09.11.2022
On November, 16, 2022 Dr. Christopher Kadow will present during the scientific poster display his work on „Artificial Intelligence Reconstructs Missing Climate“. He will demonstrate that artificial intelligence techniques perform accurate reconstructions to climate information. Historical temperature measurements are the basis of important global climate datasets but contain many missing values and have low resolution grids. Kadow will show that through his development of a neural network, these observation gaps can be cleverly filled and even scaled up in combination with numerical climate model data - which is unique and state-of-the-art in climate research.
With a further poster on „Distributed Deep Learning on HPC for Infilling Holes in Spatial Precipitation Data“ presents how machine learning methods can be used to fill gaps in precipitation data series. So far, existing approaches for infilling missing precipitation data are mostly numerical or statistical techniques that require time consuming computations and are not suitable for large regions with missing data.
On November, 17, 2022 Dr. Panagiotis Adamidis will contribute to the Birds of a Feather Session (BoF) “DAOS Storage Community”. DAOS is an open-source scale-out object store that delivers extremely high performance to the most data-intensive HPC/AI workloads. This BoF brings together the DAOS community to discuss, share experiences, and brainstorm on future enhancements of DAOS. Topics include practical experiences with on-prem and cloud deployments, application use cases, and the software roadmap.
Further information and conference program: sc22.supercomputing.org