Machine learning approaches in materials science


13 Sept.			09:00 - 10:30

ROOM 8

ADVANCED MATERIALS
TT.IX - Technical Multi-Track with Parallel SYMPOSIA
Machine learning approaches in materials science
Co-organized with iENTRANCE@ENL, INRIM Chair: Pietro ASINARI, INRIM
This session delves into the transformative impact of machine learning (ML) on materials science. As the complexity of materials and the vastness of experimental data grow, ML offers powerful tools for accelerating the discovery, design, and optimization of new materials. The session will explore various ML techniques, including supervised and unsupervised learning, neural networks, and reinforcement learning, and their application in predicting material properties, discovering novel compounds, and optimizing manufacturing processes. Case studies highlighting successful ML-driven advancements in areas such as nanomaterials, polymers, and energy storage will be discussed. Attendees will gain insights into the integration of ML with traditional experimental and computational methods, as well as the challenges and future directions in this rapidly evolving field.

TT.IX.E.1	Massimo BOCUS - CV Center for Molecular Modeling, Ghent University Machine learning potentials to bridge the gap between theory and experiments in zeolite catalysis
TT.IX.E.2	Paolo DE ANGELIS - CV Polytechnic of Turin Investigating Ion Transport in Solid Electrolyte Interfaces with Advanced Reactive Force Fields
TT.IX.E.3	Francesco MAMBRETTI - CV IIT How does structural disorder impact heterogeneous catalysts? Ammonia decomposition on ionic crystals
TT.IX.E.4	Umberto RAUCCI - CV IIT Revealing the Dynamic Behavior of Heterogeneous Catalysts via Machine Learning-Driven Molecular Dynamicss