% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Betancourt:892258,
author = {Betancourt, Clara and Stadtler, Scarlet and Stomberg, Timo
and Edrich, Ann-Kathrin and Patnala, Ankit and Roscher,
Ribana and Kowalski, Julia and Schultz, Martin},
title = {{G}lobal fine resolution mapping of ozone metrics through
explainable machine learning},
reportid = {FZJ-2021-01988},
year = {2021},
abstract = {Through the availability of multi-year ground based ozone
observations on a global scale, substantial geospatial meta
data, and high performance computing capacities, it is now
possible to use machine learning for a global data-driven
ozone assessment. In this presentation, we will show a
novel, completely data-driven approach to map tropospheric
ozone globally.Our goal is to interpolate ozone metrics and
aggregated statistics from the database of the Tropospheric
Ozone Assessment Report (TOAR) onto a global 0.1° x 0.1°
resolution grid. It is challenging to interpolate ozone, a
toxic greenhouse gas because its formation depends on many
interconnected environmental factors on small scales. We
conduct the interpolation with various machine learning
methods trained on aggregated hourly ozone data from five
years at more than 5500 locations worldwide. We use several
geospatial datasets as training inputs to provide proxy
input for environmental factors controlling ozone formation,
such as precursor emissions and climate. The resulting maps
contain different ozone metrics, i.e. statistical
aggregations which are widely used to assess air pollution
impacts on health, vegetation, and climate.The key aspects
of this contribution are twofold: First, we apply
explainable machine learning methods to the data-driven
ozone assessment. Second, we discuss dominant uncertainties
relevant to the ozone mapping and quantify their impact
whenever possible. Our methods include a thorough a-priori
uncertainty estimation of the various data and methods,
assessment of scientific consistency, finding critical model
parameters, using ensemble methods, and performing error
modeling.Our work aims to increase the reliability and
integrity of the derived ozone maps through the provision of
scientific robustness to a data-centric machine learning
task. This study hence represents a blueprint for how to
formulate an environmental machine learning task
scientifically, gather the necessary data, and develop a
data-driven workflow that focuses on optimizing transparency
and applicability of its product to maximize its scientific
knowledge return.},
month = {Apr},
date = {2021-04-19},
organization = {EGU General Assembly 2021, Online
(Online), 19 Apr 2021 - 30 Apr 2021},
subtyp = {Other},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {511 - Enabling Computational- $\&$ Data-Intensive Science
and Engineering (POF4-511) / IntelliAQ - Artificial
Intelligence for Air Quality (787576) / Earth System Data
Exploration (ESDE)},
pid = {G:(DE-HGF)POF4-511 / G:(EU-Grant)787576 /
G:(DE-Juel-1)ESDE},
typ = {PUB:(DE-HGF)6},
doi = {10.13140/RG.2.2.17134.13123},
url = {https://juser.fz-juelich.de/record/892258},
}