Published October 27, 2021 | Version v1.0
Dataset Open

BNNOz - Infilled vertically resolved ozone dataset

Description

This vertical ozone dataset is a fusion of an existing ozone dataset (Bodeker Scientific) with chemistry-climate model output from the Chemistry-Climate modelling initiative.

The vertically and latitudinally resolved ozone dataset (zmo3_BNNOz.nc) has been produced by fusing the above data within a Bayesian neural network.

More information about this processing and the data can be found here.

In addition to the output product we include the training dataset of observed and modelled ozone as a python pickled dataframe. The code to use this training dataset can be found here.

This data submission supports a manuscript submission to ESSD.

Files

Files (150.8 MB)

Name Size Download all
md5:87f9094a12d5d1424bd2701e784820a3
139.7 MB Download
md5:bf8d917315aed025397bc24aa1afa4e2
11.2 MB Download

Additional details

Funding

UK Research and Innovation
ENVISION: Developing next generation leaders in environmental science NE/L002604/1
UK Research and Innovation
Data Science of the Natural Environment EP/R01860X/1