A Bayesian Deep Learning Approach to Near-Term Climate Prediction
Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate prediction. The example problem setting we consider consists of pre...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2022
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2202.11244 https://arxiv.org/abs/2202.11244 |
id |
ftdatacite:10.48550/arxiv.2202.11244 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2202.11244 2023-05-15T17:34:03+02:00 A Bayesian Deep Learning Approach to Near-Term Climate Prediction Luo, Xihaier Nadiga, Balasubramanya T. Ren, Yihui Park, Ji Hwan Xu, Wei Yoo, Shinjae 2022 https://dx.doi.org/10.48550/arxiv.2202.11244 https://arxiv.org/abs/2202.11244 unknown arXiv Creative Commons Attribution Non Commercial No Derivatives 4.0 International https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode cc-by-nc-nd-4.0 CC-BY-NC-ND Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences Article CreativeWork article Preprint 2022 ftdatacite https://doi.org/10.48550/arxiv.2202.11244 2022-03-10T15:09:53Z Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate prediction. The example problem setting we consider consists of predicting natural variability of the North Atlantic sea surface temperature on the interannual timescale in the pre-industrial control simulation of the Community Earth System Model (CESM2). While previous works have considered the use of recurrent networks such as convolutional LSTMs and reservoir computing networks in this and other similar problem settings, we currently focus on the use of feedforward convolutional networks. In particular, we find that a feedforward convolutional network with a Densenet architecture is able to outperform a convolutional LSTM in terms of predictive skill. Next, we go on to consider a probabilistic formulation of the same network based on Stein variational gradient descent and find that in addition to providing useful measures of predictive uncertainty, the probabilistic (Bayesian) version improves on its deterministic counterpart in terms of predictive skill. Finally, we characterize the reliability of the ensemble of ML models obtained in the probabilistic setting by using analysis tools developed in the context of ensemble numerical weather prediction. : 32 pages, 12 figures Article in Journal/Newspaper North Atlantic DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences |
spellingShingle |
Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences Luo, Xihaier Nadiga, Balasubramanya T. Ren, Yihui Park, Ji Hwan Xu, Wei Yoo, Shinjae A Bayesian Deep Learning Approach to Near-Term Climate Prediction |
topic_facet |
Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences |
description |
Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate prediction. The example problem setting we consider consists of predicting natural variability of the North Atlantic sea surface temperature on the interannual timescale in the pre-industrial control simulation of the Community Earth System Model (CESM2). While previous works have considered the use of recurrent networks such as convolutional LSTMs and reservoir computing networks in this and other similar problem settings, we currently focus on the use of feedforward convolutional networks. In particular, we find that a feedforward convolutional network with a Densenet architecture is able to outperform a convolutional LSTM in terms of predictive skill. Next, we go on to consider a probabilistic formulation of the same network based on Stein variational gradient descent and find that in addition to providing useful measures of predictive uncertainty, the probabilistic (Bayesian) version improves on its deterministic counterpart in terms of predictive skill. Finally, we characterize the reliability of the ensemble of ML models obtained in the probabilistic setting by using analysis tools developed in the context of ensemble numerical weather prediction. : 32 pages, 12 figures |
format |
Article in Journal/Newspaper |
author |
Luo, Xihaier Nadiga, Balasubramanya T. Ren, Yihui Park, Ji Hwan Xu, Wei Yoo, Shinjae |
author_facet |
Luo, Xihaier Nadiga, Balasubramanya T. Ren, Yihui Park, Ji Hwan Xu, Wei Yoo, Shinjae |
author_sort |
Luo, Xihaier |
title |
A Bayesian Deep Learning Approach to Near-Term Climate Prediction |
title_short |
A Bayesian Deep Learning Approach to Near-Term Climate Prediction |
title_full |
A Bayesian Deep Learning Approach to Near-Term Climate Prediction |
title_fullStr |
A Bayesian Deep Learning Approach to Near-Term Climate Prediction |
title_full_unstemmed |
A Bayesian Deep Learning Approach to Near-Term Climate Prediction |
title_sort |
bayesian deep learning approach to near-term climate prediction |
publisher |
arXiv |
publishDate |
2022 |
url |
https://dx.doi.org/10.48550/arxiv.2202.11244 https://arxiv.org/abs/2202.11244 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_rights |
Creative Commons Attribution Non Commercial No Derivatives 4.0 International https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode cc-by-nc-nd-4.0 |
op_rightsnorm |
CC-BY-NC-ND |
op_doi |
https://doi.org/10.48550/arxiv.2202.11244 |
_version_ |
1766132750988869632 |