[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121347-en":3,"doc-seo-121347-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121347,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","High-resolution greenhouse gas flux inversions using a machine learning surrogate model for atmospheric transport","Quantifying greenhouse gas (GHG) emissions is essential for projecting climate and evaluating environmental policy. Inferring emissions from atmospheric observations typically relies on computationally expensive source–receptor relationships (“footprints”). This work presents a faster GHG flux inversion framework using a machine learning emulator for atmospheric transport (FootNet) as a surrogate for a full-physics model, producing ~1 km footprints and improving deep-learning architecture for inversion performance. FootNet-based posterior fluxes agree with STILT results while requiring only meteorology, GHG measurements, and prior fluxes.","Atmos. Chem. Phys., 25, 5159–5174, 2025 [https://doi.org/10.5194/acp-25-5159-2025](https://doi.org/10.5194/acp-25-5159-2025)[ ](https://doi.org/10.5194/acp-25-5159-2025)© Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nHigh-resolution greenhouse gas flux inversions using a machine learning surrogate model for atmospheric transport  \nNikhil Dadheech 1 ;􀀔 , Tai-Long He1,a ;􀀔 , and Alexander J. Turner 1  \n1Department of Atmospheric and Climate Science, University of Washington, Seattle, WA, USA anow at: School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA  \n􀀔 These authors contributed equally to this work.  \nCorrespondence: Alexander J. Turner ([turneraj@uw.edu](turneraj@uw.edu))  \nReceived: 20 September 2024 – Discussion started: 26 September 2024  \nRevised: 7 March 2025 – Accepted: 9 March 2025 – Published: 21 May 2025  \nAbstract. Quantifying greenhouse gas (GHG) emissions is critically important for projecting future climate and assessing the impact of environmental policy. Estimating GHG emissions using atmospheric observations is typically done using source–receptor relationships (i.e., “footprints”) . Constructing these footprints can be computationally expensive and is rapidly becoming a computational bottleneck for studying GHG fluxes at highspatio-temporal resolution using dense observations. Here, we demonstrate a computationally efficient GHG flux inversion framework using a machine learning emulator for atmospheric transport (FootNet) as a surrogate for the full-physics model. The footprints generated by FootNet are at approximately 1 km resolution. We update the architecture of the deep-learning model to improve the performance in a GHG flux inversion. We find that the posterior fluxes estimated with FootNet footprints are in good agreement with the posterior fluxes estimated with STILT footprints. We observe that the more simplistic representation of transport in the machine learning model helps to mitigate transport errors. This flux inversion using a machine learning surrogate model requires only meteorological data, GHG measurements, and prior fluxes. Constructing footprints using FootNet is 650 times faster than the full-physics atmospheric transport model on similar hardware. This speedup allows for the computation of footprints “on the fly” during the GHG flux inversion (i.e., computed as needed, rather than archiving for future use) and makes near-real-time emission monitoring computationally possible. This work alleviates a major computational bottleneck with inferring GHG fluxes with next-generation dense observing systems.  \n1 Introduction  \nCarbon dioxide (CO 2) and methane are the two most powerful greenhouse gases (GHGs) . Together, they account for more than 85 % of the total GHG radiative forcing since preindustrial times (IPCC, 2023) . As such, it is important to quantify the GHG sources and sinks in order to project future climate. Near-real-time quantification of GHG emissions is key to identifying the intermittent super-emitters, which often dominate the emission budget. However, the large computational and storage costs associated with full-physics at-  \nmospheric transport models in the current inversion framework limit our ability to perform near-real-time emissions monitoring from urban to global scales (Roten et al., 2021 ; Varon et al., 2023 ; Cartwright et al., 2023 ; Fillola et al., 2023 ; Nayagam et al., 2023 ; Steiner et al., 2024 ; Janardanan et al., 2024) . Here, we use FootNet (He et al., 2025), a computationally efficient deep-learning model, to emulate a fullphysics atmospheric transport model and conduct GHG flux inversions. This work shows the feasibility of using a machine learning (ML) emulator for near-real-time computation of source–receptor relationships and to infer hourly GHG  \nPublished by Copernicus Publications on behalf of the European Geosciences Union.  \nResearch article  \n5160 N. Dadheech et al.: Hi","cbCaijT4NqNU2aL2","https://ap.wps.com/l/cbCaijT4NqNU2aL2","pdf",6679587,1,16,"English","en",105,"# Abstract\n# Introduction\n## Motivation for near-real-time GHG quantification\n## Computational bottleneck in footprint generation\n## Dense observing systems and footprint concept","[{\"question\":\"What problem does the paper address in GHG flux inversions?\",\"answer\":\"The paper targets the high computational and storage cost of generating atmospheric transport footprints, which limits near-real-time monitoring at high spatio-temporal resolution.\"},{\"question\":\"How does FootNet improve the flux inversion workflow?\",\"answer\":\"FootNet emulates the full-physics atmospheric transport model to generate footprints at ~1 km resolution, enabling much faster footprint computation and reducing the transport-related bottleneck.\"},{\"question\":\"What data inputs are required for the FootNet-based inversion?\",\"answer\":\"The method requires meteorological data, GHG measurements, and prior fluxes.\"}]","High-resolution greenhouse gas flux inversions using a machine learning surrogate model for atmospheric transport | PDF",1785735178,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"high-resolution-greenhouse-gas-flux-inversions-using-a-machine-learning-surrogate-model-for-atmospheric-transport","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/high-resolution-greenhouse-gas-flux-inversions-using-a-machine-learning-surrogate-model-for-atmospheric-transport/121347/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in GHG flux inversions?","Question",{"text":75,"@type":76},"The paper targets the high computational and storage cost of generating atmospheric transport footprints, which limits near-real-time monitoring at high spatio-temporal resolution.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does FootNet improve the flux inversion workflow?",{"text":80,"@type":76},"FootNet emulates the full-physics atmospheric transport model to generate footprints at ~1 km resolution, enabling much faster footprint computation and reducing the transport-related bottleneck.",{"name":82,"@type":73,"acceptedAnswer":83},"What data inputs are required for the FootNet-based inversion?",{"text":84,"@type":76},"The method requires meteorological data, GHG measurements, and prior fluxes.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]