BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ENCCS - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://enccs.se
X-WR-CALDESC:Events for ENCCS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20270328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20271031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20260915T090000
DTEND;TZID=Europe/Stockholm:20260916T120000
DTSTAMP:20260622T151058
CREATED:20260609T130222Z
LAST-MODIFIED:20260611T141705Z
UID:38713-1789462800-1789560000@enccs.se
SUMMARY:[Workshop] Practical Data Wrangling
DESCRIPTION:Register here\n\n\n\n\n\n\nOverview\n\n\n\nData is essential in data-driven projects\, as it forms the foundation for all subsequent analysis\, modeling\, and decision-making. Depending on the specific task\, raw data may be collected from a wide variety of sources such as databases\, APIs\, sensors\, logs\, documents\, or images. Before it can be effectively used for analysis or machine learning\, raw data must be cleaned\, transformed\, validated\, and organized into a consistent and usable format. As data comes in many different forms\, including numerical\, categorical\, time series\, text\, event/log\, and image data\, the tools and techniques used for data wrangling can vary significantly depending on the data type and the requirements of the task. \n\n\n\nIn this workshop\, we will cover practical data wrangling techniques for numerical\, categorical\, time series\, text\, event/log\, and image data. Participants will learn how to detect and handle missing values\, outliers\, inconsistencies\, duplicates\, and formatting problems. We will demonstrate methods for transforming and encoding categorical variables\, parsing and aggregating temporal data\, processing unstructured text\, analyzing event logs\, and preparing image datasets for machine learning and analytics. Each session combines concepts\, demonstrations\, and hands-on exercises using realistic datasets to help participants develop practical skills that can be applied immediately in downstream modeling tasks. \n\n\n\nWho is this workshop for?\n\n\n\nThis workshop is designed for \n\n\n\n\ndata practitioners who regularly work with raw or semi-structured data and need to prepare it for analysis or modeling.\n\n\n\ndata analysts\, data scientists\, machine learning engineers\, and software engineers who want to strengthen their practical data preprocessing skills.\n\n\n\ngraduate students and researchers working with real-world datasets who need a structured approach to data cleaning and transformation.\n\n\n\n\nPrerequisites\n\n\n\nTo ensure a smooth learning experience\, participants should have: \n\n\n\n\nbasic proficiency in Python programming (variables\, loops\, functions) and some libraries like NumPy\, Pandas\, and Matplotlib/Seaborn.\n\n\n\nbasic familiarity with statistics (mean\, median\, variance) and introductory machine learning concepts will make it easier to follow the examples.\n\n\n\nbe comfortable reading and writing simple code and working with datasets in a notebook environment.\n\n\n\n\nKey Takeaways\n\n\n\nIn this workshop\, participants will learn how to systematically clean and structure different types of real-world data\, including tabular\, time series\, text\, event/log\, and image data.By the end of this workshop\, participants will: \n\n\n\n\ngain practical experience in building reproducible data wrangling pipelines that improve data quality and usability for downstream data analysis and machine learning.\n\n\n\nunderstand common pitfalls in messy datasets and how to address them effectively using standard techniques and tools.\n\n\n\nbe able to confidently transform raw datasets into well-structured inputs suitable for downstream modeling and analysis tasks.\n\n\n\n\nTentative Schedule (TBA)\n\n\n\nDay 1 \n\n\n\n\nIntroduction\n\n\n\nData Types and Data Storage Formats\n\n\n\nNumerical Data Wrangling\n\n\n\nCategorical Data Wrangling\n\n\n\nTime Series Data Wrangling\n\n\n\n\nDay 2 \n\n\n\n\nText Data Wrangling\n\n\n\nEvent and Log Data\, and Image Data Wrangling\n\n\n\nWrangling Other Data Types\n\n\n\nSummary and Key Takeaways\n\n\n\n\nRegulations\n\n\n\nDue to EuroCC3 regulations\, we CAN NOT ACCEPT generic or private email addresses. Please use your official university or company email address for registration. \n\n\n\nThis training is for users that live and work in the European Union or a country associated with Horizon 2020. You can read more about the countries associated with Horizon2020 HERE. \n\n\n\nContact\n\n\n\nFor questions regarding this workshop or general questions about ENCCS training events\, please contact training@enccs.se.
URL:https://enccs.se/events/workshop-practical-data-wrangling/
CATEGORIES:ENCCS Event
ATTACH;FMTTYPE=image/jpeg:https://media.enccs.se/2026/06/practical-data-wrangling.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20260930T100000
DTEND;TZID=Europe/Stockholm:20260930T113000
DTSTAMP:20260622T151058
CREATED:20260609T141648Z
LAST-MODIFIED:20260611T141815Z
UID:38717-1790762400-1790767800@enccs.se
SUMMARY:[Webinar] Foundation Models for Atoms: Machine-Learned Interatomic Potentials in Practice
DESCRIPTION:Register here\n\n\n\n\n\n\nAbout this webinar\n\n\n\nQuantum-mechanical methods such as density functional theory (DFT) are accurate but limited to small systems and short timescales. Classical force fields are fast but often not accurate or transferable enough. Machine-learned interatomic potentials (MLIPs) could break this trade-off between accuracy and scale\, and the field is now moving at remarkable speed. So-called universal or “foundation” models (e.g. MACE-MP\, UMA\, MatterSim\, Orb\, the DPA/OpenLAM series) are pre-trained on tens to hundreds of millions of DFT calculations spanning the periodic table. These models approach DFT-level accuracy at a small fraction of the cost. They can be applied out-of-the-box (“zero-shot”) to almost any chemistry. Afterward\, they can be fine-tuned to a specific system with a small amount of targeted data. This shortens the path from question to result for both academic and industrial users. \n\n\n\nIn this webinar\, we will give a conceptual tour of this rapidly evolving landscape and what it means for everyday computational research on HPC systems. We will cover: \n\n\n\n\nwhat universal MLIPs are and how they differ from classical force fields and system-specific ML potentials;\n\n\n\nthe practical pre-train → fine-tune workflow and when out-of-the-box use is (and is not) good enough;\n\n\n\nthe new generation of batched\, GPU-accelerated simulation engines (e.g. TorchSim\, kUPS) built for high-throughput MLIP simulation;\n\n\n\nhow to choose and trust a model using open benchmarks;\n\n\n\nand close with a brief outlook on where the field is heading. This includes ML making its way into electronic-structure theory itself\, with learned density functionals. We will also include a short demo on European HPC resources. Throughout\, we will point to open models\, datasets\, benchmarks\, and codes. Participants can try these on their own problems right after the webinar.\n\n\n\n\nWho is the webinar for\n\n\n\nThis webinar is intended for: \n\n\n\n\nResearchers and students in computational materials science\, chemistry\, and condensed-matter physics who use DFT or ab initio MD and want to reach larger systems and longer timescales without giving up accuracy\n\n\n\nUsers of classical molecular dynamics (LAMMPS\, GROMACS\, ASE workflows) curious about upgrading to ML-based potentials\n\n\n\nIndustry R&D scientists and engineers exploring AI-accelerated materials and molecular discovery\n\n\n\nHPC support staff and research software engineers who want an overview of the modern MLIP software stack and what it needs from GPU systems\n\n\n\nAnyone curious about how the foundation-model paradigm from language and vision AI is reshaping simulation in the natural sciences\n\n\n\n\nNo prior experience with multiplet theory\, density functional theory (DFT)\, or many-body methods is required. Familiarity with basic concepts from solid-state or atomic physics is sufficient; the role of data and HPC in modern electronic-structure studies will be introduced at a conceptual level. \n\n\n\nKey takeaways\n\n\n\nBy the end of this webinar\, participants will: \n\n\n\n\nUnderstand what universal machine-learned interatomic potentials are and why they deliver near-DFT accuracy at a fraction of the cost\n\n\n\nKnow the practical pre-train → fine-tune workflow: when an off-the-shelf foundation model is sufficient\, when and how to fine-tune it with a small targeted dataset\n\n\n\nGet an overview of the modern MLIP software stack\, from ASE/LAMMPS integrations to GPU-native\, batched engines such as TorchSim\, and what it takes to run it efficiently on EuroHPC systems\n\n\n\nBe able to critically select and validate a model using open benchmarks and understand why no single model wins on every axis\n\n\n\nGain an outlook on emerging directions: long-range electrostatics\, MLIPs that predict polarisation and spectra\, the use of machine learning within DFT itself\, and early work on AI agents that help orchestrate computational workloads\n\n\n\n\nSpeaker and moderator\n\n\n\n\nKarim Elgammal\n\n\n\nYonglei Wang/Wei Li\n\n\n\n\nFor any questions contact us at training@enccs.se \n\n\n\nMore events & contact\n\n\n\nCheck out more upcoming events from ENCCS and our European network at HERE\, as well as available ENCCS lesson materials\, suitable also for self-learning. \n\n\n\nFor questions regarding this workshop or general questions about ENNCS training events\, please contact training@enccs.se \n\n\n\nSchedules can change!\n\n\n\nTo ensure that everyone has the opportunity to participate\, we kindly request that you let us know as soon as possible if you are unable to attend an event after registering. \n\n\n\nPlease send us an email at training@enccs.se to cancel your attendance. \n\n\n\nWe understand things can change\, but repeated cancellations without notice may unfortunately result in your name being removed from future event registration lists. \n\n\n\nRegulations\n\n\n\nDue to EuroCC2 regulations\, we CAN NOT ACCEPT generic or private email addresses. Please use your official university or company email address for registration. \n\n\n\nThis training is intended for users established in the European Union or a country associated with Horizon 2020. You can read more about the countries associated with Horizon2020 HERE.
URL:https://enccs.se/events/webinar-foundation-models-for-atoms/
CATEGORIES:ENCCS Event
ATTACH;FMTTYPE=image/jpeg:https://media.enccs.se/2026/06/foundation-models-1.jpg
END:VEVENT
END:VCALENDAR