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.
Join us for the kick-off of the second season of the IIASA-wide seminar series, AI for Climate Science!
We are pleased to announce that this year's first talk features IIASA colleague, Assaf Shumel.
Assaf Shmuel is a postdoctoral researcher at IIASA within the Integrated Climate Impacts Research Group, hosted by Prof. Dr. Carl-Friedrich Schleussner. His work sits at the intersection of machine learning and climate science, drawing on a multidisciplinary background in computer science, geophysics, political science, and physics. He develops interpretable models to better understand and predict Earth system processes, combining large-scale observational data and climate simulations with machine learning to uncover patterns in complex climate systems and support decision-making. Assaf Shmuel is further affiliated with the Weizmann Institute of Science (Israel) and the Dartmouth College (USA).
For online participation, a registration is necessary.
Please klick here to register.
Title:
Detection of Regional Climate Change Patterns Using Explainable Machine Learning
Abstract:
Climate change is a global phenomenon, yet its fingerprints vary substantially across regions. This talk highlights a range of these regional patterns using observational records and climate simulations, analyzed with machine learning and complementary statistical methods.
The first part of the talk examines the magnitude of climate change across temporal and spatial scales, showing how long-term warming reshapes seasonal and diurnal temperature cycles in different regions. The second part explores how machine learning can be used to detect climate signals against regional climate variability, with explainability frameworks highlighting the regions where changes are most distinct. We demonstrate this approach by analyzing how quickly mitigation signals emerge. We find that significant temperature differences emerge within a decade, compared to the several decades reported in studies based on global mean temperature.
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 Events
NOVA School of Business and Economics (Carcavelos Campus, in Lisbon - Portugal)
Circular Economy Modelling Workshop
Chulalongkorn University, Thailand