Adewoyin, Rilwan A., Dueben, Peter, Watson, Peter, He, Yulan and Dutta, Ritabrata (2022) TRU-NET : a deep learning approach to high resolution prediction of rainfall. Machine Learning, 110 (8). pp. 2035-2062. doi:10.1007/s10994-021-06022-6 ISSN 2632-2153.

Preview	PDF WRAP-TRU-NET-deep-learning-approach-high-resolution-prediction-rainfall-Adewoyin-2022.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (4Mb) | Preview
	PDF paper.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only - Requires a PDF viewer. Download (8Mb)

Request Changes to record.

Abstract

Climate models (CM) are used to evaluate the impact of climate change on the risk of floods and heavy precipitation events. However, these numerical simulators produce outputs with low spatial resolution that exhibit difficulties representing precipitation events accurately. This is mainly due to computational limitations on the spatial resolution used when simulating multi-scale weather dynamics in the atmosphere. To improve the prediction of high resolution precipitation we apply a Deep Learning (DL) approach using input data from a reanalysis product, that is comparable to a climate model’s output, but can be directly related to precipitation observations at a given time and location. Further, our input excludes local precipitation, but includes model fields (weather variables) that are more predictable and generalizable than local precipitation. To this end, we present TRU-NET (Temporal Recurrent U-Net), an encoderdecoder model featuring a novel 2D cross attention mechanism between contiguous convolutional-recurrent layers to effectively model multi-scale spatio-temporal weather processes. We also propose a non-stochastic variant of the conditionalcontinuous (CC) loss function to capture the zero-skewed patterns of rainfall. Experiments show that our models, trained with our CC loss, consistently attain lower RMSE and MAE scores than a DL model prevalent in precipitation downscaling and outperform a state-of-the-art dynamical weather model. Moreover, by evaluating the performance of our model under various data formulation strategies, for the training and test sets, we show that there is enough data for our deep learning approach to output robust, high-quality results across seasons and varying regions.

Item Type:	Journal Article
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software Q Science > QC Physics
Divisions:	Faculty of Science, Engineering and Medicine > Science > Computer Science Faculty of Science, Engineering and Medicine > Science > Statistics
Library of Congress Subject Headings (LCSH):	Climatology -- Mathematical models, Climatology -- Simulation methods, Precipitation forecasting , Rainfall probabilities , Neural networks (Computer science), Deep learning (Machine learning)
Journal or Publication Title:	Machine Learning
Publisher:	Springer
ISSN:	2632-2153
Official Date:	August 2022
Dates:	Date Event August 2022 Published 7 July 2022 Available 15 June 2021 Accepted
Volume:	110
Number:	8
Page Range:	pp. 2035-2062
DOI:	10.1007/s10994-021-06022-6
Status:	Peer Reviewed
Publication Status:	Published
Access rights to Published version:	Open Access (Creative Commons)
Date of first compliant deposit:	25 May 2022
Date of first compliant Open Access:	25 May 2022

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads