A Neural Network Model for Estimating Carbon Fluxes in Forest Ecosystems from Remote Sensing Data
Forests are among the main places on Earth where carbon is collected and accumulated. However, instrumental assessment of carbon fluxes is possible only for small areas. When solving the scaling problem, machine learning methods are used, which allow transforming the Earth’s surface reflectance inte...
Gespeichert in:
| Veröffentlicht in: | Atmospheric and oceanic optics 2023-08, Vol.36 (4), p.323-328 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 328 |
|---|---|
| container_issue | 4 |
| container_start_page | 323 |
| container_title | Atmospheric and oceanic optics |
| container_volume | 36 |
| creator | Rozanov, A. P. Gribanov, K. G. |
| description | Forests are among the main places on Earth where carbon is collected and accumulated. However, instrumental assessment of carbon fluxes is possible only for small areas. When solving the scaling problem, machine learning methods are used, which allow transforming the Earth’s surface reflectance intensities in different spectral ranges into ground-based in situ observations. We suggest a regression neural network model of the multilayer perceptron type for assessment of carbon fluxes. The model is trained on FLUXNET network data for a station located in a boreal coniferous forest (56.4615° N, 32.9221° E). Using the vegetation indices NDVI and EVI measured by the MODIS spectroradiometer onboard the
Aqua
satellite, the air temperature at an altitude of 2 m, and total precipitation as input data, the model estimates the gross primary production (GPP), net ecosystem exchange (NEE), ecosystem respiration (TER), and some other parameters which characterize water and energy fluxes. The statistical assessments for the test dataset show high correlation coefficients (
R
) and Nash–Sutcliffe coefficients (NSE):
R
> 0.9 and NSE ≥ 0.87 for GPP and TER;
R
= 0.4 and NSE = 0.15 for NEE. |
| doi_str_mv | 10.1134/S1024856023040152 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2852694964</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2852694964</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-a367ad97ec395d3990915ee63ce2242f24a33ac51485b8d310ca07590e0421c63</originalsourceid><addsrcrecordid>eNp1UE1LAzEQDaJgrf4AbwHPq5PPbY6ltipUBavnJd2dLa27m5qkaP-9WSp4EE8z8D5m3iPkksE1Y0LeLBhwOVIauAAJTPEjMuCQQwbCiGMy6OGsx0_JWQgbAK2MYgNix_QJd942acRP59_po6uwobXzdBriurVx3a3oxPql6-is2X1hoOu0OY8h0mnpwj5EbAOtvWvpC7YuIl1gF3rZrY32nJzUtgl48TOH5G02fZ3cZ_Pnu4fJeJ6VgumYWaFzW5kcS2FUJYwBwxSiFiVyLnnNpRXCloqllMtRJRiUFnJlAEFyVmoxJFcH3613H7v0XLFxO9-lkwUfKa6NNFomFjuwSu9C8FgXW59C-n3BoOibLP40mTT8oAmJ263Q_zr_L_oGDNlzhw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2852694964</pqid></control><display><type>article</type><title>A Neural Network Model for Estimating Carbon Fluxes in Forest Ecosystems from Remote Sensing Data</title><source>Springer Nature - Complete Springer Journals</source><creator>Rozanov, A. P. ; Gribanov, K. G.</creator><creatorcontrib>Rozanov, A. P. ; Gribanov, K. G.</creatorcontrib><description>Forests are among the main places on Earth where carbon is collected and accumulated. However, instrumental assessment of carbon fluxes is possible only for small areas. When solving the scaling problem, machine learning methods are used, which allow transforming the Earth’s surface reflectance intensities in different spectral ranges into ground-based in situ observations. We suggest a regression neural network model of the multilayer perceptron type for assessment of carbon fluxes. The model is trained on FLUXNET network data for a station located in a boreal coniferous forest (56.4615° N, 32.9221° E). Using the vegetation indices NDVI and EVI measured by the MODIS spectroradiometer onboard the
Aqua
satellite, the air temperature at an altitude of 2 m, and total precipitation as input data, the model estimates the gross primary production (GPP), net ecosystem exchange (NEE), ecosystem respiration (TER), and some other parameters which characterize water and energy fluxes. The statistical assessments for the test dataset show high correlation coefficients (
R
) and Nash–Sutcliffe coefficients (NSE):
R
> 0.9 and NSE ≥ 0.87 for GPP and TER;
R
= 0.4 and NSE = 0.15 for NEE.</description><identifier>ISSN: 1024-8560</identifier><identifier>EISSN: 2070-0393</identifier><identifier>DOI: 10.1134/S1024856023040152</identifier><language>eng</language><publisher>Moscow: Pleiades Publishing</publisher><subject>Air temperature ; Boreal forests ; Carbon ; Coefficients ; Coniferous forests ; Correlation coefficient ; Correlation coefficients ; Earth surface ; Fluxes ; Forest ecosystems ; Ground-based observation ; Hydrosphere ; Lasers ; Machine learning ; Multilayer perceptrons ; Neural networks ; Optical Devices ; Optics ; Photonics ; Physics ; Physics and Astronomy ; Primary production ; Reflectance ; Regression models ; Remote sensing ; Remote Sensing of Atmosphere ; Scaling ; Spectroradiometers ; Statistical analysis ; Underlying Surface ; Vegetation index</subject><ispartof>Atmospheric and oceanic optics, 2023-08, Vol.36 (4), p.323-328</ispartof><rights>Pleiades Publishing, Ltd. 2023. ISSN 1024-8560, Atmospheric and Oceanic Optics, 2023, Vol. 36, No. 4, pp. 323–328. © Pleiades Publishing, Ltd., 2023. Russian Text © The Author(s), 2023, published in Optika Atmosfery i Okeana.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-a367ad97ec395d3990915ee63ce2242f24a33ac51485b8d310ca07590e0421c63</citedby><cites>FETCH-LOGICAL-c316t-a367ad97ec395d3990915ee63ce2242f24a33ac51485b8d310ca07590e0421c63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1134/S1024856023040152$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1134/S1024856023040152$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Rozanov, A. P.</creatorcontrib><creatorcontrib>Gribanov, K. G.</creatorcontrib><title>A Neural Network Model for Estimating Carbon Fluxes in Forest Ecosystems from Remote Sensing Data</title><title>Atmospheric and oceanic optics</title><addtitle>Atmos Ocean Opt</addtitle><description>Forests are among the main places on Earth where carbon is collected and accumulated. However, instrumental assessment of carbon fluxes is possible only for small areas. When solving the scaling problem, machine learning methods are used, which allow transforming the Earth’s surface reflectance intensities in different spectral ranges into ground-based in situ observations. We suggest a regression neural network model of the multilayer perceptron type for assessment of carbon fluxes. The model is trained on FLUXNET network data for a station located in a boreal coniferous forest (56.4615° N, 32.9221° E). Using the vegetation indices NDVI and EVI measured by the MODIS spectroradiometer onboard the
Aqua
satellite, the air temperature at an altitude of 2 m, and total precipitation as input data, the model estimates the gross primary production (GPP), net ecosystem exchange (NEE), ecosystem respiration (TER), and some other parameters which characterize water and energy fluxes. The statistical assessments for the test dataset show high correlation coefficients (
R
) and Nash–Sutcliffe coefficients (NSE):
R
> 0.9 and NSE ≥ 0.87 for GPP and TER;
R
= 0.4 and NSE = 0.15 for NEE.</description><subject>Air temperature</subject><subject>Boreal forests</subject><subject>Carbon</subject><subject>Coefficients</subject><subject>Coniferous forests</subject><subject>Correlation coefficient</subject><subject>Correlation coefficients</subject><subject>Earth surface</subject><subject>Fluxes</subject><subject>Forest ecosystems</subject><subject>Ground-based observation</subject><subject>Hydrosphere</subject><subject>Lasers</subject><subject>Machine learning</subject><subject>Multilayer perceptrons</subject><subject>Neural networks</subject><subject>Optical Devices</subject><subject>Optics</subject><subject>Photonics</subject><subject>Physics</subject><subject>Physics and Astronomy</subject><subject>Primary production</subject><subject>Reflectance</subject><subject>Regression models</subject><subject>Remote sensing</subject><subject>Remote Sensing of Atmosphere</subject><subject>Scaling</subject><subject>Spectroradiometers</subject><subject>Statistical analysis</subject><subject>Underlying Surface</subject><subject>Vegetation index</subject><issn>1024-8560</issn><issn>2070-0393</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp1UE1LAzEQDaJgrf4AbwHPq5PPbY6ltipUBavnJd2dLa27m5qkaP-9WSp4EE8z8D5m3iPkksE1Y0LeLBhwOVIauAAJTPEjMuCQQwbCiGMy6OGsx0_JWQgbAK2MYgNix_QJd942acRP59_po6uwobXzdBriurVx3a3oxPql6-is2X1hoOu0OY8h0mnpwj5EbAOtvWvpC7YuIl1gF3rZrY32nJzUtgl48TOH5G02fZ3cZ_Pnu4fJeJ6VgumYWaFzW5kcS2FUJYwBwxSiFiVyLnnNpRXCloqllMtRJRiUFnJlAEFyVmoxJFcH3613H7v0XLFxO9-lkwUfKa6NNFomFjuwSu9C8FgXW59C-n3BoOibLP40mTT8oAmJ263Q_zr_L_oGDNlzhw</recordid><startdate>20230801</startdate><enddate>20230801</enddate><creator>Rozanov, A. P.</creator><creator>Gribanov, K. G.</creator><general>Pleiades Publishing</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7TN</scope><scope>F1W</scope><scope>H96</scope><scope>L.G</scope></search><sort><creationdate>20230801</creationdate><title>A Neural Network Model for Estimating Carbon Fluxes in Forest Ecosystems from Remote Sensing Data</title><author>Rozanov, A. P. ; Gribanov, K. G.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-a367ad97ec395d3990915ee63ce2242f24a33ac51485b8d310ca07590e0421c63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Air temperature</topic><topic>Boreal forests</topic><topic>Carbon</topic><topic>Coefficients</topic><topic>Coniferous forests</topic><topic>Correlation coefficient</topic><topic>Correlation coefficients</topic><topic>Earth surface</topic><topic>Fluxes</topic><topic>Forest ecosystems</topic><topic>Ground-based observation</topic><topic>Hydrosphere</topic><topic>Lasers</topic><topic>Machine learning</topic><topic>Multilayer perceptrons</topic><topic>Neural networks</topic><topic>Optical Devices</topic><topic>Optics</topic><topic>Photonics</topic><topic>Physics</topic><topic>Physics and Astronomy</topic><topic>Primary production</topic><topic>Reflectance</topic><topic>Regression models</topic><topic>Remote sensing</topic><topic>Remote Sensing of Atmosphere</topic><topic>Scaling</topic><topic>Spectroradiometers</topic><topic>Statistical analysis</topic><topic>Underlying Surface</topic><topic>Vegetation index</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rozanov, A. P.</creatorcontrib><creatorcontrib>Gribanov, K. G.</creatorcontrib><collection>CrossRef</collection><collection>Oceanic Abstracts</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><jtitle>Atmospheric and oceanic optics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rozanov, A. P.</au><au>Gribanov, K. G.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Neural Network Model for Estimating Carbon Fluxes in Forest Ecosystems from Remote Sensing Data</atitle><jtitle>Atmospheric and oceanic optics</jtitle><stitle>Atmos Ocean Opt</stitle><date>2023-08-01</date><risdate>2023</risdate><volume>36</volume><issue>4</issue><spage>323</spage><epage>328</epage><pages>323-328</pages><issn>1024-8560</issn><eissn>2070-0393</eissn><abstract>Forests are among the main places on Earth where carbon is collected and accumulated. However, instrumental assessment of carbon fluxes is possible only for small areas. When solving the scaling problem, machine learning methods are used, which allow transforming the Earth’s surface reflectance intensities in different spectral ranges into ground-based in situ observations. We suggest a regression neural network model of the multilayer perceptron type for assessment of carbon fluxes. The model is trained on FLUXNET network data for a station located in a boreal coniferous forest (56.4615° N, 32.9221° E). Using the vegetation indices NDVI and EVI measured by the MODIS spectroradiometer onboard the
Aqua
satellite, the air temperature at an altitude of 2 m, and total precipitation as input data, the model estimates the gross primary production (GPP), net ecosystem exchange (NEE), ecosystem respiration (TER), and some other parameters which characterize water and energy fluxes. The statistical assessments for the test dataset show high correlation coefficients (
R
) and Nash–Sutcliffe coefficients (NSE):
R
> 0.9 and NSE ≥ 0.87 for GPP and TER;
R
= 0.4 and NSE = 0.15 for NEE.</abstract><cop>Moscow</cop><pub>Pleiades Publishing</pub><doi>10.1134/S1024856023040152</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1024-8560 |
| ispartof | Atmospheric and oceanic optics, 2023-08, Vol.36 (4), p.323-328 |
| issn | 1024-8560 2070-0393 |
| language | eng |
| recordid | cdi_proquest_journals_2852694964 |
| source | Springer Nature - Complete Springer Journals |
| subjects | Air temperature Boreal forests Carbon Coefficients Coniferous forests Correlation coefficient Correlation coefficients Earth surface Fluxes Forest ecosystems Ground-based observation Hydrosphere Lasers Machine learning Multilayer perceptrons Neural networks Optical Devices Optics Photonics Physics Physics and Astronomy Primary production Reflectance Regression models Remote sensing Remote Sensing of Atmosphere Scaling Spectroradiometers Statistical analysis Underlying Surface Vegetation index |
| title | A Neural Network Model for Estimating Carbon Fluxes in Forest Ecosystems from Remote Sensing Data |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T19%3A49%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Neural%20Network%20Model%20for%20Estimating%20Carbon%20Fluxes%20in%20Forest%20Ecosystems%20from%20Remote%20Sensing%20Data&rft.jtitle=Atmospheric%20and%20oceanic%20optics&rft.au=Rozanov,%20A.%20P.&rft.date=2023-08-01&rft.volume=36&rft.issue=4&rft.spage=323&rft.epage=328&rft.pages=323-328&rft.issn=1024-8560&rft.eissn=2070-0393&rft_id=info:doi/10.1134/S1024856023040152&rft_dat=%3Cproquest_cross%3E2852694964%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2852694964&rft_id=info:pmid/&rfr_iscdi=true |