Model uncertainty estimation using the ensemble approach poses a large computation requirement. This is because ensembles are usually generated form multi-model and multi-simulation with slightly perturbed initialization.
In this presentation, an analog-based method, Analog Ensemble, for model uncertainty learning, is introduced. Analog Ensemble is a highly efficient and scalable technique to extract uncertainty information from a single realization of a deterministic model. The method relies on the predictive model and the corresponding historical observations or model analysis. Case studies will be presented to show the performance of Analog Ensemble.
The presentation is the first half of the series on Analog Ensemble. The second half is the hands-on tutorial on Thursday morning which will provide the practical details on running the method locally and at scale using Cheyenne.
Weiming Hu is a Ph.D. student of Prof. Guido Cervone at Penn State University in the Dept. of Geography focusing on computational algorithms, and numerical weather prediction; Guido Cervone is the Associate Professor at Dept. of Geography and the Associate Director of Institue for CyberScience at Penn State University.
He can be reached at weiming@psu.edu if you have any questions.
