Earth System Data Exploration
Earth System Data Exploration
About
The ESDE group explores the use of state-of-the-art deep learning methods for analysing and forecasting atmospheric data with a focus on air quality and weather and a dedication to open data and open science.
Our ability to analyse air quality, weather and climate data is fundamentally important to save lives, for example during extreme weather events, to protect nature and biodiversity and to create and preserve economic value through science-based decision making on mitigation and protection measures. Modern machine learning can play an important role to complement or even substitute traditional simulation models and to extract more information from the huge amount of environmental monitoring data that has become available in recent years. We see the handling, processing and distribution of such data with modern high-performance computing technology abiding to open, federated and FAIR principles as a necessary requirement for building sustainable tools for the analysis of the environment, but also as an interesting research topic in itself.
Research Topics
- Develop machine learning tools and methods for the interpolation, forecasting and quality control of global air pollution data including uncertainty analysis and explainable artificial intelligence (XAI),
- Investigate the use of high-end deep learning methods for weather froecasting and downscaling of weather model output,
- Build and maintain a world-leading data infrastructure for global air quality observations with web-based analysis and visualisation capabilities,
- Develop FAIR and scalable workflow solutions for extreme data management and dissemination in collaboration with leading weather and climate centres.