% 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{Stadtler:906258,
author = {Stadtler, Scarlet and Betancourt, Clara and Roscher,
Ribana},
title = {{E}xplainable {M}achine {L}earning {R}eveals
{C}apabilities, {R}edundancy, and {L}imitations of a
{G}eospatial {A}ir {Q}uality {B}enchmark {D}ataset},
journal = {Machine learning and knowledge extraction},
volume = {4},
number = {1},
issn = {2504-4990},
address = {Basel},
publisher = {MDPI},
reportid = {FZJ-2022-01329},
pages = {150 - 171},
year = {2022},
abstract = {Air quality is relevant to society because it poses
environmental risks to humans and nature. We use explainable
machine learning in air quality research by analyzing model
predictions in relation to the underlying training data. The
data originate from worldwide ozone observations, paired
with geospatial data. We use two different architectures: a
neural network and a random forest trained on various
geospatial data to predict multi-year averages of the air
pollutant ozone. To understand how both models function, we
explain how they represent the training data and derive
their predictions. By focusing on inaccurate predictions and
explaining why these predictions fail, we can (i) identify
underrepresented samples, (ii) flag unexpected inaccurate
predictions, and (iii) point to training samples irrelevant
for predictions on the test set. Based on the
underrepresented samples, we suggest where to build new
measurement stations. We also show which training samples do
not substantially contribute to the model performance. This
study demonstrates the application of explainable machine
learning beyond simply explaining the trained model.},
cin = {JSC},
ddc = {004},
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) / AI
Strategy for Earth system data $(kiste_20200501)$ / Earth
System Data Exploration (ESDE)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)787576 /
$G:(DE-Juel1)kiste_20200501$ / G:(DE-Juel-1)ESDE},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000774979600001},
doi = {10.3390/make4010008},
url = {https://juser.fz-juelich.de/record/906258},
}