Reconstructing Aerosols Vertical Profiles with Aggregate Output Learning

This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.


Download Preprint


Sofija Stefanovic, Shahine Bouabid, Philip Stier, Athanasios Nenes, Dino Sejdinovic


Aerosol-cloud interactions constitute the largest source of uncertainty in assessments of anthropogenic climate change. This uncertainty arises in part from the inability to observe aerosol amounts at the cloud formation levels, and, more broadly, the vertical distribution of aerosols. Hence, we often have to settle for less informative two-dimensional proxies, i.e. vertically aggregated data. In this work, we formulate the problem of disaggregation of vertical profiles of aerosols. We propose some initial solutions for such an aggregate output regression problem and demonstrate their potential on climate model data.



Physical Sciences and Mathematics


Aerosols, , ICML, Aerosols, Vertical Profiles, Optical Depth, Gaussian Processes, Aggregate Learning, Kernel Mean Embeddings, Variational Inference, ICML, Vertical Profiles, Optical Depth, Aggregate Learning


Published: 2021-07-02 19:58

Last Updated: 2021-07-02 22:58


CC BY Attribution 4.0 International

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.