{"id":"https://openalex.org/W7164988825","doi":"https://doi.org/10.48550/arxiv.2606.17413","title":"Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows","display_name":"Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7164988825","doi":"https://doi.org/10.48550/arxiv.2606.17413"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.17413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138773974","display_name":"Alejandro Calle-Saldarriaga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Calle-Saldarriaga, Alejandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121190636","display_name":"Felix Jimenez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jimenez, Felix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138816332","display_name":"Jack Grosskreuz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grosskreuz, Jack","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138775943","display_name":"Jiazheng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiazheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138762760","display_name":"Jonathan Hobbs","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hobbs, Jonathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038477614","display_name":"Matthias Katzfu\u00df","orcid":"https://orcid.org/0000-0001-7496-7992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katzfuss, Matthias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11588","display_name":"Atmospheric and Environmental Gas Dynamics","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11588","display_name":"Atmospheric and Environmental Gas Dynamics","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11111","display_name":"Spectroscopy and Laser Applications","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11302","display_name":"CO2 Sequestration and Geologic Interactions","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5927000045776367},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48089998960494995},{"id":"https://openalex.org/keywords/laplaces-method","display_name":"Laplace's method","score":0.4724000096321106},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.4668000042438507},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4643000066280365},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.460099995136261},{"id":"https://openalex.org/keywords/laplace-transform","display_name":"Laplace transform","score":0.4593999981880188},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4447000026702881},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4174000024795532}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5321000218391418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5228000283241272},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C22243797","wikidata":"https://www.wikidata.org/wiki/Q2058297","display_name":"Laplace's method","level":3,"score":0.4724000096321106},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C97937538","wikidata":"https://www.wikidata.org/wiki/Q199691","display_name":"Laplace transform","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4174000024795532},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4120999872684479},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C147947694","wikidata":"https://www.wikidata.org/wiki/Q837552","display_name":"Numerical weather prediction","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.17413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Space-based":[0],"monitoring":[1],"of":[2,25,60,105,140,146,216],"atmospheric":[3],"carbon":[4,13],"dioxide":[5],"(CO2)":[6],"is":[7,138,227],"essential":[8],"for":[9,63,166],"constraining":[10],"the":[11,58,106,214,217],"global":[12],"budget.":[14],"NASA's":[15],"Orbiting":[16],"Carbon":[17],"Observatory-2":[18],"(OCO-2)":[19],"estimates":[20,103],"column-averaged":[21],"dry-air":[22],"mole":[23],"fractions":[24],"CO2":[26,108],"(XCO2)":[27],"using":[28,73,97,114],"high-resolution":[29],"spectra.":[30],"However,":[31],"current":[32],"operational":[33,132,233],"retrieval":[34],"algorithms":[35],"are":[36],"computationally":[37],"expensive":[38],"and":[39,69,102,121,197],"do":[40],"not":[41],"properly":[42],"quantify":[43],"uncertainties.":[44],"We":[45,178],"present":[46],"a":[47,74,98,228],"novel":[48],"deep":[49,225],"learning":[50,226],"framework":[51,206],"that":[52,158,223],"addresses":[53],"these":[54],"challenges.":[55],"Due":[56],"to":[57,81,131,184],"difficulties":[59],"ground-truth":[61],"data":[62,148],"real":[64],"satellite":[65],"observations,":[66],"we":[67],"develop":[68],"validate":[70],"our":[71,163,205],"approach":[72,125],"high-fidelity":[75],"simulation":[76],"dataset.":[77],"This":[78],"dataset,":[79],"created":[80],"support":[82],"OCO-2":[83],"uncertainty":[84,195],"quantification":[85],"(UQ),":[86],"incorporates":[87],"realistic":[88],"forward":[89],"model":[90,161],"errors.":[91],"Our":[92,124],"architecture":[93],"encodes":[94],"spectral":[95],"bands":[96],"multi-branch":[99],"neural":[100],"network":[101],"posteriors":[104],"full":[107],"column":[109],"or":[110],"desired":[111],"summaries":[112],"thereof":[113],"two":[115],"scalable":[116],"UQ":[117],"methods:":[118],"Laplace":[119],"approximations":[120],"normalizing":[122,203],"flows.":[123],"has":[126],"five":[127],"key":[128],"advantages":[129],"relative":[130],"\"full-physics\"":[133],"solvers:":[134],"(1)":[135],"Amortization:":[136],"Inference":[137],"orders":[139],"magnitude":[141],"faster,":[142],"enabling":[143],"real-time":[144],"processing":[145,234],"massive":[147],"streams;":[149],"(2)":[150],"Model":[151],"error":[152],"robustness:":[153],"By":[154],"training":[155],"on":[156],"simulations":[157],"explicitly":[159],"include":[160],"discrepancies,":[162],"method":[164],"accounts":[165],"systematic":[167],"errors":[168],"often":[169],"neglected":[170],"by":[171],"standard":[172],"inversions;":[173],"(3)":[174],"Point":[175],"estimate":[176],"accuracy:":[177],"achieve":[179],"superior":[180],"predictive":[181],"accuracy":[182],"compared":[183],"baseline":[185],"methods;":[186],"(4)":[187],"Improved":[188],"UQ:":[189],"The":[190],"probabilistic":[191],"outputs":[192],"yield":[193],"better-calibrated":[194],"estimates;":[196],"(5)":[198],"Non-Gaussian":[199],"posteriors:":[200],"When":[201],"utilizing":[202],"flows,":[204],"successfully":[207],"models":[208],"complex,":[209],"asymmetric":[210],"posterior":[211],"distributions,":[212],"overcoming":[213],"limitations":[215],"Gaussian":[218],"assumption.":[219],"These":[220],"results":[221],"suggest":[222],"simulation-based":[224],"viable":[229],"path":[230],"toward":[231],"next-generation":[232],"systems.":[235]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-18T00:00:00"}