Machine-learned potentials

• 11–14 Jan 2027

  Computational electrochemistry in the era of AI

  workshop · in-person · Beijing, CN · CECAM Beijing node

  Four days on simulating electrochemical interfaces for batteries, fuel cells and electrolysers, and on what machine-learned potentials and AI-driven workflows change about how those interfaces are modelled.

  materials-modelingml-potentialscatalysiselectrochemistryregistration 10 Dec 2026

• 25–27 Jan 2027

  Automating atomistic machine learning

  workshop · in-person · Lausanne, CH · CECAM

  This workshop focuses on automating machine-learned interatomic potentials (MLIPs) to make them a routine, accessible tool in computational materials modelling. It covers integrating MLIPs into automation frameworks, tackling challenges like active learning, GPU training, and data provenance. Topics include automating data selection, descriptors, and regression. Key discussions address which parts of MLIP development should be automated, interfacing with DFT infrastructure, the role of pre-trained foundation models and AI agents, and future applications.

  ml-potentialssoftware-hpcmaterials-modelingregistration 23 Dec 2026

• 3 Mar 2027

  Machine Learning Assisted Molecular (Thermo)Dynamics

  workshop · in-person · Lausanne, CH · Michele Ceriotti, Marylou Gabrié, Simon Olsson, Grant Rotskoff

  CECAM Flagship workshop on machine learning for molecular simulations, covering ML interatomic potentials, coarse-grained models, and generative models. It brings together researchers from computational chemistry, physics, applied maths, and ML to discuss advances and key challenges in transferability, reliability, scalability, and bridging timescales, connecting short-time dynamics with long-time conformational sampling and kinetic observables.

  molecular-dynamicsml-potentialsml-chemistry

• 22–25 Mar 2027

  Challenges in ionic fluids: Theory, simulation, and experiment

  workshop · in-person · Lausanne, CH · Stephen Cox (Durham University); Susan Perkin (Oxford University); Benjamin Rotenberg (CNRS and Sorbonne Université)

  Ionic fluids, such as electrolyte solutions and ionic liquids, are essential in biological and physical sciences but are challenging to understand due to their multiscale nature and the competition between short-range steric and long-range Coulomb interactions. This workshop brings together researchers in theory, simulation, and experiment to explore how recent advances—such as machine-learned potentials, classical density functional theory, and advanced spectroscopic techniques—can help tackle these major outstanding issues.

  molecular-dynamicsdftml-potentialsspectroscopysoft-matter

• 28 Mar – 2 Apr 2027

  Current Topics in Theoretical Chemistry 2027

  workshop · in-person · CECAM-TW, TW · Julia Contreras, Chao-Ping Hsu, Ángel Martín Pendás, Eduard Matito, Henryk Witek

  Workshop on current topics in theoretical chemistry, prioritizing areas that enhance fundamental understanding and contribute to academic communities in Taiwan and the broader Asian region. It highlights two critical fields: density functional theories, addressing fractional charge and spin errors; and dynamics simulations for revealing catalysis, solvation, and complex processes, including machine-learning-enabled simulations and nonadiabatic nuclear-electronic dynamics for coupled electronic-nuclear motions. It aims to share advanced research.

  catalysisdftexcited-statesml-potentialsmolecular-dynamics

• 2–7 Apr 2027

  Machine Learning for Atomistic Simulations of Materials

  school · in-person · Bad Honnef, DE

  This summer school focuses on the theoretical foundations and practical implementation of machine learning for atomistic simulations of materials. Lectures cover the construction of ML interatomic potentials, representations of atomic environments, learning algorithms, validation strategies, and applications to diverse materials classes, emphasizing the integration of ML with established atomistic simulation methods.

  ml-potentialsml-chemistrymaterials-modelingmolecular-dynamicseducation-training

• 5–9 Apr 2027

  Chemical and materials machine learning school (CAMMLs)

  school · hybrid · Daresbury, GB · PSDI, AIchemy, STFC-SCD, CCP5, CCP9, and CECAM

  An international training course on machine learning for materials and molecular simulations, targeting PhD students and industrial applicants. It covers the basics of machine learning, machine learning interatomic potentials, and graph neural networks, featuring talks, practical sessions, and a poster session.

  ml-potentialsml-chemistrymaterials-modelingeducation-training