ID: 2.2/08.B
Machine learning models are typically trained over a specific domain, with a particular climatology, a particular geography, a particular set of conditions. That’s a strength when you’re working in that domain, but it becomes a limitation the moment you want to apply the model somewhere else. This is exactly the problem that transfer learning and upscaling address. This webinar introduces you to upscaling and transfer learning, two strategies that let water resources machine learning models trained in one place make reliable predictions somewhere else entirely.
Learning Objectives
- What upscaling and transfer learning (TL) mean in the context of machine learning models
- What you need to apply upscaling or transfer learning to your own data
- How these approaches work in practice: illustrated through two real case studies
Target Audience
- Decisions makers, modelers, scientists
Keywords
Machine Learning models, water management, Transfer Learning (TL), upscaling
Related Resources
[Category: 2.2 / Level: 2]
Presenter:
Dr. Leandro Avila, Forschungszentrum Jülich (FZJ)
For further questions please contact us via this form https://stars4water.eu/contact/