CS MSc Thesis Presentation 15 October 2025

Wednesday, 15 October there will be a master thesis presentation in Computer Science at Lund University, Faculty of Engineering.

The presentation will take place in E:2405 (Glasburen).

Note to potential opponents: Register as an opponent to the presentation of your choice by sending an email to the examiner for that presentation (firstname [dot] lastname [at] cs [dot] lth [dot] se). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions for opponents are found here on the LTH thesis project page.

10:00-11:00 in E:2405 (Glasburen)

• Presenter: Christopher Källström
• Title: Data Quality and Quanity for Machine Learning at the European Spallation Source
• Examiner: Per Runeson
• Supervisor: Fredrik Edman (LTH), Karin Rathsman (ESS), Timo Korhonen (ESS)

This thesis investigates data governance challenges and solution strategies for preparing the European Spallation Source (ESS) control-system data infrastructure for machine learning (ML)-driven analytics. ESS generates millions of process variables daily, yet current practices emphasize engineering-driven collection over analytical readiness. Through a literature review and stakeholder interviews, three research questions are addressed (i) identifying key challenges in data quality, metadata, and retrieval (ii) proposing governance, architectural, and tooling strategies (iii) evaluating their applicability in ESS test environments. Findings reveal ambiguous ownership, metadata incompleteness, oversampling, and retrieval inefficiencies as core barriers to ML readiness. Solution candidates include clarified governance roles, standardized metadata and configuration policies, adaptive archiving, and improved technical configurations. The evaluation highlights both organizational and technical pathways to transition ESS from ad hoc data accumulation toward a curated, machine-learning-ready data ecosystem. This contributes practical recommendations for ESS and advances research on data governance in large-scale scientific infrastructures.