Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic
In this paper, we present the novel approach for the downscaling of of near-surface winds in the North Atlantic. Surface wind is one of the most important physical fields in climate research. Accurate prediction of high-resolution near-surface winds has a wide variety of applications. Statistical do...
Main Authors: | , , , |
---|---|
Format: | Conference Object |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://zenodo.org/record/5760067 https://doi.org/10.5281/zenodo.5760067 |
id |
ftzenodo:oai:zenodo.org:5760067 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:5760067 2023-05-15T17:26:45+02:00 Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic Vadim Rezvov Mikhail Krinitskiy Alexander Gavrikov Sergey Gulev 2021-09-16 https://zenodo.org/record/5760067 https://doi.org/10.5281/zenodo.5760067 eng eng doi:10.5281/zenodo.5760066 https://zenodo.org/record/5760067 https://doi.org/10.5281/zenodo.5760067 oai:zenodo.org:5760067 info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode Statistical downscaling neural networks North Atlantic near-surface wind info:eu-repo/semantics/conferencePaper publication-conferencepaper 2021 ftzenodo https://doi.org/10.5281/zenodo.576006710.5281/zenodo.5760066 2023-03-11T02:02:16Z In this paper, we present the novel approach for the downscaling of of near-surface winds in the North Atlantic. Surface wind is one of the most important physical fields in climate research. Accurate prediction of high-resolution near-surface winds has a wide variety of applications. Statistical downscaling methods obtain high-resolution information about the physical quantity distribution using available low-resolution data. They avoid high-resolution hydrodynamic simulations that are computationally expensive. Deep learning methods are one of the typical examples of the machine learning approaches to complex nonlinear functions approximating. In this work, we consider statistical downscaling of near-surface wind in the North Atlantic. For this, cubic interpolation, various architectures of convolutional networks, and generative adversarial network are applied. Based on the results obtained, the quality of these statistical downscaling methods is compared, and their advantages and disadvantages are identified. Conference Object North Atlantic Zenodo |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
English |
topic |
Statistical downscaling neural networks North Atlantic near-surface wind |
spellingShingle |
Statistical downscaling neural networks North Atlantic near-surface wind Vadim Rezvov Mikhail Krinitskiy Alexander Gavrikov Sergey Gulev Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic |
topic_facet |
Statistical downscaling neural networks North Atlantic near-surface wind |
description |
In this paper, we present the novel approach for the downscaling of of near-surface winds in the North Atlantic. Surface wind is one of the most important physical fields in climate research. Accurate prediction of high-resolution near-surface winds has a wide variety of applications. Statistical downscaling methods obtain high-resolution information about the physical quantity distribution using available low-resolution data. They avoid high-resolution hydrodynamic simulations that are computationally expensive. Deep learning methods are one of the typical examples of the machine learning approaches to complex nonlinear functions approximating. In this work, we consider statistical downscaling of near-surface wind in the North Atlantic. For this, cubic interpolation, various architectures of convolutional networks, and generative adversarial network are applied. Based on the results obtained, the quality of these statistical downscaling methods is compared, and their advantages and disadvantages are identified. |
format |
Conference Object |
author |
Vadim Rezvov Mikhail Krinitskiy Alexander Gavrikov Sergey Gulev |
author_facet |
Vadim Rezvov Mikhail Krinitskiy Alexander Gavrikov Sergey Gulev |
author_sort |
Vadim Rezvov |
title |
Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic |
title_short |
Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic |
title_full |
Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic |
title_fullStr |
Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic |
title_full_unstemmed |
Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic |
title_sort |
comparison of al-based approaches for statistical downscaling of surface wind fields in the north atlantic |
publishDate |
2021 |
url |
https://zenodo.org/record/5760067 https://doi.org/10.5281/zenodo.5760067 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_relation |
doi:10.5281/zenodo.5760066 https://zenodo.org/record/5760067 https://doi.org/10.5281/zenodo.5760067 oai:zenodo.org:5760067 |
op_rights |
info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.5281/zenodo.576006710.5281/zenodo.5760066 |
_version_ |
1766118550281388032 |