April 28-29-30, 2026
Location: Villa Grumello (https://www.villadelgrumello.it/) right on the shore of Como Lake, Italy

Data-inspired and hybrid physics-data techniques are being applied across a wide spectrum of nonlinear systems, enhancing capabilities in modeling, simulation, prediction, and optimization. These methods provide powerful new ways to uncover hidden patterns, develop predictive models, and manage the inherent complexities of dynamical systems. Strategies exploiting neural networks, deep learning, and hybrid physics-data architectures (e.g., physics-inspired symbolic regression, deep symbolic regression methods) which merge physical insights with machine learning to derive interpretable models are particularly welcome. The colloquium will provide opportunities for discussion, collaboration, and exploration of new research directions in machine learning for nonlinear dynamics.

The meeting will feature invited keynote lectures, contributed presentations, and flash (10 min) talks within a single-track format to encourage discussion and exchange.

Potential topics include but are not limited to:

• Data-driven methods to discover nonlinear dynamics and physical laws
• Deep Learning-based and data-driven model order reduction
• Characterization of nonlinear resonances and dynamic phenomena via machine learning
• Physics-enhanced machine learning to tackle nonlinear dynamics challenges
• Learning and predicting nonlinear dynamics using Neural Networks
• Deep learning-based and data-driven closure models
• Data-driven control & reinforcement learning for dynamical systems

Chair:

Alice Cicirello (Cambridge University)
Department of Engineering, Trumpington Street, CB2 1PZCambridge, UK
email: ac685 at cam.ac.uk

Co-Chairs:

Andrea Manzoni (Politecnico di Milano)

Eleni Chatzi (ETH Zurich)

Local organising Committee:

Andrea Manzoni (Politecnico di Milano)

Attilio Frangi (Politecnico di Milano)

Pierpaolo Belardinelli (Universita’ Politecnica delle Marche)

Please note:

• We can host only about 50-60 people!
• The will be an initial invitation only phase
• At a later stage, places will be made available for other people who would like to participate. PhD students and Postdocs will be given priority.