Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes

Satellite retrievals of XCO2 at northern high latitudes currently have sparser coverage and lower data quality than most other regions of the world. We use a neural network (NN) to filter Orbiting Carbon Observ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	J. Mendonca, R. Nassar, C. W. O'Dell, R. Kivi, I. Morino, J. Notholt, C. Petri, K. Strong, D. Wunch
Formato:	article
Lenguaje:	EN
Publicado:	Copernicus Publications 2021
Materias:	Environmental engineering TA170-171 Earthwork. Foundations TA715-787
Acceso en línea:	https://doaj.org/article/2d281de1674742429e37e44d1d0ac717
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2d281de1674742429e37e44d1d0ac717
record_format	dspace
spelling	oai:doaj.org-article:2d281de1674742429e37e44d1d0ac7172021-12-03T15:33:07ZAssessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes10.5194/amt-14-7511-20211867-13811867-8548https://doaj.org/article/2d281de1674742429e37e44d1d0ac7172021-12-01T00:00:00Zhttps://amt.copernicus.org/articles/14/7511/2021/amt-14-7511-2021.pdfhttps://doaj.org/toc/1867-1381https://doaj.org/toc/1867-8548<p>Satellite retrievals of <span class="inline-formula">XCO<sub>2</sub></span> at northern high latitudes currently have sparser coverage and lower data quality than most other regions of the world. We use a neural network (NN) to filter Orbiting Carbon Observatory 2 (OCO-2) B10 bias-corrected <span class="inline-formula">XCO<sub>2</sub></span> retrievals and compare the quality of the filtered data to the quality of the data filtered with the standard B10 quality control filter. To assess the performance of the NN filter, we use Total Carbon Column Observing Network (TCCON) data at selected northern high latitude sites as a truth proxy. We found that the NN filter decreases the overall bias by 0.25 <span class="inline-formula">ppm</span> (<span class="inline-formula">∼</span> 50 %), improves the precision by 0.18 <span class="inline-formula">ppm</span> (<span class="inline-formula">∼</span> 12 %), and increases the throughput by 16 % at these sites when compared to the standard B10 quality control filter. Most of the increased throughput was due to an increase in throughput during the spring, fall, and winter seasons. There was a decrease in throughput during the summer, but as a result the bias and precision were improved during the summer months. The main drawback of using the NN filter is that it lets through fewer retrievals at the highest-latitude Arctic TCCON sites compared to the B10 quality control filter, but the lower throughput improves the bias and precision.</p>J. MendoncaR. NassarC. W. O'DellR. KiviI. MorinoJ. NotholtC. PetriK. StrongD. WunchCopernicus PublicationsarticleEnvironmental engineeringTA170-171Earthwork. FoundationsTA715-787ENAtmospheric Measurement Techniques, Vol 14, Pp 7511-7524 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Environmental engineering TA170-171 Earthwork. Foundations TA715-787
spellingShingle	Environmental engineering TA170-171 Earthwork. Foundations TA715-787 J. Mendonca R. Nassar C. W. O'Dell R. Kivi I. Morino J. Notholt C. Petri K. Strong D. Wunch Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes
description	<p>Satellite retrievals of <span class="inline-formula">XCO<sub>2</sub></span> at northern high latitudes currently have sparser coverage and lower data quality than most other regions of the world. We use a neural network (NN) to filter Orbiting Carbon Observatory 2 (OCO-2) B10 bias-corrected <span class="inline-formula">XCO<sub>2</sub></span> retrievals and compare the quality of the filtered data to the quality of the data filtered with the standard B10 quality control filter. To assess the performance of the NN filter, we use Total Carbon Column Observing Network (TCCON) data at selected northern high latitude sites as a truth proxy. We found that the NN filter decreases the overall bias by 0.25 <span class="inline-formula">ppm</span> (<span class="inline-formula">∼</span> 50 %), improves the precision by 0.18 <span class="inline-formula">ppm</span> (<span class="inline-formula">∼</span> 12 %), and increases the throughput by 16 % at these sites when compared to the standard B10 quality control filter. Most of the increased throughput was due to an increase in throughput during the spring, fall, and winter seasons. There was a decrease in throughput during the summer, but as a result the bias and precision were improved during the summer months. The main drawback of using the NN filter is that it lets through fewer retrievals at the highest-latitude Arctic TCCON sites compared to the B10 quality control filter, but the lower throughput improves the bias and precision.</p>
format	article
author	J. Mendonca R. Nassar C. W. O'Dell R. Kivi I. Morino J. Notholt C. Petri K. Strong D. Wunch
author_facet	J. Mendonca R. Nassar C. W. O'Dell R. Kivi I. Morino J. Notholt C. Petri K. Strong D. Wunch
author_sort	J. Mendonca
title	Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes
title_short	Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes
title_full	Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes
title_fullStr	Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes
title_full_unstemmed	Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes
title_sort	assessing the feasibility of using a neural network to filter orbiting carbon observatory 2 (oco-2) retrievals at northern high latitudes
publisher	Copernicus Publications
publishDate	2021
url	https://doaj.org/article/2d281de1674742429e37e44d1d0ac717
work_keys_str_mv	AT jmendonca assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT rnassar assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT cwodell assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT rkivi assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT imorino assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT jnotholt assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT cpetri assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT kstrong assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes AT dwunch assessingthefeasibilityofusinganeuralnetworktofilterorbitingcarbonobservatory2oco2retrievalsatnorthernhighlatitudes
_version_	1718373135842017280

Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes

Ejemplares similares