<div class="csl-bib-body">
<div class="csl-entry">Bittner, M., Hobeichi, S., Zawish, M., Diatta, S., Ozioko, R., Xu, S., & Jantsch, A. (2023, December). <i>An LSTM-based Downscaling Framework for Australian Precipitation Projections</i> [Poster Presentation]. NeurIPS 2023 Workshop: Tackling Climate Change with Machine Learning, New Orleans, United States of America (the). http://hdl.handle.net/20.500.12708/193304</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/193304
-
dc.description.abstract
Understanding potential changes in future rainfall and their local impacts on
Australian communities can inform adaptation decisions worth billions of dollars in
insurance, agriculture, and other sectors. This understanding relies on downscaling
a large ensemble of coarse Global Climate Models (GCMs), our primary tool for
simulating future climate. However, the prohibitively high computational cost of
downscaling has been a significant barrier. In response, this study develops a cost-
efficient downscaling framework for daily precipitation using Long Short-Term
Memory (LSTM) models. The models are trained with ERA5 reanalysis data and
a customized quantile loss function to better capture precipitation extremes. The
framework is employed to downscale precipitation from a GCM member of the
CMIP6 ensemble. We demonstrate the skills of the downscaling models to capture
spatial and temporal characteristics of precipitation. We also explore regional
future changes in precipitation extremes projected by the downscaled GCM. In
general, this framework will enable the generation of a large ensemble of regional
future projections for Australian rainfall. This will further enhance the assessment
of likely climate risks and the quantification of their uncertainties.
en
dc.description.sponsorship
Christian Doppler Forschungsgesellschaft
-
dc.language.iso
en
-
dc.subject
Downscaling Precipitation
en
dc.subject
Recurrent Neural Networks
en
dc.subject
Global Climate Models
en
dc.title
An LSTM-based Downscaling Framework for Australian Precipitation Projections
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.contributor.affiliation
UNSW Sydney, Australia
-
dc.contributor.affiliation
South East Technological University, Ireland
-
dc.contributor.affiliation
Ziguinchor University, Senegal
-
dc.contributor.affiliation
University of Nigeria, Nigeria
-
dc.contributor.affiliation
Indigo Information Services (United States), United States of America (the)
-
dc.relation.grantno
123456
-
dc.type.category
Poster Presentation
-
tuw.project.title
CDL Embedded Machine Learning
-
tuw.researchTopic.id
E4
-
tuw.researchTopic.id
C3
-
tuw.researchTopic.name
Environmental Monitoring and Climate Adaptation
-
tuw.researchTopic.name
Computational System Design
-
tuw.researchTopic.value
50
-
tuw.researchTopic.value
50
-
tuw.publication.orgunit
E384-02 - Forschungsbereich Systems on Chip
-
tuw.author.orcid
0009-0004-8022-2232
-
tuw.author.orcid
0000-0001-6825-3854
-
tuw.author.orcid
0000-0002-4994-3443
-
tuw.author.orcid
0000-0003-2251-0004
-
tuw.event.name
NeurIPS 2023 Workshop: Tackling Climate Change with Machine Learning
