Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: test datasets.
We provide here the datasets used for the test and assessment 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 Circula...
Main Author: | |
---|---|
Format: | Dataset |
Language: | unknown |
Published: |
2020
|
Subjects: | |
Online Access: | https://zenodo.org/record/3943700 https://doi.org/10.5281/zenodo.3943700 |
id |
ftzenodo:oai:zenodo.org:3943700 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:3943700 2023-05-15T17:32:00+02:00 Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: test datasets. Buongiorno Nardelli, Bruno 2020-07-14 https://zenodo.org/record/3943700 https://doi.org/10.5281/zenodo.3943700 unknown doi:10.5281/zenodo.3943699 https://zenodo.org/record/3943700 https://doi.org/10.5281/zenodo.3943700 oai:zenodo.org:3943700 info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode ocean observations info:eu-repo/semantics/other dataset 2020 ftzenodo https://doi.org/10.5281/zenodo.394370010.5281/zenodo.3943699 2023-03-10T22:38:38Z We provide here the datasets used for the test and assessment 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 test dataset presented here includes different sets of co-located temperature and salinity vertical profiles: in situ observations extracted from the quality controlled Argo and CTD profiles produced by Copernicus Marine Environment Monitoring Service CORA 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; synthetic profiles obtained through three different techniques: multivariate EOF reconstruction, a 2 layer feed-forward network (with 1000 units in each hidden layer) and a stacked LSTM network (with 2 LSTM layers and 35 hidden units) References: Buongiorno Nardelli, B.: A Deep Learning network to retrieve ocean hydrographic profiles from combined satellite and in situ measurements, 2020, submitted. Locarnini, R. A., Mishonov, A. V., Antonov, J. I., ... Dataset North Atlantic Zenodo Cora ENVELOPE(-60.317,-60.317,-62.467,-62.467) |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
unknown |
topic |
ocean observations |
spellingShingle |
ocean observations Buongiorno Nardelli, Bruno Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: test datasets. |
topic_facet |
ocean observations |
description |
We provide here the datasets used for the test and assessment 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 test dataset presented here includes different sets of co-located temperature and salinity vertical profiles: in situ observations extracted from the quality controlled Argo and CTD profiles produced by Copernicus Marine Environment Monitoring Service CORA 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; synthetic profiles obtained through three different techniques: multivariate EOF reconstruction, a 2 layer feed-forward network (with 1000 units in each hidden layer) and a stacked LSTM network (with 2 LSTM layers and 35 hidden units) References: Buongiorno Nardelli, B.: A Deep Learning network to retrieve ocean hydrographic profiles from combined satellite and in situ measurements, 2020, submitted. Locarnini, R. A., Mishonov, A. V., Antonov, J. I., ... |
format |
Dataset |
author |
Buongiorno Nardelli, Bruno |
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: test datasets. |
title_short |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: test datasets. |
title_full |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: test datasets. |
title_fullStr |
Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: test 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: test datasets. |
title_sort |
developing a deep learning network to retrieve ocean hydrographic profiles in the north atlantic from combined satellite and in situ measurements: test datasets. |
publishDate |
2020 |
url |
https://zenodo.org/record/3943700 https://doi.org/10.5281/zenodo.3943700 |
long_lat |
ENVELOPE(-60.317,-60.317,-62.467,-62.467) |
geographic |
Cora |
geographic_facet |
Cora |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_relation |
doi:10.5281/zenodo.3943699 https://zenodo.org/record/3943700 https://doi.org/10.5281/zenodo.3943700 oai:zenodo.org:3943700 |
op_rights |
info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.5281/zenodo.394370010.5281/zenodo.3943699 |
_version_ |
1766129907520241664 |