% 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”.
@ARTICLE{Kleinert:889193,
author = {Kleinert, Felix and Leufen, Lukas H. and Schultz, Martin
G.},
title = {{I}ntelli{O}3-ts v1.0: a neural network approach to predict
near-surface ozone concentrations in {G}ermany},
journal = {Geoscientific model development},
volume = {14},
number = {1},
issn = {1991-9603},
address = {Katlenburg-Lindau},
publisher = {Copernicus},
reportid = {FZJ-2021-00103},
pages = {1 - 25},
year = {2021},
abstract = {The prediction of near-surface ozone concentrations is
important for supporting regulatory procedures for the
protection of humans from high exposure to air pollution. In
this study, we introduce a data-driven forecasting model
named “IntelliO3-ts”, which consists of multiple
convolutional neural network (CNN) layers, grouped together
as inception blocks. The model is trained with measured
multi-year ozone and nitrogen oxide concentrations of more
than 300 German measurement stations in rural environments
and six meteorological variables from the meteorological
COSMO reanalysis. This is by far the most extensive dataset
used for time series predictions based on neural networks so
far. IntelliO3-ts allows the prediction of daily maximum
8 h average (dma8eu) ozone concentrations for a lead time
of up to 4 d, and we show that the model outperforms
standard reference models like persistence models. Moreover,
we demonstrate that IntelliO3-ts outperforms climatological
reference models for the first 2 d, while it does not add
any genuine value for longer lead times. We attribute this
to the limited deterministic information that is contained
in the single-station time series training data. We applied
a bootstrapping technique to analyse the influence of
different input variables and found that the previous-day
ozone concentrations are of major importance, followed by
2 m temperature. As we did not use any geographic
information to train IntelliO3-ts in its current version and
included no relation between stations, the influence of the
horizontal wind components on the model performance is
minimal. We expect that the inclusion of
advection–diffusion terms in the model could improve
results in future versions of our model.},
cin = {JSC / NIC},
ddc = {550},
cid = {I:(DE-Juel1)JSC-20090406 / I:(DE-Juel1)NIC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / IntelliAQ -
Artificial Intelligence for Air Quality (787576) / PhD no
Grant - Doktorand ohne besondere Förderung
(PHD-NO-GRANT-20170405) / Deep Learning for Air Quality and
Climate Forecasts $(deepacf_20191101)$ / Earth System Data
Exploration (ESDE)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)787576 /
G:(DE-Juel1)PHD-NO-GRANT-20170405 /
$G:(DE-Juel1)deepacf_20191101$ / G:(DE-Juel-1)ESDE},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000606577700001},
doi = {10.5194/gmd-14-1-2021},
url = {https://juser.fz-juelich.de/record/889193},
}