{"id":6712,"date":"2024-09-09T16:44:14","date_gmt":"2024-09-09T14:44:14","guid":{"rendered":"https:\/\/ingenius.ecoledesponts.fr\/?p=6712"},"modified":"2025-07-29T16:15:41","modified_gmt":"2025-07-29T14:15:41","slug":"using-deep-learning-to-monitor-greenhouse-gas-emissions-from-space","status":"publish","type":"post","link":"https:\/\/ingenius.ecoledesponts.fr\/en\/articles\/using-deep-learning-to-monitor-greenhouse-gas-emissions-from-space\/","title":{"rendered":"Using deep learning to monitor greenhouse gas emissions from space"},"content":{"rendered":"\n\n\n
\"\"
Credit: Adobe Stock_Studio-FI<\/figcaption><\/figure>\n\n\n\n

For more than a decade, observing carbon dioxide (CO2<\/sub>) emissions from space has emerged as an essential means of supporting the inventory of these emissions on a national and local scale. The technique should also make it possible to monitor the impact of emission reduction policies as part of the international fight against climate change.<\/p>\n\n\n\n

In recent years, several satellite missions have been launched, providing images of atmospheric CO2<\/sub> concentrations around major sources : large cities, power plants and other industrial sites. Such images make it possible to identify plumes downwind of sources, i.e. areas where concentrations increase as a result of the CO2<\/sub> emitted by these sources, then are transported and dispersed in the atmosphere. CO2<\/sub> emissions can therefore be quantified by processing these images, determining the extent and amplitude of plumes according to meteorological conditions, in particular wind and the associated transport in the atmosphere.
<\/p>\n\n\n\n

Since 2019, the International Space Station has been home to the Orbiting Carbon Observatory-3 instrument1<\/a><\/sup>. Its \u201cSnapshot Area Maps\u201d (SAM) mode has already provided several thousand images focused on specific sources.  The Copernicus Anthropogenic Carbon Dioxide Monitoring (CO2M) mission of the European Union and the European Space Agency, scheduled for launch in 2026, will be dedicated to the continuous generation of larger images (based on a wider field of observation).<\/p>\n\n\n\n

<\/p>\n\n\n\n

\"\"
Figure 1: XCO2<\/sub> hotspot measured by OCO-3 on June 26, 2021 and centered around the Tuoketo power plant.<\/figcaption><\/figure>\n\n\n\n

However, quantifying CO2<\/sub> emissions from large local sources using satellite images of their plumes poses significant scientific and technical challenges. Spatial variation in CO2<\/sub> concentrations is not only linked to these plumes. They also reflect natural emissions from ecosystems and those from human activities, such as cities or remote industrial sites. The plume studied is superimposed on this hotspot, which may include complex variations. For example, CO2<\/sub> emissions from a power plant in Germany can create CO2<\/sub> variations in images centered on Paris. Finally, the proportional relationship between emissions and plume amplitude is directly linked to local atmospheric transport conditions (notably the wind field) at the time the satellite passes by, conditions which are not perfectly known. This is why the application of conventional image analysis techniques (for plume detection and source quantification) is based on approximations that generate a high degree of uncertainty in the results. <\/p>\n\n\n\n

However, it would appear that the image analysis problem can be managed using a deep learning approach such as neural networks. The learning algorithm can be trained using synthetic images generated with atmospheric plume models from known sources, before being applied to real images.  Using massive amounts of data, these AI methods can learn to identify characteristic plume structures on a CO2<\/sub> map, as well as the relationship between these structures and emissions from the source causing the plume.<\/p>\n\n\n\n


We explored this concept, first testing it on synthetic data with known CO2<\/sub> source emissions, then applying it to data from the OCO-3 satellite. For example, from the CO2<\/sub> hotspot centered around the Parish Generating Station measured by OCO-3, our neural network identified the plume emitted by the power station and deduced an estimate of the source\u2019s emissions consistent with energy industry estimates.<\/p>\n\n\n\n

\"\"
Figure 2: XCO2<\/sub> hotspot measured by OCO-3 on December 27, 2021 and centered around the Parish Generating Station, after post-treatment (left), and identification of the CO2<\/sub> plume from which Parish emissions will be estimated (right).<\/figcaption><\/figure>\n\n\n\n
\n

Quantification of CO2<\/sub> hotspot emissions from OCO-3 SAM CO2<\/sub> satellite images using deep learning methods, Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Gr\u00e9goire Broquet, Gerrit Kuhlmann, and Marc Bocquet<\/p>\n<\/div>\n\n\n

  1. Instrument developed by the National Aeronautics and Space Administration -NASA- and the Jet Propulsion Laboratory -JPL. \u21a9\ufe0e<\/a><\/li><\/ol>","protected":false},"excerpt":{"rendered":"

    For more than a decade, observing carbon dioxide (CO2) emissions from space has emerged as an essential means of supporting […]<\/p>\n","protected":false},"author":6,"featured_media":6734,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_related_content_post":[],"_related_content_subject":[937],"_related_content_author":[6709,6720,6743],"_related_content_category":[1720],"_related_content_folder":[6755],"_excerpt":"","_duration":3,"_manual_duration":false,"footnotes":"[{\"content\":\"Instrument developed by the National Aeronautics and Space Administration -NASA- and the Jet Propulsion Laboratory -JPL.\",\"id\":\"ec26ddbd-bf9d-44fc-a4d6-d0f0a4d9c3d7\"}]"},"article-types":[13,27],"class_list":["post-6712","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","article-types-article","article-types-folder"],"has_blocks":true,"block_data":[{"blockName":"enpc\/excerpt","attrs":{"lock":[],"metadata":[],"className":"","style":""},"innerBlocks":[],"innerHTML":"","innerContent":[],"rendered":""},{"blockName":"core\/image","attrs":{"id":6748,"sizeSlug":"large","linkDestination":"none","align":"wide","blob":"","url":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2024\/09\/Ph-Adobe-Stock-Studio-FI-1024x576.jpg","alt":"","caption":"Credit: Adobe Stock_Studio-FI","lightbox":[],"title":"","href":"","rel":"","linkClass":"","width":"","height":"","aspectRatio":"","scale":"","linkTarget":"","lock":[],"metadata":[],"className":"wp-block-image alignwide size-large","style":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    \"\"
    Credit: Adobe Stock_Studio-FI<\/figcaption><\/figure>\n","innerContent":["\n
    \"\"
    Credit: Adobe Stock_Studio-FI<\/figcaption><\/figure>\n"],"rendered":"\n
    \"\"
    Credit: Adobe Stock_Studio-FI<\/figcaption><\/figure>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"For more than a decade, observing carbon dioxide (CO2) emissions from space has emerged as an essential means of supporting the inventory of these emissions on a national and local scale. The technique should also make it possible to monitor the impact of emission reduction policies as part of the international fight against climate change.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    For more than a decade, observing carbon dioxide (CO2<\/sub>) emissions from space has emerged as an essential means of supporting the inventory of these emissions on a national and local scale. The technique should also make it possible to monitor the impact of emission reduction policies as part of the international fight against climate change.<\/p>\n","innerContent":["\n

    For more than a decade, observing carbon dioxide (CO2<\/sub>) emissions from space has emerged as an essential means of supporting the inventory of these emissions on a national and local scale. The technique should also make it possible to monitor the impact of emission reduction policies as part of the international fight against climate change.<\/p>\n"],"rendered":"\n

    For more than a decade, observing carbon dioxide (CO2<\/sub>) emissions from space has emerged as an essential means of supporting the inventory of these emissions on a national and local scale. The technique should also make it possible to monitor the impact of emission reduction policies as part of the international fight against climate change.<\/p>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"In recent years, several satellite missions have been launched, providing images of atmospheric CO2 concentrations around major sources : large cities, power plants and other industrial sites. Such images make it possible to identify plumes downwind of sources, i.e. areas where concentrations increase as a result of the CO2 emitted by these sources, then are transported and dispersed in the atmosphere. CO2 emissions can therefore be quantified by processing these images, determining the extent and amplitude of plumes according to meteorological conditions, in particular wind and the associated transport in the atmosphere.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    In recent years, several satellite missions have been launched, providing images of atmospheric CO2<\/sub> concentrations around major sources : large cities, power plants and other industrial sites. Such images make it possible to identify plumes downwind of sources, i.e. areas where concentrations increase as a result of the CO2<\/sub> emitted by these sources, then are transported and dispersed in the atmosphere. CO2<\/sub> emissions can therefore be quantified by processing these images, determining the extent and amplitude of plumes according to meteorological conditions, in particular wind and the associated transport in the atmosphere.
    <\/p>\n","innerContent":["\n

    In recent years, several satellite missions have been launched, providing images of atmospheric CO2<\/sub> concentrations around major sources : large cities, power plants and other industrial sites. Such images make it possible to identify plumes downwind of sources, i.e. areas where concentrations increase as a result of the CO2<\/sub> emitted by these sources, then are transported and dispersed in the atmosphere. CO2<\/sub> emissions can therefore be quantified by processing these images, determining the extent and amplitude of plumes according to meteorological conditions, in particular wind and the associated transport in the atmosphere.
    <\/p>\n"],"rendered":"\n

    In recent years, several satellite missions have been launched, providing images of atmospheric CO2<\/sub> concentrations around major sources : large cities, power plants and other industrial sites. Such images make it possible to identify plumes downwind of sources, i.e. areas where concentrations increase as a result of the CO2<\/sub> emitted by these sources, then are transported and dispersed in the atmosphere. CO2<\/sub> emissions can therefore be quantified by processing these images, determining the extent and amplitude of plumes according to meteorological conditions, in particular wind and the associated transport in the atmosphere.
    <\/p>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"Since 2019, the International Space Station has been home to the Orbiting Carbon Observatory-3 instrument1.\u00a0Its \u201cSnapshot Area Maps\u201d (SAM) mode has already provided several thousand images focused on specific sources.\u00a0 The Copernicus Anthropogenic Carbon Dioxide Monitoring (CO2M) mission of the European Union and the European Space Agency, scheduled for launch in 2026, will be dedicated to the continuous generation of larger images (based on a wider field of observation).","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    Since 2019, the International Space Station has been home to the Orbiting Carbon Observatory-3 instrument1<\/a><\/sup>. Its \u201cSnapshot Area Maps\u201d (SAM) mode has already provided several thousand images focused on specific sources.  The Copernicus Anthropogenic Carbon Dioxide Monitoring (CO2M) mission of the European Union and the European Space Agency, scheduled for launch in 2026, will be dedicated to the continuous generation of larger images (based on a wider field of observation).<\/p>\n","innerContent":["\n

    Since 2019, the International Space Station has been home to the Orbiting Carbon Observatory-3 instrument1<\/a><\/sup>. Its \u201cSnapshot Area Maps\u201d (SAM) mode has already provided several thousand images focused on specific sources.  The Copernicus Anthropogenic Carbon Dioxide Monitoring (CO2M) mission of the European Union and the European Space Agency, scheduled for launch in 2026, will be dedicated to the continuous generation of larger images (based on a wider field of observation).<\/p>\n"],"rendered":"\n

    Since 2019, the International Space Station has been home to the Orbiting Carbon Observatory-3 instrument1<\/a><\/sup>. Its \u201cSnapshot Area Maps\u201d (SAM) mode has already provided several thousand images focused on specific sources.  The Copernicus Anthropogenic Carbon Dioxide Monitoring (CO2M) mission of the European Union and the European Space Agency, scheduled for launch in 2026, will be dedicated to the continuous generation of larger images (based on a wider field of observation).<\/p>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    <\/p>\n","innerContent":["\n

    <\/p>\n"],"rendered":"\n

    <\/p>\n"},{"blockName":"core\/image","attrs":{"id":6715,"sizeSlug":"large","linkDestination":"none","blob":"","url":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2024\/09\/2024_DDAP_outilsmediation-8-1024x576.jpg","alt":"","caption":"Figure 1: XCO2 hotspot measured by OCO-3 on June 26, 2021 and centered around the Tuoketo power plant.","lightbox":[],"title":"","href":"","rel":"","linkClass":"","width":"","height":"","aspectRatio":"","scale":"","linkTarget":"","lock":[],"metadata":[],"align":"","className":"wp-block-image size-large","style":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    \"\"
    Figure 1: XCO2<\/sub> hotspot measured by OCO-3 on June 26, 2021 and centered around the Tuoketo power plant.<\/figcaption><\/figure>\n","innerContent":["\n
    \"\"
    Figure 1: XCO2<\/sub> hotspot measured by OCO-3 on June 26, 2021 and centered around the Tuoketo power plant.<\/figcaption><\/figure>\n"],"rendered":"\n
    \"\"
    Figure 1: XCO2<\/sub> hotspot measured by OCO-3 on June 26, 2021 and centered around the Tuoketo power plant.<\/figcaption><\/figure>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"However, quantifying CO2 emissions from large local sources using satellite images of their plumes poses significant scientific and technical challenges. Spatial variation in CO2 concentrations is not only linked to these plumes. They also reflect natural emissions from ecosystems and those from human activities, such as cities or remote industrial sites. The plume studied is superimposed on this hotspot, which may include complex variations. For example, CO2 emissions from a power plant in Germany can create CO2 variations in images centered on Paris. Finally, the proportional relationship between emissions and plume amplitude is directly linked to local atmospheric transport conditions (notably the wind field) at the time the satellite passes by, conditions which are not perfectly known. This is why the application of conventional image analysis techniques (for plume detection and source quantification) is based on approximations that generate a high degree of uncertainty in the results.\u00a0","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    However, quantifying CO2<\/sub> emissions from large local sources using satellite images of their plumes poses significant scientific and technical challenges. Spatial variation in CO2<\/sub> concentrations is not only linked to these plumes. They also reflect natural emissions from ecosystems and those from human activities, such as cities or remote industrial sites. The plume studied is superimposed on this hotspot, which may include complex variations. For example, CO2<\/sub> emissions from a power plant in Germany can create CO2<\/sub> variations in images centered on Paris. Finally, the proportional relationship between emissions and plume amplitude is directly linked to local atmospheric transport conditions (notably the wind field) at the time the satellite passes by, conditions which are not perfectly known. This is why the application of conventional image analysis techniques (for plume detection and source quantification) is based on approximations that generate a high degree of uncertainty in the results. <\/p>\n","innerContent":["\n

    However, quantifying CO2<\/sub> emissions from large local sources using satellite images of their plumes poses significant scientific and technical challenges. Spatial variation in CO2<\/sub> concentrations is not only linked to these plumes. They also reflect natural emissions from ecosystems and those from human activities, such as cities or remote industrial sites. The plume studied is superimposed on this hotspot, which may include complex variations. For example, CO2<\/sub> emissions from a power plant in Germany can create CO2<\/sub> variations in images centered on Paris. Finally, the proportional relationship between emissions and plume amplitude is directly linked to local atmospheric transport conditions (notably the wind field) at the time the satellite passes by, conditions which are not perfectly known. This is why the application of conventional image analysis techniques (for plume detection and source quantification) is based on approximations that generate a high degree of uncertainty in the results. <\/p>\n"],"rendered":"\n

    However, quantifying CO2<\/sub> emissions from large local sources using satellite images of their plumes poses significant scientific and technical challenges. Spatial variation in CO2<\/sub> concentrations is not only linked to these plumes. They also reflect natural emissions from ecosystems and those from human activities, such as cities or remote industrial sites. The plume studied is superimposed on this hotspot, which may include complex variations. For example, CO2<\/sub> emissions from a power plant in Germany can create CO2<\/sub> variations in images centered on Paris. Finally, the proportional relationship between emissions and plume amplitude is directly linked to local atmospheric transport conditions (notably the wind field) at the time the satellite passes by, conditions which are not perfectly known. This is why the application of conventional image analysis techniques (for plume detection and source quantification) is based on approximations that generate a high degree of uncertainty in the results. <\/p>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"However, it would appear that the image analysis problem can be managed using a deep learning approach such as neural networks. The learning algorithm can be trained using synthetic images generated with atmospheric plume models from known sources, before being applied to real images. \u00a0Using massive amounts of data, these AI methods can learn to identify characteristic plume structures on a CO2 map, as well as the relationship between these structures and emissions from the source causing the plume.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    However, it would appear that the image analysis problem can be managed using a deep learning approach such as neural networks. The learning algorithm can be trained using synthetic images generated with atmospheric plume models from known sources, before being applied to real images.  Using massive amounts of data, these AI methods can learn to identify characteristic plume structures on a CO2<\/sub> map, as well as the relationship between these structures and emissions from the source causing the plume.<\/p>\n","innerContent":["\n

    However, it would appear that the image analysis problem can be managed using a deep learning approach such as neural networks. The learning algorithm can be trained using synthetic images generated with atmospheric plume models from known sources, before being applied to real images.  Using massive amounts of data, these AI methods can learn to identify characteristic plume structures on a CO2<\/sub> map, as well as the relationship between these structures and emissions from the source causing the plume.<\/p>\n"],"rendered":"\n

    However, it would appear that the image analysis problem can be managed using a deep learning approach such as neural networks. The learning algorithm can be trained using synthetic images generated with atmospheric plume models from known sources, before being applied to real images.  Using massive amounts of data, these AI methods can learn to identify characteristic plume structures on a CO2<\/sub> map, as well as the relationship between these structures and emissions from the source causing the plume.<\/p>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"We explored this concept, first testing it on synthetic data with known CO2 source emissions, then applying it to data from the OCO-3 satellite. For example, from the CO2 hotspot centered around the Parish Generating Station measured by OCO-3, our neural network identified the plume emitted by the power station and deduced an estimate of the source\u2019s emissions consistent with energy industry estimates.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n


    We explored this concept, first testing it on synthetic data with known CO2<\/sub> source emissions, then applying it to data from the OCO-3 satellite. For example, from the CO2<\/sub> hotspot centered around the Parish Generating Station measured by OCO-3, our neural network identified the plume emitted by the power station and deduced an estimate of the source\u2019s emissions consistent with energy industry estimates.<\/p>\n","innerContent":["\n


    We explored this concept, first testing it on synthetic data with known CO2<\/sub> source emissions, then applying it to data from the OCO-3 satellite. For example, from the CO2<\/sub> hotspot centered around the Parish Generating Station measured by OCO-3, our neural network identified the plume emitted by the power station and deduced an estimate of the source\u2019s emissions consistent with energy industry estimates.<\/p>\n"],"rendered":"\n


    We explored this concept, first testing it on synthetic data with known CO2<\/sub> source emissions, then applying it to data from the OCO-3 satellite. For example, from the CO2<\/sub> hotspot centered around the Parish Generating Station measured by OCO-3, our neural network identified the plume emitted by the power station and deduced an estimate of the source\u2019s emissions consistent with energy industry estimates.<\/p>\n"},{"blockName":"core\/image","attrs":{"id":6717,"sizeSlug":"large","linkDestination":"none","blob":"","url":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2024\/09\/2024_DDAP_outilsmediation-9-1024x576.jpg","alt":"","caption":"Figure 2: XCO2 hotspot measured by OCO-3 on December 27, 2021 and centered around the Parish Generating Station, after post-treatment (left), and identification of the CO2 plume from which Parish emissions will be estimated (right).","lightbox":[],"title":"","href":"","rel":"","linkClass":"","width":"","height":"","aspectRatio":"","scale":"","linkTarget":"","lock":[],"metadata":[],"align":"","className":"wp-block-image size-large","style":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    \"\"
    Figure 2: XCO2<\/sub> hotspot measured by OCO-3 on December 27, 2021 and centered around the Parish Generating Station, after post-treatment (left), and identification of the CO2<\/sub> plume from which Parish emissions will be estimated (right).<\/figcaption><\/figure>\n","innerContent":["\n
    \"\"
    Figure 2: XCO2<\/sub> hotspot measured by OCO-3 on December 27, 2021 and centered around the Parish Generating Station, after post-treatment (left), and identification of the CO2<\/sub> plume from which Parish emissions will be estimated (right).<\/figcaption><\/figure>\n"],"rendered":"\n
    \"\"
    Figure 2: XCO2<\/sub> hotspot measured by OCO-3 on December 27, 2021 and centered around the Parish Generating Station, after post-treatment (left), and identification of the CO2<\/sub> plume from which Parish emissions will be estimated (right).<\/figcaption><\/figure>\n"},{"blockName":"enpc\/accordion","attrs":{"title":"REFERENCE","lock":[],"metadata":[],"className":"wp-block-enpc-accordion","style":""},"innerBlocks":[{"blockName":"core\/paragraph","attrs":{"align":"","content":" Quantification of CO2 hotspot emissions from OCO-3 SAM CO2 satellite images using deep learning methods, Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Gr\u00e9goire Broquet, Gerrit Kuhlmann, and Marc Bocquet","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

    Quantification of CO2<\/sub> hotspot emissions from OCO-3 SAM CO2<\/sub> satellite images using deep learning methods, Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Gr\u00e9goire Broquet, Gerrit Kuhlmann, and Marc Bocquet<\/p>\n","innerContent":["\n

    Quantification of CO2<\/sub> hotspot emissions from OCO-3 SAM CO2<\/sub> satellite images using deep learning methods, Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Gr\u00e9goire Broquet, Gerrit Kuhlmann, and Marc Bocquet<\/p>\n"],"rendered":"\n

    Quantification of CO2<\/sub> hotspot emissions from OCO-3 SAM CO2<\/sub> satellite images using deep learning methods, Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Gr\u00e9goire Broquet, Gerrit Kuhlmann, and Marc Bocquet<\/p>\n"}],"innerHTML":"\n

    <\/div>\n","innerContent":["\n
    ",null,"<\/div>\n"],"rendered":"\n
    \n

    Quantification of CO2<\/sub> hotspot emissions from OCO-3 SAM CO2<\/sub> satellite images using deep learning methods, Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Gr\u00e9goire Broquet, Gerrit Kuhlmann, and Marc Bocquet<\/p>\n<\/div>\n"},{"blockName":"core\/footnotes","attrs":{"lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","fontSize":"","fontFamily":"","borderColor":""},"innerBlocks":[],"innerHTML":"","innerContent":[],"rendered":""}],"seo":{"title":"Using deep learning to monitor greenhouse gas emissions from space"},"media":{"img":"\"\"","src":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2024\/09\/2024_DDAP_outilsmediation-11.jpg"},"url":"\/en\/articles\/using-deep-learning-to-monitor-greenhouse-gas-emissions-from-space\/","related":{"post":[],"author":[{"title":"Marc Bocquet","url":"\/en\/authors\/marc-bocquet\/","id":"6709","media":"\"\"","slug":"marc-bocquet"},{"title":"Joffrey Dumont Le Brazidec","url":"\/en\/authors\/joffrey-dumont-le-brazidec\/","id":"6720","media":"\"\"","slug":"joffrey-dumont-le-brazidec"},{"title":"Gr\u00e9goire Broquet","url":"\/en\/authors\/gregoire-broquet\/","id":"6743","media":"\"\"","slug":"gregoire-broquet"}],"subject":[{"title":"Energy, Ecology & Climate","url":"\/en\/subjects\/energy-ecology-climate\/","id":"937","media":"\"\"","slug":"energy-ecology-climate"}],"category":[{"title":"Article collection","url":"\/en\/articles\/category\/dossier\/","id":"1720","media":"","slug":"dossier","_related_post_type":"folder"}],"folder":[{"title":"Space: a unique platform for scientific observation and experimentation","url":"\/en\/folders\/space-a-unique-platform-for-scientific-observation-and-experimentation\/","id":"6755","media":"\"\"","slug":"space-a-unique-platform-for-scientific-observation-and-experimentation"}]},"translated":"https:\/\/ingenius.ecoledesponts.fr\/articles\/surveiller-les-emissions-de-gaz-a-effet-de-serre-depuis-lespace-grace-a-lapprentissage-profond\/","icon":"icon-article","duration":"3","custom_excerpt":"","duration_type":"","_links":{"self":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts\/6712","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/comments?post=6712"}],"version-history":[{"count":5,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts\/6712\/revisions"}],"predecessor-version":[{"id":8987,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts\/6712\/revisions\/8987"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/media\/6734"}],"wp:attachment":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/media?parent=6712"}],"wp:term":[{"taxonomy":"article-types","embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/article-types?post=6712"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}