<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>CompChem Observer — newly added machine-learned potentials events</title>
  <link href="https://compchem.observer/topics/ml-potentials.xml" rel="self"/>
  <link href="https://compchem.observer"/>
  <id>https://compchem.observer/topics/ml-potentials/</id>
  <updated>2026-09-28T15:41:52Z</updated>
  <author>
    <name>CompChem Observer</name>
  </author>
  <entry>
    <title>Studying dynamics in soft matter and porous materials</title>
    <link href="https://compchem.observer/events/studying-dynamics-in-soft-matter-and-porous-materials-2026/"/>
    <id>https://compchem.observer/events/studying-dynamics-in-soft-matter-and-porous-materials-2026/</id>
    <updated>2026-09-28T00:00:00Z</updated>
    <summary>CECAM Flagship School on dynamics in soft matter and porous materials, covering polymer dynamics, lattice Boltzmann, coarse-graining, and machine learning, with hands-on sessions using ESPResSo and waLBerla.</summary>
  </entry>
  <entry>
    <title>Machine Learning Assisted Molecular (Thermo)Dynamics</title>
    <link href="https://compchem.observer/events/machine-learning-assisted-molecular-thermo-dynamics-2027/"/>
    <id>https://compchem.observer/events/machine-learning-assisted-molecular-thermo-dynamics-2027/</id>
    <updated>2026-09-28T00:00:00Z</updated>
    <summary>CECAM Flagship workshop on machine learning for molecular simulations, discussing ML interatomic potentials, coarse-grained models, generative models, and challenges in transferability, reliability, and scalability.</summary>
  </entry>
  <entry>
    <title>Challenges in ionic fluids: Theory, simulation, and experiment</title>
    <link href="https://compchem.observer/events/challenges-in-ionic-fluids-theory-simulation-and-experiment-2027/"/>
    <id>https://compchem.observer/events/challenges-in-ionic-fluids-theory-simulation-and-experiment-2027/</id>
    <updated>2026-09-28T00:00:00Z</updated>
    <summary>Workshop on ionic fluids, uniting theory, simulation, and experiment to tackle multiscale challenges. Topics include ML potentials, classical DFT, and advanced spectroscopic techniques.</summary>
  </entry>
  <entry>
    <title>Current Topics in Theoretical Chemistry 2027</title>
    <link href="https://compchem.observer/events/current-topics-in-theoretical-chemistry-2027-2027/"/>
    <id>https://compchem.observer/events/current-topics-in-theoretical-chemistry-2027-2027/</id>
    <updated>2026-09-28T00:00:00Z</updated>
    <summary>Workshop on current topics in theoretical chemistry, focusing on density functional theories and dynamics simulations, including nonadiabatic nuclear-electronic dynamics and machine learning for catalysis.</summary>
  </entry>
  <entry>
    <title>Machine Learning Interatomic Potentials: Bridging Model Development and Interdisciplinary Applications</title>
    <link href="https://compchem.observer/events/mlip-model-development-applications-2026/"/>
    <id>https://compchem.observer/events/mlip-model-development-applications-2026/</id>
    <updated>2026-09-20T00:00:00Z</updated>
    <summary>A CECAM workshop in Taiwan that puts the people who build machine-learned interatomic potentials in the same room as the people who apply them, covering descriptors, message-passing models, transferability and cost.</summary>
  </entry>
  <entry>
    <title>Computational electrochemistry in the era of AI</title>
    <link href="https://compchem.observer/events/computational-electrochemistry-ai-2027/"/>
    <id>https://compchem.observer/events/computational-electrochemistry-ai-2027/</id>
    <updated>2026-09-20T00:00:00Z</updated>
    <summary>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.</summary>
  </entry>
  <entry>
    <title>Automating atomistic machine learning</title>
    <link href="https://compchem.observer/events/automating-atomistic-machine-learning-2027/"/>
    <id>https://compchem.observer/events/automating-atomistic-machine-learning-2027/</id>
    <updated>2026-09-20T00:00:00Z</updated>
    <summary>Machine-learned interatomic potentials still lean on hand-tuning and personal experience. This workshop looks at the automated workflows, provenance and reproducible benchmarking needed to make them a routine tool.</summary>
  </entry>
</feed>
