Skip to content

Integrate precipitation representations into training #25

Open
@mlangguth89

Description

@mlangguth89

Is your feature request related to a problem? Please describe.

So far, precipitation is not explicitly included into the training process. For instance, the ERA5 dataset used so far does not involve precipitation.
However, precipitation in ERA5 also has systematic issues (e.g. overestimation of weak precipitation events -> 'convective drizzle' and underestimation of strong precipitation events), so the first step will target to include the observation-based IMERG dataset for training (https://gpm.nasa.gov/data/imerg). In addition to data loading, this will likely also require modifications to the normalization procedure since log-transformation is a standard approach to tackle the highly right-skewed PDF of precipitation data.

Describe the solution you'd like

No response

Describe alternatives you've considered

No response

Additional context

No response

Organisation

No response

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    • Status

      Concept phase

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions