Enhancing Regional Climate Projections with Deep Learning
29.01.2025Global climate models play a vital role in predicting future climate conditions, such as temperature or precipitation. However, their coarse spatial resolution (typically 50–100 km) limits their ability to capture regional climate phenomena.
To bridge this gap, higher-resolution regional climate data can be generated using either statistical methods or computationally intensive numerical models.
Recently, downscaling techniques using Deep Learning have shown great results compared to traditional numerical methods in both accuracy and efficiency.
The aim of this project is to evaluate/improve the performance of deep learning models in downscaling present and future climate conditions.
Supervisor: Simon Hentschel
Requirements
Experience programming with Python and PyTorch/Tensorflow
(Beneficial) Interest in data-driven climate science
