% 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{Kleinert:890961,
author = {Kleinert, Felix and Leufen, Lukas H. and Lupascu, Aurelia
and Butler, Tim and Schultz, Martin G.},
title = {{R}epresenting chemical history for ozone time-series
predictions - a method development study for deep learning
models},
reportid = {FZJ-2021-01277},
year = {2021},
abstract = {<p>Machine learning techniques like deep learning gained
enormous momentum in recent years. This was mainly caused by
the success story of the main drivers like image and speech
recognition, video prediction and autonomous driving, to
name just a few.<br>Air pollutant forecasting models are an
example, where earth system scientists start picking up deep
learning models to enhance the forecast quality of time
series. Almost all previous air pollution forecasts with
machine learning rely solely on analysing temporal features
in the observed time series of the target compound(s) and
additional variables describing precursor concentrations and
meteorological conditions. These studies, therefore, neglect
the 'chemical history' of air masses, i.e. the fact that air
pollutant concentrations at a given observation site are a
result of emission and sink processes, mixing and chemical
transformations along the transport pathways of air.<br>This
study develops a concept of how such factors can be
represented in the recently published deep learning model
IntelliO3. The concept is demonstrated with numerical model
data from the WRF-Chem model because the gridded model data
provides an internally consistent dataset with complete
spatial coverage and no missing values.<br>Furthermore,
using model data allows for attributing changes of the
forecasting performance to specific conceptual aspects. For
example, we use the 8 wind sectors (N, NE, E, SE, etc.) and
circles with predefined radii around our target locations to
aggregate meteorological and chemical data from the
intersections. Afterwards, we feed this aggregated data into
a deep neural network while using the ozone concentration of
the central point's next timesteps as targets. By analysing
the change of forecast quality when moving from
4-dimensional (x, y, z, t) to 3-dimensional (x, y, t or r,
$\φ,$ t) sectors and thinning out the underlying model
data, we can deliver first estimates of expected performance
gains or losses when applying our concept to station based
surface observations in future studies.</p>},
month = {Apr},
date = {2021-04-19},
organization = {EGU General Assembly 2021, Vienna
(online) (Austria), 19 Apr 2021 - 30
Apr 2021},
cin = {JSC},
ddc = {610},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / IntelliAQ -
Artificial Intelligence for Air Quality (787576) / Earth
System Data Exploration (ESDE)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)787576 /
G:(DE-Juel-1)ESDE},
typ = {PUB:(DE-HGF)1},
doi = {10.5194/egusphere-egu21-12146},
url = {https://juser.fz-juelich.de/record/890961},
}