Welcome to the website of 2023 Machine Learning Interatomic Potential School for Young & Early Career Researchers (6-10 November 2023)
Thank you to all the participants, speakers, and organizers who helped make this workshop happen! We'll be sending out links to the recordings in the next few days, so stay tuned. We hope your experience at the workshop was positive, interesting, and helpful, and we wish you all the best in your future careers!
Photo by Márcio Soares
Workshop format and goals
MLIP 2023 is a CECAM & Psi-k hybrid school aimed at young and early-career researchers who are interested in using machine learning interatomic potentials (ML-IP) in their research. The two main goals of this school are:
to give researchers a solid introduction to the basic scientific techniques of designing, fitting, and validating MLIPs for chemical/material systems
to provide a platform for those interested in using MLIPs to connect with those involved in MLIP development to accelerate the adoption of ML techniques in the wider atomistic simulation community
MLIP 2023 was the second edition of the MLIP 2021 workshop, and took place in person at Aalto University in Espoo, Finland, from 06–10 November 2023. Remote, online participation was also possible.
The school consisted of keynote lectures on different topics of MLIP as well as hands-on tutorials that allowed the participants to apply the explained concepts to relevant toy cases and also their own research. The invited speakers were chosen from leading scientists in the field of ML-IP, at various career stages, who are well-equipped to share their experience with those getting started in the field.
The MLIP 2023 workshop will focus on:
MLIP 2023 is a hybrid school, allowing prospective participants to engage in the school remotely.
We will utilize widely used video-conference and co-working platforms like Zoom and Slack to best accommodate the remote participants. We will also record the sessions to make talks available in the Resources section, provided the speaker's and participants' consent.
Max Veit (he/him/his) obtained his bachelor's degree from the University of Minnesota, Twin Cities in 2014, and his PhD with Prof. Gábor Csányi at the University of Cambridge in 2018. Before joining Miguel Caro's group at Aalto University in 2022, he was a postdoc in the COSMO group at EPFL, led by Prof. Michele Ceriotti. His research interests center on the development of machine learning models for simulating complex, realistic systems.
Lead organizer, on-site contact
Felix-Cosmin Mocanu is working with Prof. Saiful Islam in Oxford on modelling Li-ion battery cathodes. He has been postdoctoral researcher at the Laboratoire de Physique Théorique at École Normale Supérieure, in Paris, working with Francesco Zamponi and Ludovic Berthier on the properties of glassy systems at low temperatures. He did his PhD studies at the University of Cambridge with Prof. Stephen Elliott and Gábor Csányi on modelling phase-change memory materials with machine learning interatomic potentials.
Chiheb Ben Mahmoud is a postdoc in the group of Prof. Volker Deringer, Oxford University. He earned his PhD in 2023 at the Swiss Federal Institute of Technology (EPFL), supervised by Prof. Michele Ceriotti. His research focuses on leveraging machine-learning techniques to learn electronic structure properties like the electronic density of states, and on applying these models to study electronic thermal excitations in condensed matter.
Kevin Kazuki Huguenin-Dumittan graduated with a BSc and MSc in Physics from ETH Zurich and is currently working as a PhD student in Prof. Michele Ceriotti’s group at EPFL. He is currently working on the theory of representations of atomic structures for physics inspired machine learning models with a special focus on long range interactions in condensed phases.
Jigyasa Nigam graduated with an MS in solid state physics from the Indian Institute of Space Science and Technology and is currently working as a PhD student in Prof. Michele Ceriotti’s group at EPFL. She is interested in the theory of atomic representations and has developed and extended multiple frameworks allowing for systematic description of atomic properties.
Sanggyu "Raymond" Chong obtained his BS, MS, and PhD degrees in Chemical and Biomolecular Engineering from Korea Advanced Institute of Science and Technology (KAIST), where he performed the computational design of metal-organic frameworks for various applications. Since 2022, he has been working as a postdoctoral researcher in the Laboratory of Computational Science and Modelling (COSMO) led by Prof. Michele Ceriotti, at EPFL, Switzerland, and he is currently investigating the robustness of local and/or component-wise predictions made by atomistic ML models.
Federico Grasselli is a Collaborateur Scientifique in the Laboratory of Computational Science and Modeling (COSMO), led by Prof. Michele Ceriotti, at EPFL, Switzerland. He earned his PhD degree in Physics and Nanosciences from the University of Modena and Reggio Emilia, Italy, working on indirect excitons under the supervision of Prof. Guido Goldoni, and he has been postdoc fellow in Prof. Stefano Baroni's group at SISSA, Italy, where he contributed to advancements in the ab-initio theory of heat and charge transport and its application to planetary materials.
Davide Tisi graduated in Physics from University of Modena and Reggio Emilia, Italy. He earned his PhD in SISSA under the supervision of Prof. Stefano Baroni, working on the computation of transport properties of liquids from ab initio approach and NN potential. He is currently a post-doc in the Laboratory of Computational Science and Modelling (COSMO), led by Prof. Michele Ceriotti, at EPFL, Switzerland.
Carlo Maino is a PhD candidate at the University of Warwick in the EPSRC-supported Centre for Doctoral Training in Modelling of Heterogeneous Systems (HetSys CDT), where he is working on accelerating theoretical spectroscopy using machine learning. He graduated from King's College London with a BSc in Physics in 2019 and from the University of Warwick with a Postgraduate Diploma in Modelling of Heterogeneous Systems in 2021. As part of his Swiss Civil Service at CREALP he is applying machine learning methods to problems ranging from predicting debris flows and solid transport in rivers to forecasting groundwater levels in Valais.
Miguel Caro graduated with a Physics degree from University of La Laguna, Tenerife, Spain. He then pursued a PhD in computational condensed-matter physics under Prof. Eoin O’Reilly at the Tyndall National Institute in Cork, Ireland. After the PhD, he moved to Aalto University, Finland as a postdoc in 2013; since 2020, he is an Academy of Finland Research Fellow there. Dr. Caro’s current research interests concern the atomistic simulation of real materials, especially carbon-based materials, using a battery of simulation tools and methodologies, from density functional theory to machine learning.