Jesper Dramsch implements state-of-the-art machine learning solutions for numerical weather prediction.
They are currently contributing to the core development of AIFS, the fully data-driven NWP model at ECMWF.
• Validation of machine learning models in real-world contexts
• Machine learning in science and reproducibility
• Machine learning for science
• Research software engineering & sustainable software
• Outreach, education & communication of research
• Testing implicit assumptions of modeling choices
Jesper Dramsch works at the intersection of machine learning and physical, real-world data. Currently, they're working as a scientist for machine learning in numerical weather prediction at the coordinated organisation ECMWF.
Before, Jesper has worked on applied exploratory machine learning problems, e.g. satellites and Lidar imaging on trains, and defended a PhD in machine learning for geoscience. During the PhD, Jesper wrote multiple publications and often presented at workshops and conferences, eventually holding keynote presentations on the future of machine learning.
Moreover, they worked as consultant machine learning and Python educator in international companies and the UK government. Their courses on Skillshare have been watched over 25 days by over 2000 students. Additionally, they create educational notebooks on Kaggle, reaching rank 81 worldwide.
Fields of expertise: Reproducibility for Machine Learning in the Sciences, Physics, Programming, Gaming, Board games, Climbing, Content Creation