Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets
We provide here the datasets used for the development of a deep learning algorithm which is presently candidate for the development of a daily 3D ocean product covering the North Atlantic at 1/10° resolution, over the 2010-2018 period, as part of the European Space Agency World Ocean Circulation pro...
Main Author: | |
---|---|
Format: | Other/Unknown Material |
Language: | unknown |
Published: |
Zenodo
2020
|
Subjects: | |
Online Access: | https://doi.org/10.5281/zenodo.4040843 |
id |
ftzenodo:oai:zenodo.org:4040843 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:4040843 2024-09-09T19:56:38+00:00 Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets Buongiorno Nardelli, Bruno 2020-09-21 https://doi.org/10.5281/zenodo.4040843 unknown Zenodo https://doi.org/10.5281/zenodo.4040842 https://doi.org/10.5281/zenodo.4040843 oai:zenodo.org:4040843 info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode info:eu-repo/semantics/other 2020 ftzenodo https://doi.org/10.5281/zenodo.404084310.5281/zenodo.4040842 2024-07-26T22:16:46Z We provide here the datasets used for the development of a deep learning algorithm which is presently candidate for the development of a daily 3D ocean product covering the North Atlantic at 1/10° resolution, over the 2010-2018 period, as part of the European Space Agency World Ocean Circulation project (ESA-WOC). The method is based on a stacked Long Short-Term Memory neural network, coupled to a Monte-Carlo dropout approach, and allows to project satellite-derived sea surface temperature, sea surface salinity and absolute dynamic topography data at depth after training with sparse co-located in situ vertical hydrographic profiles (Buongiorno Nardelli, 2020, doi: 10.3390/rs12193151 ). The training/test dataset presented here includes different sets of co-located temperature and salinity vertical profiles and corresponding satellite surface data: in situ observations extracted from the quality controlled Argo and CTD profiles produced byCopernicus Marine Environment Monitoring ServiceCORA 5.2 ( http://marine.copernicus.eu/services-portfolio/access-to-products/ ,product_id: INSITU_GLO_TS_REP_OBSERVATIONS_013_001_b, doi:10.17882/46219TS1,Szekely et al., 2019)and interpolated through a spline on a regularly spaced vertical grid (with 10 m intervals); climatological profiles extracted from World Ocean Atlas 2013 optimally interpolated monthly fields(Locarnini et al., 2013; Zweng et al., 2013), interpolated through a spline on a regularly spaced vertical grid (with 10 m intervals), upsized to a 1/10° horizontal grid through a cubic spline and linearly interpolated in time between the central day of each month; co-located Sea Surface Temperaturetaken from the level 4 (L4, i.e. interpolated) multi-year reprocessed Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA) developed by U.K. Met Office and distributed (upon free registration) through the Copernicus Marine Environment Monitoring Service (CMEMS, http://marine.copernicus.eu/services-portfolio/access-to-products/ , ... Other/Unknown Material North Atlantic Sea ice Zenodo |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
unknown |
description |
We provide here the datasets used for the development of a deep learning algorithm which is presently candidate for the development of a daily 3D ocean product covering the North Atlantic at 1/10° resolution, over the 2010-2018 period, as part of the European Space Agency World Ocean Circulation project (ESA-WOC). The method is based on a stacked Long Short-Term Memory neural network, coupled to a Monte-Carlo dropout approach, and allows to project satellite-derived sea surface temperature, sea surface salinity and absolute dynamic topography data at depth after training with sparse co-located in situ vertical hydrographic profiles (Buongiorno Nardelli, 2020, doi: 10.3390/rs12193151 ). The training/test dataset presented here includes different sets of co-located temperature and salinity vertical profiles and corresponding satellite surface data: in situ observations extracted from the quality controlled Argo and CTD profiles produced byCopernicus Marine Environment Monitoring ServiceCORA 5.2 ( http://marine.copernicus.eu/services-portfolio/access-to-products/ ,product_id: INSITU_GLO_TS_REP_OBSERVATIONS_013_001_b, doi:10.17882/46219TS1,Szekely et al., 2019)and interpolated through a spline on a regularly spaced vertical grid (with 10 m intervals); climatological profiles extracted from World Ocean Atlas 2013 optimally interpolated monthly fields(Locarnini et al., 2013; Zweng et al., 2013), interpolated through a spline on a regularly spaced vertical grid (with 10 m intervals), upsized to a 1/10° horizontal grid through a cubic spline and linearly interpolated in time between the central day of each month; co-located Sea Surface Temperaturetaken from the level 4 (L4, i.e. interpolated) multi-year reprocessed Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA) developed by U.K. Met Office and distributed (upon free registration) through the Copernicus Marine Environment Monitoring Service (CMEMS, http://marine.copernicus.eu/services-portfolio/access-to-products/ , ... |
format |
Other/Unknown Material |
author |
Buongiorno Nardelli, Bruno |
spellingShingle |
Buongiorno Nardelli, Bruno Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets |
author_facet |
Buongiorno Nardelli, Bruno |
author_sort |
Buongiorno Nardelli, Bruno |
title |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets |
title_short |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets |
title_full |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets |
title_fullStr |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets |
title_full_unstemmed |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: training datasets |
title_sort |
developing a deep learning network to retrieve ocean hydrographic profiles in the north atlantic from combined satellite and in situ measurements: training datasets |
publisher |
Zenodo |
publishDate |
2020 |
url |
https://doi.org/10.5281/zenodo.4040843 |
genre |
North Atlantic Sea ice |
genre_facet |
North Atlantic Sea ice |
op_relation |
https://doi.org/10.5281/zenodo.4040842 https://doi.org/10.5281/zenodo.4040843 oai:zenodo.org:4040843 |
op_rights |
info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.5281/zenodo.404084310.5281/zenodo.4040842 |
_version_ |
1809927414003793920 |