MARATTO

article · Zenodo (CERN European Organization for Nuclear Research)

#RSAfrica26 On Building a Sustainable Research Software and HPC Training Pipeline in West Africa

Abstract

This presentation was delivered at Research Software Africa 2026 (RSAfrica26) and describes the development and evaluation of a pilot training pathway created by the Center for Computational Research and Education (CCRE) to expand participation in high-performance computing (HPC), research software engineering, and computational research in Africa. The pilot used a staged model comprising open recruitment, application review, structured preparatory training, mentored group projects using HPC resources, and post-program evaluation. Twenty-four applicants were documented, twelve were selected for the preparatory stage, and six completed all required modules and advanced to mentored computational projects. Participants worked on end-to-end research workflows including thermal-hydraulic surrogate modeling and machine-learning-based brain-tumor MRI classification. The pilot identified persistent barriers involving access to HPC resources, computing cost, local mentorship, structured training pathways, and research-computing communities. The presentation argues that sustainable computational capacity requires more than access to hardware and proposes a framework centered on four interconnected elements: access, preparation, mentored practice, and sustainability. The presentation is based on the preprint: Afful, J. et al. (2026), Introducing HPC-Enabled Computational Research Training in Africa: A Pilot Study. Research Square. https://doi.org/10.21203/rs.3.rs-10437458/v1 Presented at Research Software Africa 2026 (RSAfrica26), 27 August 2026. Research Square preprint10.21203/rs.3.rs-10437458/v1 RSAfrica26 conference presentation10.5281/zenodo.22183129

Research topics

  • Scientific Computing and Data Management
  • Genetics, Bioinformatics, and Biomedical Research
  • ICT in Developing Communities

Read the original research

This page summarises published work. The authoritative version sits with the publisher.

DOI: 10.5281/zenodo.22183128

Is something wrong with this record? Report it or request removal.

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.