Artificial Intelligence (AI) and Machine Learning (ML) methods are becoming increasingly important in both science and society. In climate science - where complex biophysical and societal processes interact across diverse temporal and spatial scales, and datasets are often large, heterogenous and incomplete - AI and ML methods offer new powerful solutions.
Seminar Series
The monthly AI seminar at IIASA features global experts in the field of AI and ML who will showcase the newest methodological advancements and applications in the field. Through a series of invited talks, the seminar showcases cutting edge research with the aim of strengthening AI and ML expertise at IIASA and to foster external collaborations. Additionally, it serves as an institute-wide platform for discussions and knowledge exchange across programs and working groups to spark new ideas and innovations.
As an initiative from the ECE/ ICI Theme on Extreme Weather and Climate Dynamics, this seminar is designed for both experts already integrating AI and ML into their workflows and those eager to expand their knowledge in these fields.
Upcoming Seminars
How much climate data do we need? Machine learning approaches for evaluating high-resolution climate models
Date: 03.06.2025, 14:00 - 15:30 CET
For our June session, we are excited to announce two speakers from the University of Vienna. Aiko Voigt and Maximilian Meindl will explore machine learning approaches for evaluating high-resolution climate models.
Past Seminars
AI applications for Climate Science
Date: 03.04.2025, 14:00 - 15:00 CET
In the first seminar, Yi-Ling Hwong and Sandeep Chowdhary presented insights into AI applications for Climate Science and share their professional experiences in the field.
Kai Kornhuber introduce the seminar and moderate the session.
Why We Still Need Traditional Climate and Earth System Models – and How They Might Be Improved
Date: 07.05.2025, 14:00 - 15:30 CET
The second talk in the IIASA-wide AI Seminar Series featured Professor Steven Sherwood from the University of New South Wales, Sydney. Focusing on the problem of atmospheric convection, Professor Sherwood did outline some novel strategies and a broader range of numerical simulation strategies, that might show how our standard climate models can be fixed.
Machine Learnt Climate Emulators Enabling Multi-Sector Risk Assessments for a Multitude of Emissions Pathways
Date: 22.05.2025, 11:00 - 12:30 CET
In the third talk in the series, Dr. Vassili Kitsios from CSIRO (Commonwealth Scientific and Industrial Research Organisation), Australia, talked about how machine learning-based climate emulators can rapidly generate detailed climate projections for a wide range of emissions scenarios, helping to better assess future climate risks and human impacts.
Neural Network Solvers for High-Dimensional PDEs: The Deep Galerkin Method
Date: 09.07.2025, 14:00 - 15:30 CET
In July, Ibrahim Tahri (EF) join the AI for Climate Science Seminar Series to provide a detailed introduction into the Deep Galerkin Method and demonstrated how he uses this novel framework for solving high-dimensional partial differential equations in mathematical finance.
AI-empowered Next-generation Multiscale Climate Modeling for Mitigation and Adaptation
Date: 06.08.2025, 14:00 - 15:30 CET
We heard from Veronika Eyring about the necessity of an AI-empowered multiscale approach for hybrid Earth System Models. The talk presented progress in hybrid modelling work with the ICOsahedral Non-hydrostatic (ICON) atmospheric model as well as key challenges and visions how to enhance climate modeling with machine learning.
Adverse (and extreme) Weather and the renewable energy system
Date: 03.09.2025, 14:00 - 15:30 CET
In the September edition of the seminar series, we have heard from Dr. Irene Schicker (GeoSphere Austria). Dr. Irene Schicker is a meteorologist with a focus on renewable energies and machine learning. She is managing GeoSphere's national projects (extreme events, renewable energies, AI), and the “Renewable Energy ” group in the project “Destination Earth Digital Twin Extremes ”.
From Data to Dialogue – How FableGPT Makes Science Accessible
Date: 18.09.2025, 14:00 - 15:30 CET
For a especially interactive session we welcomed Marcial Sandoval-Gastelum from IIASA's EM group to introduce us to the FableGPT, a web-based AI assistant designed to help users navigate and understand the FABLE Calculator—an IAM tool developed at IIASA for modeling sustainable food and land-use pathways. Please, note that at the moment we can only offer participation for IIASA staff.
AI for (sub)seasonal forecasting - boosting predictability and understanding teleconnections
Date: 14.10.2025, 14:00 - 15:30 CET
In October we were hosting guest seminar by Prof. Dr. Dim Coumou, Professor of Climate Extremes & Societal Risk at VU Amsterdam. Dim Coumou co-founded Beyond Weather in 2023 to bring advanced AI-based seasonal forecasts to end-users in the energy and agricultural sector. Currently, he leads the XAIDA project that unites 16 European research institutes with climate risk practitioners to better assess and predict the influence of climate change on extreme weather using novel artificial intelligence methods.
AI in climate science and impact analysis – What's trending?
Date: 03.11.2025, 14:00 - 15:30 CET
The November edition was an IIASA-internal talk, providing an overview of the latest AI approaches used in climate modelling and analysis, and their connection with the work at IIASA. We were given an exciting insight of the work of recently joint IIASA colleague, Verena Kain.
From AI Ethics to Citizen Literacy: Challenges and Directions
Date: 01.12.2025, 15:00 - 16:30 CET
In December, our seminar was joined by Eugenia Stamboliev from the University of Vienna. In her talk she gave a brief overview on ethical concerns and topics regarding AI design and narratives (like responsibility, autonomy and discrimination)
Joint Seminar with the SYRR Risk & Resilience Hub: Can ChatGPT do my climate job?
Date: 10.12.2025, 11:00 - 12:00 CET
We are excited to jointly host the last 2025 edition of the AI for Climate Science Seminar series together with IIASA's SYRR Risk & Resilience Hub. In this joint seminar, Rob Wilby (Loughborough University) will talk to us about the use of LLM's like ChatGPT in climate risk assessments.
Detection of Regional Climate Change Patterns Using Explainable Machine Learning
Date: 04.03.2025, 14:00 - 15:30 CET
We kicked of the second season of the AI seminar with an exciting talk by our IIASA colleague, Assaf Shumel, on the use of explainable machine learning for detection of regional climate change patterns.
Towards AI-Assisted Climate Scenario Assessment
Date: 20.05.2025, 14:00 - 15:30 CET
In May, we hosted an exciting seminar by Jade Eva Guisiano.In here talk she explored how the assessment of climate scenarios can be leveraged with the support of LLMs.
© IIASA
Help Shape the Future of AI at IIASA!
We invite you to take part in the anonymous "AI at IIASA" Survey.
Your input will help us:
🔹 Build a database to support institute-wide exchange on AI tools and applications
🔹 Collect ideas for inspiring topics and speakers for the “AI in Climate Science” seminar series
Join us in shaping a vibrant, AI-engaged community at IIASA!
Contact
Events
Online and in Raiffa room at IIASA (Laxenburg, Austria)
AI for Climate Science seminar series: How much climate data do we need? Machine learning approaches for evaluating high-resolution climate models
Online and in Raiffa room at IIASA (Laxenburg, Austria)