News

FONDA Winter 2025/2026 Lecture Series Begins Oct. 28

On selected Tuesday afternoons from October 28th 2025 to mid-February 2026, FONDA will host 2-3 short scientific talks on a variety of topics related to large scale data analysis and workflows in natural science. The complete schedule (subject to change) can be found here: FONDA Winter Lecture Series.

On October 28th, we will meet in the Humboldt-Kabinett (first floor seminar room of Rudower Chaussee 25, 12489 Berlin-Adlershof) at 15:15 for the following two talks:

  • Nikos Tsakiridis – University of Thessaloniki: From Petabytes to Pedons: Cloud-Native Earth Analytics for Soil Mapping
  • Matthes Rieke – 52 Degrees North: Biodiversity monitoring with openEO – a look at scalability and reproducibility

You can also follow our lecture series online.

We are looking forward to seeing you there!

Presentation By Mercator Fellow Caroline Jay

Title: Socio-Technical Resilience in Research Software Engineering

Date: 21.10.2025

Time:11:30-12:30

Location: Humboldt-Kabinett, Rudower Chaussee 25, 12489 Berlin

Abstract:

Software quality is influenced by a multitude of factors, from technical, to organisational, to cultural. This talk uses a ‘resilience engineering’ lens to study this issue. This entails examining what helps research software engineering (RSE) teams – and the codebases they create – to respond well and adapt to changes and threats, which are viewed as inevitable. It will explore the role of the professional identity in supporting resilience within the individual, and examine how resilience may be affected by the professional culture in which someone works.

Bio:

Caroline Jay is a Professor of Computer Science and Head of Engineering Research at the University of Manchester, where she leads the institution’s AI for Research and Digital Infrastructure Strategies. She is qualified as both a Psychologist (BA, CPsychol) and Computer Scientist (MSc, PhD), and undertakes research exploring the relationship between humans and technology. She is Research Director of the Software Sustainability Institute and holds a Mercator Fellowship at Humboldt University of Berlin.

FONDA Fall 2025 Retreat

FONDA’s members met from October 7th to 9th in Potsdam for our Fall Retreat. In addition to subproject progress reports, each PhD student presented a poster regarding their thesis topic, and we had two marvelous keynote talks by Carole Goble and Sarah Cohen-Boulakia!

PhD Retreat at Coconat


From September 10-12, FONDA’s doctoral researchers met at Coconat space for a self-organized retreat. The group shared tools they use to keep their research organized and worked on abstracts for potential collaborations between subprojects, ideas for potential master’s thesis topics, and other ideas for FONDA

Introducing TCO2: Total CO2 Cost of Ownership

TCO2: Total CO2 Cost of Ownership is a tool for analyzing the carbon footprint of database server replacements. It was developed by the Data Engineering Systems group at the Hasso Platner Institute, including Tilmann Rabl (PI) and Ilin Tolovski (doctoral researcher) from FONDA subproject B6.  Ilin, Tilmann and Marcel Weisgut presented TCO2 at the 51st Conference on Very Large Databases (VLDB) on September 3rd. The tool provides a break-even analysis of server replacement, taking into consideration, among other factors, the embodied carbon of new hardware, the carbon intensity of a nation’s power supply, and the type of workload being run. Explore these relationships for yourself here!

Abstract: 

Data centers produce a significant and increasing amount of CO2 emissions. In the past, these have been predominantly due to energy generation for powering data centers. With the transition to energy sources with lower carbon production, the embodied carbon (i.e., CO2 and other greenhouse gas emissions during production, transport, and end-of-life) plays an increasing role when planning server lifecycles. While replacing an old server with newer hardware will typically reduce the power consumption of individual tasks, due to better efficiency of modern CPUs, offsetting the embodied carbon of new hardware can take months to tens of years, depending on the grid carbon intensity.

Read more here!

Snakemake Tutorial with Johannes Köster

FONDA has invited Professor Johannes Köster to give a tutorial on Snakemake, a widely used, python based workflow management system. Snakemake allows users to create scalable, human readable, reproducible workflows for scientific data analysis.

Professor Köster the leader of the Bioinformatics and Computational Oncology group at the Institute for AI in Medicine at the University of Duisburg-Essen, where his work focuses on reproducibility and bioinformatics workflows. He is the author and lead developer of Snakemake.

The full-day tutorial will be on July 02, 2025 starting at 9 am. Please contact Tobias Price if you are interested in attending.

NUMA, Portability, and AI: Three Bites of HPC

Guest Lecture by Ruben Laso

Date, time, and location:
Tuesday, July 1st, 11:15 am in the Humboldt-Kabinett (aka HUK, Rudower Chaussee 25, 1st floor)

Abstract:
In this presentation, we will cover three past and ongoing projects related to High-Performance Computing (HPC).

The first part will focus on NUMA (Non-Uniform Memory Access) systems, showing how process and memory placement can be improved to reduce execution times.

The second part will discuss the feasibility of using standard C++ for performance-portable HPC applications, showing how C++ can be used to write code that runs efficiently on different hardware architectures without sacrificing performance.

Finally, we will explore the optimisation of GPU-GPU communication to improve the performance of AI applications. As modern workloads often involve significant data movement, there is an opportunity to tune communication libraries for better performance.

Bio:
Ruben Laso is currently a postdoctoral researcher at the Research Group for Scientific Computing at the University of Vienna. He holds a PhD in High-Performance Computing (2023), a Master’s in Industrial Mathematics (2019), and a Bachelor’s in Computer Science (2017), all from the Universidade de Santiago de Compostela. His research interests include parallel computing, with a particular focus on manycore and NUMA systems, as well as performance portability in scientific codes.

Ruben will be visiting FONDA until mid-July.

Tutorial on Human-Computer Interaction with Thomas Weber

On June 12th from 10:00 -13:00 we will have a Tutorial on Human-Computer Interaction with Thomas Weber from LMU Munich. The event will be in the Humboldt-Kabinett. Everyone is invited to attend!

The abstract and bio Dr. Weber provided for the event can be found below.

Abstract:

Artificial Intelligence, especially Large Language Models, have proven
highly successful in many domains, including software development. New AI-powered tools not only increase the productivity of professional and novice software developers alike, they also enable completely new, highly flexible ways to interact with software. In this workshop, we will have a hands-on exploration of these capabilities and how they can enable and enhance rich and flexible interaction. However, integrating AI into interactive systems is not without challenges. Thus, we will also discuss how to design and evaluate AI-powered interactive systems to make sure they are both usable and useful.

Bio:

Thomas Weber is a post-doctoral research at LMU Munich. In his research, he investigates how AI-powered systems affect the lives and behavior of software developers from two perspectives: first, considering the rapid pace at which new and improved AI-powered tools emerge, how can developers use these tools productively to create high-quality software? However, software developers not only use AI but are also the ones building and shaping it. Thus secondly, how do requirements differ for building AI systems compared to traditional systems and how does this affect the behavior of developers.

To answer these questions, he combines methods from both software engineering research and human-computer interaction.

FONDA PhD Defense: Jonathan Bader on “Task Resource Prediction for Efficient Execution of Scientific Workflows”

Jonathan Bader defended his doctoral dissertation “Task Resource Prediction for Efficient Execution of Scientific Workflows” with distinction on June 4th, 2025. He is a member of the group “Distributed and Operating Systems” at TU Berlin, where he worked on FONDA subproject B1. His work focuses on predicting which tasks in a workflow are most resource intensive in order to dynamically adjust resource allocation and scheduling.

As part of this research, he introduced Lotaru and Sizey, two novel methods for predicting task run-time and memory requirements, respectively. Lotaru allows researchers to create a sensible baseline resource allocation profile for a workflow based on the task requirements and target infrastructure. Sizey continuously predicts the amount of memory each task requires and adjusts the memory allocation during runtime to minimize over-allocation while also preventing failures. Both outperform previous methods and improve the efficiency of workflow execution.

Congratulations Jonathan!

Data Aware Scheduling Method Now Available for Nextflow

With the latest release of the nf-cws Nextflow-Plugin, Fabian Lehmann and Friedrich Tschirpke introduce the WOW scheduling method as a production-ready feature. This release marks the transition of the WOW approach from a research prototype to a usable software component, fully integrated with the official Nextflow versions (v24.04.0 up to v25.02.3-edge).

Key Features:

  • WOW Scheduling for Nextflow: The Workflow-Aware data movement and task scheduling (WOW) method is now available as part of nf-cws. This enables dynamic coordination of data transfers and task execution, reducing network congestion and workflow runtime.
  • Seamless Integration: The nf-cws plugin can be used directly with Nextflow’s Kubernetes executor, requiring no experimental patches or custom setups.
  • Production Use: The improvements demonstrated in the original publication can now be leveraged by all Nextflow users in real-world scenarios.

-Fabian Lehmann