This video belongs to the openHPI course clean-IT: Towards Sustainable Digital Technologies. Do you want to see more?
An error occurred while loading the video player, or it takes a long time to initialize. You can try clearing your browser cache. Please try again later and contact the helpdesk if the problem persists.
To enable the transcript, please select a language in the video player settings menu.
About this video
Read a blog-post version of this openXchange live talk here on Medium!
To understand the complex processes of climate change effects and our nature in general, we need models, that approximate and explain these processes. However, these models can often become very complex and computationally intensive as well. Therefore, earth system scientists and physicians start using AI applications, for example to emulate complex processes. Also Deep Reinforcement Learning techniques can be used, to train agents and improve existing climate models. In this talk, Dr. Jonathan Donges presents the opportunities and challenges of using AI for earth system science.
Dr. Jonathan Donges is Co-Leader of the FutureLab on Earth Resilience in the Anthropocene and also Working Group Leader on Whole Earth System Analysis at the Potsdam Institute for Climate Impact Research (PIK). His research work focuses on dynamics of planetary-scale socio-ecological systems, climatic and social tipping elements, and their dynamics and interactions. He studied physics mostly in Potsdam but also in Bonn for 2 years and holds a PhD in theoretical physics. Since 2013, he has been working as a researcher on various projects, mostly at the Potsdam Institute for Climate Impact Research.