A Spark to Begin
Before we dive into the day’s discoveries, we invite you to experience a moment that will awaken your senses and set the tone for what’s to come. Something unexpected will unfold , a spark of creativity and wonder to open the stage and the mind.

After this opening act, Valeriu, our day chair and a leading figure in the advanced computing community, will take the stage to officially open the Advanced Computing User Day.

Keynote by Maria Girone, Head of CERN openlab

CRISPR gene editing is transforming how we approach challenges in health, food, and sustainability, but one question still slows everyone down: which guideRNA will actually work?

MPI-AMRVAC is a parallel adaptive mesh refinement framework aimed at solving partial differential equations by a number of different numerical schemes. It is written in Fortran 90 and uses MPI for parallelisation across many CPUs.

In modern HPC infrastructure, most compute power is however not in the CPUs but in accelerators such as GPUs. In order to make use of this compute power, we have enabled MPI-AMRVAC to run on GPUs using OpenACC, enabling larger-scale simulations than ever before.

I will discuss the advantages and challenges of OpenACC in our experience, and highlight the achieved performance improvement in MPI-AMRVAC on both Snellius and LUMI.

Artificial intelligence has been transformative for earth and environmental sciences: nowadays this technique is a common instrument scientists’ toolbox. In the domain of meteorology, machine learning often displays superior accuracy compared to traditional computational methods. Even in weather prediction, where complex numerical PDE-solving codes have seen decades of development, graph neural networks and transformer architectures have proven to produce more skillful forecast at a fraction of the computational cost. Inspired by the recent developments in generative modeling of textual data through large language models, several research groups have made efforts to design a foundation model for weather and climate, one that allows fine-tuning for specific objectives and benefits from a pre-trained rich latent space. The WeatherGenerator EU project aims to develop the leading European AI foundation model of the atmosphere. This model will be pre-trained with petabytes of multi-modal data (reanalyses, station observations, satellite products,…) on Europe’s first exascale-class supercomputers, ultimately keeping Europe’s global forecast capabilities at the forefront as we enter an era of democratized data-driven weather prediction.

LOFAR, Europe’s powerful low-frequency radio telescope, produces vast amounts of data, making high-resolution imaging a major challenge. Thanks to new algorithms, SURF’s Spider platform, and AI expertise, researchers now achieve unprecedented detail, delivering the sharpest LOFAR images of the Universe so far.

Digital Twins (DT), highly accurate virtual representations of physical entities, have revolutionized industries by integrating numerical simulations and observational data to create realistic, dynamic models. Initially developed for industrial applications, digital twins have expanded into diverse domains. They enable accurate predictions by simulating real-world performance, identifying potential issues, and iterating feedback loops for optimized decision-making. This paradigm leverages advanced computational techniques to enhance our understanding and management of complex systems. The Horizon Europe interTwin project has developed a highly generic Digital Twin Engine (DTE) to support interdisciplinary Digital Twins(DT). The project brought together infrastructure providers, technology providers and DT use cases from different domains. This group of experts enables the co-design of both the DTE Blueprint Architecture and the prototype platform; not only benefiting end users like scientists and policymakers but also DT developers. The main contributions of the DTE are: (1) a federated architecture that allows seamless integration of distributed computing and storage resources across various institutions, (2) standardized interfaces and protocols that support interoperability among different scientific fields, (3) a co-design approach that includes requirements from high-energy physics, radio astronomy, gravitational-wave astrophysics, climate research, and environmental monitoring, and (4) strong methods for assessing AI model quality, provenance, and uncertainty measurement in federated settings.
The talk will focus on the DTE software components developed and integrated, detailing some of the pilot use cases that have successfully driven the DTE implementation.

Have you ever wondered how much energy your research on Snellius uses? Or maybe how performant or efficient your application is on Snellius? We at SURF did as well. This is why we have developed an end-user friendly, interactive, dashboard that allows you to display the energy usage of your jobs on Snellius and gives you insight into how well your application is using Snellius. This dashboard gives researchers the tools and visualizations for energy aware computing.

Snellius and other HPC systems are not magic, even if it sometimes may feel so.
Efficient usage of the available hardware is the difference between a model that may be just 'OK', or a model that is State-of-the-art (and I have examples in my pocket to prove it!).
Trusting that whatever you throw at the system will be efficient 'automagically' is the quickest way to burn GPU hours without getting what you really want: breakthrough science!

In this presentation, we discuss the PartitionedArrays programming model as an alternative to the message passing interface (MPI). We present the key features of this model and illustrate how it can help users of Snellius and other supercomputers to reduce the burden of implementing complex distributed-memory parallel applications. We illustrate the capabilities of this model with the implementation of key kernels in scientific computing such as the distributed sparse matrix-vector product (SpMV), the distributed sparse matrix-matrix product (SpMM), as well as the high-performance conjugate gradient (HPCG) benchmark used in the top 500 supercomputer list. We also compare the performance of the resulting codes against state-of-the art implementations, showing that the proposed model improves user experience without compromising performance, or even improving it.

We live in a golden age of satellite remote sensing. The European Space Agency's Sentinel program in particular, which focuses on spaceborne Earth observation (EO), has set the standard for continuous, free and readily available satellite observations and products. The archive of EO data is vast, and continues to grow by many petabytes a year. From a scientific perspective, these vast quantities enable ever more research to be conducted, especially in the age of data-hungry artifical intelligence. Yet, without special infrastructure, the sheer magnitude of satellite data causes it to become unwieldly. Cloud-hosted services tailored to satellite data exist (noteably Google Earth Engine), but these tend to have their own shortcomings, such as limited availability of low-level (raw) satellite observations.

In our research group we study the ocean surface with spaceborne radars. Radars are uniquely capable for ocean monitoring: when mounted on a satellite they provide large coverage while being mostely unaffected by atmospheric interference (e.g. they can look through clouds), and the signals reflecting from the ocean surface provide all sorts of geophysical insights that are used in meteorology, storm tracking, swell predictions, and much more. But when looking at high resolution radar imagery of the ocean, one can identify a wealth of atmospheric information that is commonly ignored. Thus, we set about developing a methodology for extracting this information, focusing on the heat-flux exchange between the ocean and atmosphere---a critical climate variable for which no satellite products are available---from Sentinel-1's entire 10+ year data catalogue.

In this presentation we will outline the development of our methodology, which we call FluxSAR, and share preliminary scientific results. The presentation focuses on the challenges involved in working with the petabytes of high-resolution radar data, and how SURF's Spider HPC has enabled us to tackle these challenges head on.

Importance of Simulation of Surface Water Systems
Forecasting of flooding, morphology and water quality in coastal and estuarine areas, rivers, and lakes is of great importance for society. To tackle this, the Delft3D Flexible Mesh Suite (Delft3D FM) has been developed by Deltares. Delft3D FM is used worldwide and consists of modules for modelling hydrodynamics, waves, morphology, water quality, and ecology.

Transformer-based LLMs, at scale, are prohibitively expensive to train, requiring massive GPU capacity. Alternative technologies do exist, producing functionally equivalent LLMs at a fraction of the training costs, using high-memory CPU nodes. I will illustrate this with a memory-based LLM trained on Snellius' hi-mem nodes.

Right after lunch, Rob and Emiel invite you to engage your mind in an unexpected way.

We are increasingly engaged in transdisciplinary research to address the complex challenges our world faces today, such as transitioning to renewable energy systems, advancing personalised medicine, leveraging digital twins, and accurately predicting climate change. Advanced research e-infrastructure has become essential for tackling these questions in an integrated manner. To achieve these ambitions, we are converging on using multiple technologies, methodologies, computing and data infrastructures, and software stacks to create sustainable, long-term value. In this respect, applications and workflows are crucial for addressing scientific challenges, achieving outcomes, and advancing the boundaries of research.

This session aims to explore the feasibility of a community-driven approach to foster energy-efficient scientific computing in the Netherlands. By engaging researchers, support staff, and infrastructure providers, such an initiative can establish a self-sustaining Community of Practice, create an open knowledge base with practical training on energy monitoring and reduction in scientific computing, and organize nationwide training sessions to build foundational expertise. Together, these actions can complement infrastructure-level efficiency improvements with user-level practices, advancing sustainable and environmentally responsible research. A soon-to-be-launched initiative supported by TDCC-NES seeks to do this in the Natural and Engineering Sciences (NES) domain. During the session, participants will have the opportunity to learn more about the initiative, share feedback, and discuss ways to expand its impact to other scientific domains in the Netherlands.

SURF will start next year to investigate a Data Lakehouse, among others to explore its application in scientific workflows.

ROMEO HPC Center of University of Reims, under the lead of Teratec, is partner of the French National Competence Center.

In this talk, we address the challenges of quantitative MRI (qMRI) reconstruction and introduce COMPAS, a flexible and GPU-accelerated toolkit designed for use in qMRI research. Our evaluation shows that COMPAS significantly reduces reconstruction times, from hours to minutes, using the GPU infracture provided by SURF, including Snellius and LUMI supercomputers.

Large Language Models are becoming core research tools, yet dependence on commercial APIs raises issues of privacy, compliance, and long-term cost. At TU Delft, REIT and ICT are prototyping TULIP, a Kubernetes-based platform for locally hosted open LLMs. We’ll share design choices that prioritize responsible innovation: containerized serving with an OpenAI-compatible API, cluster-native scaling, and transparent monitoring.

While national initiatives like SURF’s WiLLMa focus on shared capacity, TULIP explores the campus-level space: providing researchers with reproducible endpoints, model governance, and early feasibility metrics for institutional hosting. We will share early lessons, governance implications, and practical guidance for universities and labs aiming to offer sustainable, open alternatives to proprietary AI services.

While open-source search models have greatly improved with transformer-based architectures, they face challenges outside their training domain, such as when applied to multi-modal or non-English text data. In this talk, we will describe some of our ongoing work developing new open-source models to address these challenges:

• Multilingual retrieval. We train an effective multilingual sparse retrieval model achieving state-of-the-art performance on standard multilingual benchmarks while continuing to perform well in English.
• Multimodal retrieval. We improve multimodal retrieval for the visual document retrieval task with an approach leveraging existing vision-language models.
• Complex retrieval. We develop query expansion for complex information needs that cannot be handled well with standard methods.
• Synthetic data generation. We explore synthetic data generation for enabling training and evaluation on broader scenarios like retrieval-augmented generation (RAG).
• Efficient retrieval models. Given the increased computational costs of using LLMs for retrieval, we explore several strategies for improving their efficiency, including an effective pruning approach that results in smaller models with comparable performance and engineering work.

Gravitational wave astronomy has advanced from theoretical prediction to observational reality, with over 200 black hole and neutron star mergers detected in the past decade. The Einstein Telescope, a proposed next-generation detector with a candidate site at the border of the Netherlands, Germany, and Belgium, is expected to detect hundreds of thousands of events per year. However, analyzing this unprecedented volume of observations poses a fundamental challenge, as existing software cannot scale to extract science from such a rich dataset. We present ongoing development of a GPU-native framework written in JAX that accelerates the analysis of gravitational wave data from hours to mere minutes. Crucially, our approach avoids using machine learning surrogates, preserving high fidelity in the results while achieving this speedup. By developing and testing our framework on the Snellius GPU cluster, we underscore the Netherlands' active role in both the instrumentation and the data analysis for the Einstein Telescope.

This presentation introduces the public draft of SPECTRUM's Technical Blueprint and Strategic Research, Innovation and Deployment Agenda (SRIDA) for European data-intensive science infrastructure. The Technical Blueprint addresses the technical aspects whilst the SRIDA defines the strategic and policy dimensions of a unified European compute and data continuum. Both are based on comprehensive requirements analysis from High-Energy Physics and Radio Astronomy communities, including HL-LHC's exabyte-scale data processing, SKA's unprecedented computational demands, and LOFAR's distributed data processing challenges. We invite the advanced computing community to provide feedback during the open consultation phase to ensure the final documents address the research infrastructure needs.

An overview of the data visualization options that are available from SURF, including usage of Snellius and other infrastructure, plus available support from SURF for visualization projects.

Get up to speed with the latest developments in advanced computing, services, and technology within SURF. This session offers a concise overview of what’s new, what’s changing, and how these innovations will support the community in the year ahead.

This final moment isn’t just a closing. It’s a celebration, a lasting spark to carry with you beyond today. And when their act finishes, Valeriu will step back into the spotlight to guide us through the day’s final reflections and officially bring the Advanced Computing User Day to a close.