Convolutional conditional neural processes for local climate downscaling
Vaughan, Anna; Tebbutt, Will; Hosking, J. Scott ORCID: https://orcid.org/0000-0002-3646-3504; Turner, Richard E.. 2022 Convolutional conditional neural processes for local climate downscaling. Geoscientific Model Development, 15 (1). 251-268. 10.5194/gmd-15-251-2022
Before downloading, please read NORA policies.Preview |
Text (Open Access)
© Author(s) 2022. This work is distributed under the Creative Commons Attribution 4.0 License. gmd-15-251-2022.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (6MB) | Preview |
Abstract/Summary
A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently developed class of models that allow deep-learning techniques to be applied to off-the-grid spatio-temporal data. In contrast to existing methods that map from low-resolution model output to high-resolution predictions at a discrete set of locations, this model outputs a stochastic process that can be queried at an arbitrary latitude–longitude coordinate. The convCNP model is shown to outperform an ensemble of existing downscaling techniques over Europe for both temperature and precipitation taken from the VALUE intercomparison project. The model also outperforms an approach that uses Gaussian processes to interpolate single-site downscaling models at unseen locations. Importantly, substantial improvement is seen in the representation of extreme precipitation events. These results indicate that the convCNP is a robust downscaling model suitable for generating localised projections for use in climate impact studies.
Item Type: | Publication - Article |
---|---|
Digital Object Identifier (DOI): | 10.5194/gmd-15-251-2022 |
ISSN: | 1991-9603 |
Date made live: | 25 Jan 2022 09:00 +0 (UTC) |
URI: | https://nora.nerc.ac.uk/id/eprint/531816 |
Actions (login required)
View Item |
Document Downloads
Downloads for past 30 days
Downloads per month over past year