{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T03:14:30Z","timestamp":1788146070304,"version":"build-2803163510"},"reference-count":48,"publisher":"American Geophysical Union (AGU)","issue":"5","license":[{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["agupubs.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Geophysical Research: Machine Learning and Computation"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Geostationary hyperspectral infrared sounders provide hourly observations of the atmospheric composition. However, the conventional optimal estimation method (OEM)\u2010based retrieval algorithm requires computationally expensive radiative transfer calculations and inverse modeling, making it difficult to monitor in real time. This study presents a machine learning (ML) framework that is trained using a small subset of OEM retrievals to retrieve both column density and associated averaging kernel (AK) information. This framework was applied to predict the columns of ammonia (NH\n                    <jats:sub>3<\/jats:sub>\n                    ) and formic acid (HCOOH) and the carbon monoxide (CO) profile over East Asia, using data from the Geostationary Interferometric Infrared Sounder (GIIRS) on the FengYun\u20104B meteorological satellite. The results show that ML\u2010GIIRS reproduces OEM\u2010GIIRS retrievals with high accuracy (\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    \u00a0&gt;\u00a00.9 for CO,\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    \u00a0&gt;\u00a00.8 for NH\n                    <jats:sub>3<\/jats:sub>\n                    and HCOOH), captures diurnal and seasonal variability and effectively recovers AK information, while achieving computation efficiency that is three orders of magnitude faster. However, prediction performance is slightly lower at night due to the reduced thermal contrast, which reduces detection sensitivity. Furthermore, the results demonstrate that the AK information, which quantifies the vertical sensitivity of the observing system, can be accurately predicted by the ML framework. Comparison with model simulations incorporating AK corrections shows that the ML\u2010GIIRS results exhibit negligible bias. Including AK prediction extends ML retrievals beyond column density estimates and supports the use of space\u2010borne hyperspectral infrared data for more physically interpretable applications. This developed ML framework has great potential to support near\u2010real\u2010time monitoring of air pollutants from geostationary hyperspectral infrared sounders.\n                  <\/jats:p>","DOI":"10.1029\/2026jh001562","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T02:41:45Z","timestamp":1788144105000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Machine Learning Framework for Retrieving Atmospheric Composition and the Associated Averaging Kernels From a Geostationary Hyperspectral Infrared Sounder"],"prefix":"10.1029","volume":"3","author":[{"given":"Sirui","family":"Wu","sequence":"first","affiliation":[{"name":"School of Earth and Space Sciences Peking University  Beijing China"},{"name":"Faculty of Science National University of Singapore  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiancong","family":"Hua","sequence":"additional","affiliation":[{"name":"School of Earth and Space Sciences Peking University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0688-0075","authenticated-orcid":false,"given":"Runyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Earth and Space Sciences Peking University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8261-621X","authenticated-orcid":false,"given":"Mengya","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Earth and Space Sciences Peking University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0008-6508","authenticated-orcid":false,"given":"Zhao\u2010Cheng","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Earth and Space Sciences Peking University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"13","published-online":{"date-parts":[[2026,8,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2005.863716"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS\u201087\u20107\u2010911"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1029\/94jd00907"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u201016\u20105009\u20102023"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u20109\u20106041\u20102009"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u20103\u20101495\u20102003"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","unstructured":"Copernicus Atmosphere Monitoring Service. (2026).CAMS global reanalysis (EAC4)[Dataset].Copernicus Atmosphere Monitoring Service (CAMS) Atmosphere Data Store.https:\/\/doi.org\/10.24381\/d58bbf47","DOI":"10.24381\/d58bbf47"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u20107\u20104367\u20102014"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asr.2022.09.010"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u20108\u20107389\u20102008"},{"key":"e_1_2_9_12_1","unstructured":"FengYun\u2010AIR. (2026).CO NH3 and HCOOH retrieval data[Dataset].FengYun satellite Atmospheric composition Infrared Retrieval (FY\u2010AIR) data portal. Retrieved fromhttps:\/\/fengyunair.github.io\/data.html"},{"key":"e_1_2_9_13_1","unstructured":"FengYun Satellite Data Center. (2026).FY\u20104B\/GIIRS Level 1 data[Dataset].FengYun Satellite Data Center. Retrieved fromhttps:\/\/data.nsmc.org.cn\/DataPortal\/en\/home\/index.html"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1029\/2018JD029633"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1029\/2025GL115286"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10533\u2010004\u20100370\u20100"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/2013JD020344"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/qj.3803"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1029\/1999JD901173"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS\u2010D\u201019\u20100304.1"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2025.114829"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u201019\u20104013\u20102026"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u201019\u20103515\u20102019"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1029\/2024JH000432"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1029\/2020MS002413"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS\u2010D\u201021\u20100328.1"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.3788\/AOS202242.0630001"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1029\/2025JH000648"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u201015\u20106283\u20102015"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u201011\u2010857\u20102011"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1029\/2002JD002299"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1175\/2007JAMC1590.1"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u201026\u20107803\u20102026"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1174760"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u201014\u20102013\u20102021"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u20109\u20104897\u20102009"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u201010\u20104905\u20102017"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010020\u20102664\u20103"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u201019\u20103095\u20102026"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/2016JD024828"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u201013\u2010837\u20102013"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2959830"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1029\/2025JD046036"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS\u2010D\u201016\u20100065.1"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jqsrt.2024.109336"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1029\/2024JD041352"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u201016\u20103059\u20102023"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.5194\/amt\u201016\u20103693\u20102023"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1029\/2024JH000409"}],"container-title":["Journal of Geophysical Research: Machine Learning and Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2026JH001562","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/full-xml\/10.1029\/2026JH001562","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2026JH001562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T02:41:49Z","timestamp":1788144109000},"score":1,"resource":{"primary":{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/10.1029\/2026JH001562"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,30]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1029\/2026JH001562"],"URL":"https:\/\/doi.org\/10.1029\/2026jh001562","archive":["Portico"],"relation":{},"ISSN":["2993-5210","2993-5210"],"issn-type":[{"value":"2993-5210","type":"print"},{"value":"2993-5210","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,30]]},"assertion":[{"value":"2026-06-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2026JH001562"}}