Can I read Data-Efficient Generative Modeling of Non-Gaussian Global Climate Fields Via Scalable Composite Transformations on EtoBox?

Data-Efficient Generative Modeling of Non-Gaussian Global Climate Fields Via Scalable Composite Transformations by scomatozze28 is a document available to read on EtoBox.

What is Data-Efficient Generative Modeling of Non-Gaussian Global Climate Fields Via Scalable Composite Transformations about?

The document presents a data-efficient framework for emulating the internal variability of global climate fields, addressing the challenges posed by the high computational costs of physical climate models and limited training data. The proposed method utilizes a composite transformation approach, combining nonparametric Bayesian transport maps with flexible marginal models to accurately capture non-Gaussian behavior and spatial dependencies. The framework demonstrates superior performance in generating clim

Author

scomatozze28

Language

EN