-of-the-art constructive methods. We also extend our analysis to two pickup and delivery TSP variants to validate our results. Finally, we employ our search strategy for offline and online adaptation of the pre-trained improvement policy, leading to improved search performance and surpassing recent adaptive methods for constructive heuristics
Chair: Alberto Valese
RT4 scientific session on Applications of Digital Twins in Industry, Medicine, Environmental Sciences, Daily Life
16:50 - 17:10 - Federica Adobbati, Stefano Piani, Marco Reale, Lorenzo Bonin, Gianpiero Cossarini, Cosimo Solidoro (OGS), Stefano Salon, Stefano Querin, Paolo Lazzari. Deep learning methods for super-resolution tasks in ocean modelling
Abstract: In regional ocean models, increasing resolution helps capture small- and mesoscale features that remain undetectable at the coarser resolutions used for larger basins. However, high-resolution numerical simulations are computationally expensive and time-consuming. To address this challenge, deep learning methods for super-resolution of marine variables have been increasingly developed in recent years, inspired by techniques from digital image processing. In this study, we focus on the northern Adriatic Sea, a region of the Mediterranean, and present two applications of a super-resolution algorithm. We discuss the strengths and limitations of this approach in the context of marine environmental modeling.
17:10 - 17:30 - Stefano Campanella, Lorenzo Bonin, Stefano Querin, Stefano Salon. Data-driven Earth system modeling
Abstract: Applications of machine learning to Earth system modelling address different scientific questions, and span methodological approaches, Earth system components, time and spatial scales. We will present a high-level overview of current developments in data-driven Earth modelling, drawing from advancements in weather forecasting and with a focus on ocean modelling. In particular, we present current efforts for the development of a global ocean circulation model targeted at subseasonal-to-seasonal time scales and ensemble superresolution.
Chair: Eleonora Spricigo
17:30
Mattia Fogagnolo, Matteo Zavatteri
Closing
* lunch is not included in the registration