This Tuesday 21st May at 4 pm (BST) the DataLearning group are hosting Julia Kaltenborn and Charlotte Lange from McGill University and Mila. They will be presenting their recently published NeurIPS work ‘ClimateSet’ (https://climateset.github.io).
Join online: https://zoom.us/j/95291664305?pwd=b0lXeXNxbnllcjdCK2ZBaUs2WENyQT09
Abstract
Climate models have been key for assessing the impact of climate change and simulating future climate scenarios. The machine learning (ML) community has taken an increased interest in supporting climate scientists’ efforts on various tasks such as climate model emulation, downscaling, and prediction tasks. Many of those tasks have been addressed on datasets created with single climate models. However, both the climate science and ML communities have suggested that to address those tasks at scale, we need large, consistent, and ML-ready climate model datasets. Here, we introduce ClimateSet, a dataset containing the inputs and outputs of 36 climate models from the Input4MIPs and CMIP6 archives. In addition, we provide a modular dataset pipeline for retrieving and preprocessing additional climate models and scenarios. We showcase the potential of our dataset by using it as a benchmark for ML-based climate model emulation. We gain new insights about the performance and generalization capabilities of the different ML models by analyzing their performance across different climate models. Furthermore, the dataset can be used to train an ML emulator on several climate models instead of just one. Such a “super emulator” can quickly project new climate change scenarios, complementing existing scenarios already provided to policymakers. We believe ClimateSet will create the basis needed for the ML community to tackle climate-related tasks at scale.
About the speakers
Julia Kaltenborn is a PhD student at McGill University and the Mila-Quebec AI Institute. Her research is two-fold: She explores machine learning for climate model emulation, and cryospheric sciences. She focuses on creating ML resources that can be used cross-disciplinary, such as ClimateSet, and developing ML models that are actively used in the field, e.g., by MOSAiC, the largest polar expedition in history. Julia co-founded the NGO Unser Dialog, co-organized AI Helps Ukraine, and was a local Greenpeace leader in her youth. She has been a fellow of the German Academic Scholarship Foundation, received the Mitacs Globalink Research Fellowship, and was a DeepMind scholar. Last but not least, Julia was a member of the Juneau Icefield Research Expedition 2023 and has traversed the Juneau Icefield.