Green AI Seminar
This seminar explores the potential of AI in combating global climate change by discussing its role in monitoring climate crises, conserving nature, and reducing greenhouse gas emissions in various sectors. The seminar will also consider the sustainability of AI itself, as advances in machine learning come with a significant increase in carbon emissions. Participants will learn about essential aspects of improving the sustainability of machine learning algorithms and gain a different perspective on machine learning’s role in addressing climate change.
The seminar provides:
- Introduction to “Green AI” versus “Red AI”
- Guests talks on related research topics
- Group discussions on future prospects of AI, specifically machine learning
- Best practices for literature review and scientific presentations
- Literature review on Green AI in certain areas in groups
- Scientific talk of each student on one specific topic
Contact: Dr.-Ing. Eva Dorschky and René Raab
Time and place: Wednesday 10:15 – 11:45, MaD seminar room (ground floor, Carl-Thiersch-Str. 2b, 91052 Erlangen)
Optimization-in-the-loop ML for energy and climate
This talk will present the framework of “optimization-in-the-loop ML,” which addresses the limitations that machine learning (ML) often faces in contending with the physics, hard constraints, and complex decision-making processes involved in climate and energy problems.
Guest speaker: Priya Donti (Climate Change AI)
Zoom information: Zoom link, Meeting ID: 643 5900 5780, Passcode: 811140
Where, When and how much? – How to reduce nitrogen consumption and optimizing crop yield using AI methods
This talk will focus on the economic problem farmers face today and how AI models can be used to optimize fertilizer use and reduce environmental impact. Insights into ongoing projects with farms in Germany and the potential impact on the future of sustainable agriculture will be discussed.
Guest Speaker: Thomas Maier (Machine Learning and Data Analytics Lab, FAU)
Biodiversity and glacier monitoring
This talk will present research on the automatic monitoring of environmental changes. Biodiversity is monitored by detecting and recognizing birds in aerial videos. Glacier melting is observed by delineating glacier fronts in satellite imagery using deep learning models.
Guest Speaker: Nora Gourmelon (Pattern Recognition Lab, FAU)
Neuromorphic Computing: The state and potential of Spiking Neural Networks
This talk will present an introduction to biology-inspired Spiking Neural Networks (SNNs), their current state, and their potential as an energy-efficient alternative to conventional artificial neural networks (ANNs). In addition, the necessity, benefit, and challenges of developing neuromorphic hardware suitable for SNNs will be discussed.
Guest speaker: Ferdinand Pscheidl (Fraunhofer EMFT)
|Introduction and group work||19.04.2023|
|Literature review and scientific writing||26.04.2023|
|Invited talk by Priya Donti on power grid (from 2pm-3pm via zoom)||26.04.2023|
|Invited talk by Thomas Maier on smart agriculture||03.05.2023|
|Invited talk by Nora Gourmelon on remote sensing||10.05.2023|
|Sustainability of AI||24.05.2023|
|Invited Talk by Ferdinand Pscheidl on spiking neural networks||31.05.2023|