ACINN Graduate Seminar - SS 2026

2026-03-25 at 12:00 (on-line and on-site) in the seminar room

How much climate data do we need? Machine learning approaches for
evaluating high-resolution climate models

Maximilian Meindl

University of Vienna, Austria

 

The emergence of kilometer-scale climate models represents a major step forward in the simulation of atmospheric processes, allowing many phenomena to be represented explicitly rather than through parameterization. However, these simulations also produce enormous data volumes and are often limited to relatively short time periods due to their high computational cost. As a result, traditional climate model evaluation methods based on long climatological averages become increasingly difficult to apply and may provide limited insight when only short segments of high-frequency output are available.

In this talk, I present recent work from the HighResLearn project that addresses these challenges from several perspectives. First, I briefly introduce a scalable framework for accessing and processing large climate datasets, enabling efficient analysis workflows for high-resolution simulations.

Second, I focus on a machine learning (ML) based approach for evaluating climate models on regional scales using short periods of daily temperature data. A convolutional neural network (CNN) is trained to distinguish spatial temperature fields from simulations of the EURO-CORDEX ensemble and global kilometer-scale models. Applying the trained CNN to observation-based datasets provides an alternative evaluation metric based on the similarity between model-generated and observed spatial patterns, while explainable AI methods help identify the spatial features that drive the classification.

Finally, I show ongoing work exploring whether the climatological bias structure of climate models can be inferred directly from short samples of daily temperature fields using ML based spatial feature extraction.

 

The content of this webpage is the author’s opinion and the author’s intellectual property. ACINN has the author’s consent to make this information available on the webpage for the announcement of the seminar presentation and in the seminar archive.