Where machine learning meets research data management.
Building and testing models for classification, prediction, and pattern recognition, from simple features to deep and generative methods. I focus on what really works on real, messy scientific data.
Building pipelines and tools that make research data easy to reproduce and reuse, guided by the FAIR principles (Findable, Accessible, Interoperable, Reusable) and FAIR4RS for research software.
Making AI systems clear enough that people can trust them and ask questions. This matters most in sensitive fields like healthcare and public health.
Using machine learning for disease monitoring and prevention, such as classifying genomes and spotting new viral variants early, so public health teams can react in time.