MeteoSwiss/photocast
Watch
2
mirror of https://github.com/MeteoSwiss/photocast.git synced 2026-08-26 13:24:21 +00:00
Code Releases Activity
Read-only mirror of https://github.com/MeteoSwiss/photocast — MeteoSwiss. Issues & pull requests at the source.
16 commits 1 branch 0 tags 666 MiB
  • Python 69.1%
  • R 30.9%
Find a file
Exact
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Christian Sigg f94849ee44
 Update README.md 
Changed link to published paper
2023-01-08 22:06:38 +01:00
data updated analog retrieval experiments 2022-03-29 14:18:23 +00:00
experiment renamed evaluation folders, added updated matching condition results, added input reproduction results 2022-08-04 12:46:13 +00:00
renv Import 2022-03-23 21:27:17 +01:00
src Import 2022-03-23 21:27:17 +01:00
.gitignore Import 2022-03-23 21:27:17 +01:00
.Rprofile Import 2022-03-23 21:27:17 +01:00
AUTHORS Import 2022-03-23 21:27:17 +01:00
LICENSE Initial commit 2022-02-24 14:16:47 +01:00
photographic-visualization.png Add files via upload 2022-09-29 18:02:46 +02:00
README.md Update README.md 2023-01-08 22:06:38 +01:00
renv.lock Import 2022-03-23 21:27:17 +01:00
requirements.txt Import 2022-03-23 21:27:17 +01:00

README.md

Photographic Visualizations of Weather Forecasts

A sequence of images taken by the Cevio camera (top row), and the corresponding images synthesized by the generator (bottom row)

DOI

This is the companion repository for our paper on Photographic Visualizations of Weather Forecasts. It contains the Tensorflow implementations of the generator and discriminator networks, as well as the code to reproduce the experiments presented in Sections 1.2 and 4 of the paper.

The data used in the expert evaluations and their detailed results (summarized in Tables 2, 3 and 4 of the paper) are also available.

Because of the large file size of the trained models, they are only availble in the Zenodo upload (which also contains everything else from this GitHub repository).

The complete image archive and COSMO-1 forecast fields used for the training and evaluation of the networks can not be published online due to licensing restrictions. But they can be obtained free of charge for academic research purposes by contacting the MeteoSwiss customer service desk. Once obtained, add the images to data/raw__/image and the COSMO-1 .csv files to data/raw__/cosmo_1-2019-2020 (see the examples therein), and regenerate the training and testing data sets using the scripts in data/cosmo/surface and data/nowcasting.