SISSA MathLab

20/10/2026

🆕 Federico Tamburlin, Giovanni Canali, Giuseppe Alessio D’Inverno, Nicola Demo, Andrea Mola, and Gianluigi Rozza are the authors of “Constraint-driven optimization and parametrization of industrial NURBS geometries via neural deformation field”, a new scientific article now fully accessible on Computer Methods in Applied Mechanics and Engineering (Elsevier).

⛴️ The study presents a differentiable framework for parametrizing and optimizing complex industrial CAD geometries. By combining neural networks with physics-informed constraints, the approach enables shape optimization while preserving geometric requirements, with applications to ship hull design.

🔗 Read the full article: https://www.sciencedirect.com/science/article/pii/S0045782526007735



𝘍𝘪𝘨𝘶𝘳𝘦 𝘳𝘦𝘱𝘳𝘰𝘥𝘶𝘤𝘦𝘥 𝘧𝘳𝘰𝘮 𝘵𝘩𝘦 𝘢𝘶𝘵𝘩𝘰𝘳𝘴' 𝘱𝘳𝘦𝘱𝘳𝘪𝘯𝘵, 𝘢𝘷𝘢𝘪𝘭𝘢𝘣𝘭𝘦 𝘰𝘯 𝘢𝘳𝘟𝘪𝘷 𝘶𝘯𝘥𝘦𝘳 𝘊𝘊 𝘉𝘠-𝘕𝘊-𝘕𝘋 4.0 𝘭𝘪𝘤𝘦𝘯𝘴𝘦

19/10/2026

14/10/2026

🤝 SISSA mathLab is a partner in m.a.r.i.n.A.I. – Main Advancements to Reduce Irradiated Noise with Artificial Intelligence, a project led by Fincantieri, in collaboration with Groupe Beneteau Italia, MICAD, Fast Computing, and Università degli studi di Trieste, with the involvement of MARE Technology Cluster FVG.

🎯 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐨𝐛𝐣𝐞𝐜𝐭𝐢𝐯𝐞𝐬
The m.a.r.i.n.A.I. project aims to reduce underwater noise generated by ships and yacht engines through an innovative approach combining computational fluid dynamics, hydroacoustic simulations, and machine learning.

🚢 𝐄𝐱𝐩𝐞𝐜𝐭𝐞𝐝 𝐫𝐞𝐬𝐮𝐥𝐭𝐬
The project will develop a machine learning-based algorithm to support the design of more efficient propulsion systems, reducing underwater noise, fuel consumption, and design time.

💸 The m.a.r.i.n.A.I. project is co-funded by the European Union through the Friuli Venezia Giulia Regional Program ERDF 2021–2027.

🔹Total eligible expenditure: €1,572,912.64
🔹Public funding granted: €1,021,794.57
🔹of which EU contribution (ERDF): 40%

12/10/2026

🆕 A new article by Moaad Khamlich, Niccolò Tonicello, Federico Pichi and Gianluigi Rozza has been published in Journal of Computational Physics (Elsevier): “A multi-fidelity and parametric reduced-order modeling framework with optimal transport-based interpolation: Applications to diffused-interface two-phase flows”.

🌊 The study presents a new Optimal Transport-based Reduced Order Modeling framework for the efficient simulation of complex two-phase flows. By combining low- and high-fidelity models, the approach improves the accuracy of computationally inexpensive simulations through interpolation techniques, while also addressing parametric problems.

🔗 Read the full article:
https://www.sciencedirect.com/science/article/pii/S0021999126008296



𝘍𝘪𝘨𝘶𝘳𝘦 𝘳𝘦𝘱𝘳𝘰𝘥𝘶𝘤𝘦𝘥 𝘧𝘳𝘰𝘮 𝘵𝘩𝘦 𝘢𝘶𝘵𝘩𝘰𝘳𝘴' 𝘱𝘳𝘦𝘱𝘳𝘪𝘯𝘵 𝘢𝘷𝘢𝘪𝘭𝘢𝘣𝘭𝘦 𝘰𝘯 𝘢𝘳𝘟𝘪𝘷

08/10/2026

🎓 Yesterday, our Giovanni Canali and Isabella Carla Gonnella introduced the SISSA SIAM Student Chapter to the students who have just joined SISSA as part of the new PhD cycle.

📐 The SISSA SIAM Student Chapter is a student organization affiliated with the Society for Industrial and Applied Mathematics. It brings together students interested in applied mathematics and computational science, fostering exchange and collaboration within the academic community. The Chapter also organizes seminars, scientific events, and networking activities.

🤝 Later, our Lorenzo Tomada also introduced Y-SIMAI, the Youth Commission of SIMAI Società Italiana di Matematica Applicata e Industriale, highlighting another opportunity for young researchers to engage with the broader applied mathematics community.

25/09/2026

🆕 A new article by Rahul Halder, Giovanni Stabile, and Gianluigi Rozza, “Coupling Physics Informed Neural Networks with External Solvers”, has been published in Elsevier’s Computer Physics Communications.

🧠 The study introduces a method for coupling Physics-Informed Neural Networks (PINNs) with external numerical solvers, enabling gradient-based optimization without requiring direct access to the solvers' computational graphs.

🔗 Discover the article:
https://www.sciencedirect.com/science/article/abs/pii/S0010465526004054



𝘍𝘪𝘨𝘶𝘳𝘦 𝘳𝘦𝘱𝘳𝘰𝘥𝘶𝘤𝘦𝘥 𝘧𝘳𝘰𝘮 𝘵𝘩𝘦 𝘢𝘶𝘵𝘩𝘰𝘳𝘴' 𝘱𝘳𝘦𝘱𝘳𝘪𝘯𝘵, 𝘭𝘪𝘤𝘦𝘯𝘴𝘦𝘥 𝘶𝘯𝘥𝘦𝘳 𝘊𝘊 𝘉𝘠-𝘕𝘊-𝘕𝘋 4.0

24/09/2026

🌍 Yesterday, our professor Gianluigi Rozza was named among the first Future Vision Generators of the FVG Ambassador Program, in the category dedicated to Ambassadors for Congresses, Conferences and International Events.

🤝 Promoted by with the endorsement of the President of Regione Friuli Venezia Giulia, the program recognizes academic and entrepreneurial figures who have contributed, through their work, to strengthening the region’s international visibility, attractiveness, and connections.

🏅We are proud to see Gianluigi’s commitment to building international scientific networks and bringing major research initiatives to Friuli Venezia Giulia recognized with this distinction.

➡ https://www.sissa.it/news/gianluigi-rozza-among-first-future-vision-generators-fvg-ambassador-program

SISSA MathLab | SIMAI

09/09/2026

📘 A new book chapter by Dario Coscia and Gianluigi Rozza, “Bayesian Perspectives in Scientific Machine Learning: Methods, Challenges, and Opportunities”, is featured in the eBook Numerical Analysis and Scientific Computing: an Anthology, published by Springer Nature in the Lecture Notes in Computational Science and Engineering series.

📊 The chapter explores Bayesian approaches to Scientific Machine Learning (SciML) and their potential to make data-driven scientific models more reliable. It reviews their role in uncertainty quantification, continual learning, interpretability, and robustness, while highlighting current challenges and promising research directions.

🔗 Preview the chapter:
https://link.springer.com/chapter/10.1007/978-3-032-33428-2_11

Scientific Machine Learning (SciML) is an interdisciplinary field combining data-driven machine learning with physics-based modeling, for accurate predictions across scientific and engineering applications. Despite the great successes of SciML, the widespread...

05/09/2026

🆕 A new article by Armin Sheidani, Michele Girfoglio, Annalisa Quaini and Gianluigi Rozza has been published in Results in Engineering (Elsevier): “Enhancing the accuracy of under-resolved numerical simulations of atmospheric flows with super resolution”.

🌦️ The study explores how deep learning-based super-resolution techniques can improve coarse-grid simulations of mesoscale atmospheric flows while containing computational costs. Among the approaches tested, a multi-scale convolutional neural network achieves the best balance of accuracy, robustness and computational efficiency, particularly for more complex flows.

🔗 Read the full article:
https://www.sciencedirect.com/science/article/pii/S2590123026036984



𝘍𝘪𝘨𝘶𝘳𝘦 𝘢𝘥𝘢𝘱𝘵𝘦𝘥 𝘧𝘳𝘰𝘮 𝘵𝘩𝘦 𝘢𝘶𝘵𝘩𝘰𝘳𝘴' 𝘱𝘳𝘦𝘱𝘳𝘪𝘯𝘵 𝘢𝘷𝘢𝘪𝘭𝘢𝘣𝘭𝘦 𝘰𝘯 𝘢𝘳𝘟𝘪𝘷

03/09/2026

🧮 Our Gianluigi Rozza will be one of the speakers at the round table “Mathematics, Innovation and Knowledge Transfer”, bringing our perspective on the role of applied mathematics in connecting research, technology, and innovation.

🧮 The hidden mathematics behind innovation

❓What connects fundamental research to real-world solutions?
At the round table "Mathematics, Innovation and Knowledge Transfer", leading voices from academia and industry will discuss how mathematical research fuels technological, economic and social development.

📅 8 September 2026, 15:30
📍 Budinich Lecture Hall, ICTP – Abdus Salam International Centre for Theoretical Physics
🎟️ Open event

The event is organised within the 1st Italy–China Mathematical Bilateral Meeting by ICTP: International Centre for Theoretical Physics, SISSA and INdAM – Istituto Nazionale di Alta Matematica "Francesco Severi", together with the Beijing International Center for Mathematical Research at Peking University, Great Bay University and Dongguan University of Technology.

➡ https://www.sissa.it/news/hidden-mathematics-behind-innovation-italy-and-china-meet-trieste